{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/scene-understanding","name":"Scene Understanding","slug":"scene-understanding","description_markdown":"Scene understanding involves interpreting the visual information of a scene, including objects, their spatial relationships, and the overall layout. It goes beyond simple object recognition by considering the context and how objects relate to each other and the environment.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1723,"papers_with_code":720,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":43,"subtasks":6,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/scene-understanding-on-semantic-scene","slug":"scene-understanding-on-semantic-scene","dataset":"Semantic Scene Understanding Challenge (passive actuation & ground-truth localisation)","dataset_url":null,"rows_in_archive":3,"metrics":["OMQ","avg_pairwise","avg_label","avg_spatial","avg_fp_quality"],"first_row_in_archive_order":{"model":"ACRV Baseline","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/scene-understanding-on-ade20k-val-1","slug":"scene-understanding-on-ade20k-val-1","dataset":"ADE20K val","dataset_url":"/dataset/ade20k","rows_in_archive":1,"metrics":["Mean IoU"],"first_row_in_archive_order":{"model":"CPN(ResNet-101)","paper_title":"Context Prior for Scene Segmentation","paper_url":"/paper/context-prior-for-scene-segmentation","paper_date":"2020-04-03","arxiv_id":"2004.01547","code_links":[{"title":"ycszen/ContextPrior","url":"https://github.com/ycszen/ContextPrior"},{"title":"AndPuQing/ContextPrior_Paddle","url":"https://github.com/AndPuQing/ContextPrior_Paddle"}],"syntology":null}},{"leaderboard":"/sota/scene-understanding-on-semantic-scene-1","slug":"scene-understanding-on-semantic-scene-1","dataset":"Semantic Scene Understanding Challenge (active actuation & ground-truth localisation)","dataset_url":null,"rows_in_archive":1,"metrics":["OMQ","avg_pairwise","avg_label","avg_spatial","avg_fp_quality"],"first_row_in_archive_order":{"model":"ACRV Baseline","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/ade20k","name":"ADE20K","full_name":"","num_papers_in_archive":1213},{"url":"/dataset/rellis-3d","name":"RELLIS-3D","full_name":null,"num_papers_in_archive":57},{"url":"/dataset/uavid","name":"UAVid","full_name":"","num_papers_in_archive":54},{"url":"/dataset/music-avqa","name":"MUSIC-AVQA","full_name":"","num_papers_in_archive":51},{"url":"/dataset/3r-scan","name":"3RScan","full_name":"","num_papers_in_archive":44},{"url":"/dataset/kitti-road","name":"KITTI Road","full_name":"","num_papers_in_archive":41},{"url":"/dataset/suim","name":"SUIM","full_name":"Segmentation of Underwater IMagery","num_papers_in_archive":34},{"url":"/dataset/sensaturban","name":"SensatUrban","full_name":"","num_papers_in_archive":28},{"url":"/dataset/radiate","name":"RADIATE","full_name":"RAdar Dataset In Adverse weaThEr","num_papers_in_archive":24},{"url":"/dataset/toronto-3d","name":"Toronto-3D","full_name":null,"num_papers_in_archive":24},{"url":"/dataset/shapestacks","name":"ShapeStacks","full_name":"","num_papers_in_archive":22},{"url":"/dataset/mlrsnet","name":"MLRSNet","full_name":"","num_papers_in_archive":17},{"url":"/dataset/scenenet","name":"SceneNet","full_name":"SceneNet","num_papers_in_archive":17},{"url":"/dataset/dada-2000","name":"DADA-2000","full_name":"","num_papers_in_archive":16},{"url":"/dataset/dublincity","name":"DublinCity","full_name":"","num_papers_in_archive":15},{"url":"/dataset/irs","name":"IRS","full_name":"Indoor Robotics Stereo","num_papers_in_archive":12},{"url":"/dataset/dawn","name":"DAWN","full_name":"","num_papers_in_archive":10},{"url":"/dataset/deepscores","name":"DeepScores","full_name":"","num_papers_in_archive":10},{"url":"/dataset/airs","name":"AIRS","full_name":"","num_papers_in_archive":9},{"url":"/dataset/pascal-panoptic-parts","name":"Pascal Panoptic Parts","full_name":"","num_papers_in_archive":9},{"url":"/dataset/psi-ava","name":"PSI-AVA","full_name":"","num_papers_in_archive":9},{"url":"/dataset/cityscapes-panoptic-parts","name":"Cityscapes Panoptic Parts","full_name":"","num_papers_in_archive":8},{"url":"/dataset/deeploc","name":"DeepLoc","full_name":"DeepLoc","num_papers_in_archive":8},{"url":"/dataset/synpick","name":"SynPick","full_name":"","num_papers_in_archive":7},{"url":"/dataset/a-large-dataset-of-object-scans","name":"A Large Dataset of Object Scans","full_name":"A Large Dataset of Object Scans","num_papers_in_archive":5},{"url":"/dataset/hhoi","name":"HHOI","full_name":"","num_papers_in_archive":5},{"url":"/dataset/sel","name":"SEL","full_name":"","num_papers_in_archive":5},{"url":"/dataset/www-crowd","name":"WWW Crowd","full_name":"WWW Crowd","num_papers_in_archive":5},{"url":"/dataset/aerorit","name":"AeroRIT","full_name":"","num_papers_in_archive":4},{"url":"/dataset/cds2k","name":"CDS2K","full_name":"","num_papers_in_archive":4},{"url":"/dataset/videonavqa","name":"VideoNavQA","full_name":"","num_papers_in_archive":4},{"url":"/dataset/mlm","name":"MLM","full_name":"","num_papers_in_archive":3},{"url":"/dataset/mod","name":"MOD++","full_name":"","num_papers_in_archive":3},{"url":"/dataset/raileye3d-dataset","name":"RailEye3D Dataset","full_name":"","num_papers_in_archive":3},{"url":"/dataset/instaorder","name":"InstaOrder","full_name":"","num_papers_in_archive":2},{"url":"/dataset/stanford-ecm","name":"Stanford-ECM","full_name":"Stanford-ECM","num_papers_in_archive":2},{"url":"/dataset/3threedworld","name":"3ThreeDWorld","full_name":"3ThreeDWorld","num_papers_in_archive":1},{"url":"/dataset/apron-dataset","name":"Apron Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/coqe","name":"COQE","full_name":"Containers Of liQuid contEnt","num_papers_in_archive":1},{"url":"/dataset/deeploccross","name":"DeepLocCross","full_name":"DeepLocCross","num_papers_in_archive":1},{"url":"/dataset/indoor-and-outdoor-dfd-dataset","name":"Indoor and outdoor DFD dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/navigationnet","name":"NavigationNet","full_name":"","num_papers_in_archive":1},{"url":"/dataset/panoramic-video-panoptic-segmentation-dataset","name":"Panoramic Video Panoptic Segmentation Dataset","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/3d-room-layouts-from-a-single-rgb-panorama","name":"3D Room Layouts From A Single RGB Panorama"},{"url":"/task/light-source-estimation","name":"Outdoor Light Source Estimation"},{"url":"/task/lighting-estimation","name":"Lighting Estimation"},{"url":"/task/road-scene-understanding","name":"road scene understanding"},{"url":"/task/video-semantic-segmentation","name":"Video Semantic Segmentation"},{"url":"/task/visual-relationship-detection","name":"Visual Relationship Detection"}],"parent_tasks":[{"url":"/task/scene-parsing","name":"Scene Parsing"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":18,"rows_per_page":100,"shown":100,"of":1723,"of_with_code":720,"tagged_in_all":1723,"counts":{"archive_papers_tagged":1723,"with_a_code_link":720,"where_syntology_ran_a_sample":208,"not_listed_spam_title":0,"listed":1723,"listed_where_code_ran":208,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":174,"every_run_a_failure_of_syntologys_instrument":34,"listed_with_a_run_with_no_instrument_failure":174,"listed_every_run_a_failure_of_syntologys_instrument":34,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/segnet-a-deep-convolutional-encoder-decoder","slug":"segnet-a-deep-convolutional-encoder-decoder","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","date":"2015-11-02","arxiv_id":"1511.00561","repositories_listed":74,"syntology":{"n":44,"n_ran":22,"n_constructed":0,"n_ran_checked":14,"n_instrument":8,"n_unverified":22,"n_honours":1,"n_violates":0,"n_no_contract":13,"n_pointer_only":11,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified","sample_list":"/paper/segnet-a-deep-convolutional-encoder-decoder#ran","syntology_url":"https://syntology.ai/paper/1511.00561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.00561"}},"official":null}},{"url":"/paper/microsoft-coco-common-objects-in-context","slug":"microsoft-coco-common-objects-in-context","title":"Microsoft COCO: Common Objects in Context","date":"2014-05-01","arxiv_id":"1405.0312","repositories_listed":38,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/microsoft-coco-common-objects-in-context#ran","syntology_url":"https://syntology.ai/paper/1405.0312","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1405.0312"}},"official":null}},{"url":"/paper/unified-perceptual-parsing-for-scene","slug":"unified-perceptual-parsing-for-scene","title":"Unified Perceptual Parsing for Scene Understanding","date":"2018-07-26","arxiv_id":"1807.10221","repositories_listed":25,"syntology":{"n":28,"n_ran":25,"n_constructed":0,"n_ran_checked":14,"n_instrument":11,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":12,"n_pointer_only":10,"phrase":"25 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 11 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unified-perceptual-parsing-for-scene#ran","syntology_url":"https://syntology.ai/paper/1807.10221","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.10221"}},"official":{"repos":["CSAILVision/unifiedparsing"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/bayesian-segnet-model-uncertainty-in-deep","slug":"bayesian-segnet-model-uncertainty-in-deep","title":"Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding","date":"2015-11-09","arxiv_id":"1511.02680","repositories_listed":21,"syntology":{"n":18,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":12,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/bayesian-segnet-model-uncertainty-in-deep#ran","syntology_url":"https://syntology.ai/paper/1511.02680","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.02680"}},"official":null}},{"url":"/paper/digging-into-self-supervised-monocular-depth","slug":"digging-into-self-supervised-monocular-depth","title":"Digging Into Self-Supervised Monocular Depth Estimation","date":"2018-06-04","arxiv_id":"1806.01260","repositories_listed":15,"syntology":{"n":24,"n_ran":23,"n_constructed":0,"n_ran_checked":13,"n_instrument":10,"n_unverified":1,"n_honours":4,"n_violates":1,"n_no_contract":8,"n_pointer_only":10,"phrase":"23 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 4 honoured, 1 violated, 8 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/digging-into-self-supervised-monocular-depth#ran","syntology_url":"https://syntology.ai/paper/1806.01260","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.01260"}},"official":{"repos":["nianticlabs/monodepth2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/linknet-exploiting-encoder-representations","slug":"linknet-exploiting-encoder-representations","title":"LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation","date":"2017-06-14","arxiv_id":"1707.03718","repositories_listed":14,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/linknet-exploiting-encoder-representations#ran","syntology_url":"https://syntology.ai/paper/1707.03718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.03718"}},"official":null}},{"url":"/paper/erfnet-efficient-residual-factorized-convnet","slug":"erfnet-efficient-residual-factorized-convnet","title":"ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation","date":"2017-10-09","arxiv_id":null,"repositories_listed":13,"syntology":null},{"url":"/paper/spatial-as-deep-spatial-cnn-for-traffic-scene","slug":"spatial-as-deep-spatial-cnn-for-traffic-scene","title":"Spatial As Deep: Spatial CNN for Traffic Scene Understanding","date":"2017-12-17","arxiv_id":"1712.06080","repositories_listed":9,"syntology":null},{"url":"/paper/decentralized-distributed-ppo-solving","slug":"decentralized-distributed-ppo-solving","title":"DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames","date":"2019-11-01","arxiv_id":"1911.00357","repositories_listed":8,"syntology":null},{"url":"/paper/floodnet-a-high-resolution-aerial-imagery","slug":"floodnet-a-high-resolution-aerial-imagery","title":"FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding","date":"2020-12-05","arxiv_id":"2012.02951","repositories_listed":7,"syntology":null},{"url":"/paper/resunet-a-a-deep-learning-framework-for","slug":"resunet-a-a-deep-learning-framework-for","title":"ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data","date":"2019-04-01","arxiv_id":"1904.00592","repositories_listed":7,"syntology":{"n":13,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/resunet-a-a-deep-learning-framework-for#ran","syntology_url":"https://syntology.ai/paper/1904.00592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.00592"}},"official":{"repos":["Nguyendat-bit/U-net"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]}}},{"url":"/paper/multi-task-learning-as-multi-objective","slug":"multi-task-learning-as-multi-objective","title":"Multi-Task Learning as Multi-Objective Optimization","date":"2018-10-10","arxiv_id":"1810.04650","repositories_listed":7,"syntology":{"n":19,"n_ran":17,"n_constructed":0,"n_ran_checked":15,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":1,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multi-task-learning-as-multi-objective#ran","syntology_url":"https://syntology.ai/paper/1810.04650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.04650"}},"official":{"repos":["IntelVCL/MultiObjectiveOptimization"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/groupvit-semantic-segmentation-emerges-from","slug":"groupvit-semantic-segmentation-emerges-from","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","date":"2022-02-22","arxiv_id":"2202.11094","repositories_listed":6,"syntology":null},{"url":"/paper/part-a2-net-3d-part-aware-and-aggregation","slug":"part-a2-net-3d-part-aware-and-aggregation","title":"From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network","date":"2019-07-08","arxiv_id":"1907.03670","repositories_listed":6,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/part-a2-net-3d-part-aware-and-aggregation#ran","syntology_url":"https://syntology.ai/paper/1907.03670","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.03670"}},"official":{"repos":["sshaoshuai/PointCloudDet3D"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-path-segmentation-network","slug":"multi-path-segmentation-network","title":"ShelfNet for Fast Semantic Segmentation","date":"2018-11-27","arxiv_id":"1811.11254","repositories_listed":6,"syntology":null},{"url":"/paper/boundary-seeking-generative-adversarial","slug":"boundary-seeking-generative-adversarial","title":"Boundary-Seeking Generative Adversarial Networks","date":"2017-02-27","arxiv_id":"1702.08431","repositories_listed":6,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/boundary-seeking-generative-adversarial#ran","syntology_url":"https://syntology.ai/paper/1702.08431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.08431"}},"official":null}},{"url":"/paper/towards-ghost-free-shadow-removal-via-dual","slug":"towards-ghost-free-shadow-removal-via-dual","title":"Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN","date":"2019-11-20","arxiv_id":"1911.08718","repositories_listed":5,"syntology":null},{"url":"/paper/a-dataset-for-semantic-segmentation-of-point","slug":"a-dataset-for-semantic-segmentation-of-point","title":"SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences","date":"2019-04-02","arxiv_id":"1904.01416","repositories_listed":5,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-dataset-for-semantic-segmentation-of-point#ran","syntology_url":"https://syntology.ai/paper/1904.01416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01416"}},"official":{"repos":["PRBonn/semantic-kitti-api"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/adapting-deep-network-features-to-capture","slug":"adapting-deep-network-features-to-capture","title":"Adapting Deep Network Features to Capture Psychological Representations","date":"2016-08-06","arxiv_id":"1608.02164","repositories_listed":5,"syntology":null},{"url":"/paper/repurposing-diffusion-based-image-generators","slug":"repurposing-diffusion-based-image-generators","title":"Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation","date":"2023-12-04","arxiv_id":"2312.02145","repositories_listed":4,"syntology":{"n":26,"n_ran":22,"n_constructed":0,"n_ran_checked":17,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":3,"n_no_contract":14,"n_pointer_only":5,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 3 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/repurposing-diffusion-based-image-generators#ran","syntology_url":"https://syntology.ai/paper/2312.02145","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02145"}},"official":{"repos":["prs-eth/marigold"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/panopticndt-efficient-and-robust-panoptic","slug":"panopticndt-efficient-and-robust-panoptic","title":"PanopticNDT: Efficient and Robust Panoptic Mapping","date":"2023-09-24","arxiv_id":"2309.13635","repositories_listed":4,"syntology":{"n":12,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/panopticndt-efficient-and-robust-panoptic#ran","syntology_url":"https://syntology.ai/paper/2309.13635","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.13635"}},"official":{"repos":["tui-nicr/panoptic-mapping"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/p2t-pyramid-pooling-transformer-for-scene","slug":"p2t-pyramid-pooling-transformer-for-scene","title":"P2T: Pyramid Pooling Transformer for Scene Understanding","date":"2021-06-22","arxiv_id":"2106.12011","repositories_listed":4,"syntology":null},{"url":"/paper/multi-view-radar-semantic-segmentation","slug":"multi-view-radar-semantic-segmentation","title":"Multi-View Radar Semantic Segmentation","date":"2021-03-30","arxiv_id":"2103.16214","repositories_listed":4,"syntology":{"n":13,"n_ran":9,"n_constructed":7,"n_ran_checked":7,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":13,"phrase":"9 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/multi-view-radar-semantic-segmentation#ran","syntology_url":"https://syntology.ai/paper/2103.16214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.16214"}},"official":{"repos":["valeoai/MVRSS"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/tracking-pedestrian-heads-in-dense-crowd","slug":"tracking-pedestrian-heads-in-dense-crowd","title":"Tracking Pedestrian Heads in Dense Crowd","date":"2021-03-24","arxiv_id":"2103.13516","repositories_listed":4,"syntology":null},{"url":"/paper/cityscapes-panoptic-parts-and-pascal-panoptic","slug":"cityscapes-panoptic-parts-and-pascal-panoptic","title":"Cityscapes-Panoptic-Parts and PASCAL-Panoptic-Parts datasets for Scene Understanding","date":"2020-04-16","arxiv_id":"2004.07944","repositories_listed":4,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/cityscapes-panoptic-parts-and-pascal-panoptic#ran","syntology_url":"https://syntology.ai/paper/2004.07944","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.07944"}},"official":{"repos":["tue-mps/panoptic_parts"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/pointgroup-dual-set-point-grouping-for-3d","slug":"pointgroup-dual-set-point-grouping-for-3d","title":"PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation","date":"2020-04-03","arxiv_id":"2004.01658","repositories_listed":4,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pointgroup-dual-set-point-grouping-for-3d#ran","syntology_url":"https://syntology.ai/paper/2004.01658","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.01658"}},"official":null}},{"url":"/paper/visual-semantic-graph-attention-network-for","slug":"visual-semantic-graph-attention-network-for","title":"Visual-Semantic Graph Attention Networks for Human-Object Interaction Detection","date":"2020-01-07","arxiv_id":"2001.02302","repositories_listed":4,"syntology":null},{"url":"/paper/language-based-colorization-of-scene-sketches","slug":"language-based-colorization-of-scene-sketches","title":"Language-based Colorization of Scene Sketches","date":"2019-11-17","arxiv_id":null,"repositories_listed":4,"syntology":null},{"url":"/paper/m3d-rpn-monocular-3d-region-proposal-network","slug":"m3d-rpn-monocular-3d-region-proposal-network","title":"M3D-RPN: Monocular 3D Region Proposal Network for Object Detection","date":"2019-07-13","arxiv_id":"1907.06038","repositories_listed":4,"syntology":{"n":21,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":12,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/m3d-rpn-monocular-3d-region-proposal-network#ran","syntology_url":"https://syntology.ai/paper/1907.06038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.06038"}},"official":{"repos":["garrickbrazil/M3D-RPN"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":10,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/multi-resolution-multi-modal-sensor-fusion","slug":"multi-resolution-multi-modal-sensor-fusion","title":"Multi-Resolution Multi-Modal Sensor Fusion For Remote Sensing Data With Label Uncertainty","date":"2018-05-02","arxiv_id":"1805.00930","repositories_listed":4,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multi-resolution-multi-modal-sensor-fusion#ran","syntology_url":"https://syntology.ai/paper/1805.00930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.00930"}},"official":{"repos":["GatorSense/MIMRF"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/tensor-comprehensions-framework-agnostic-high","slug":"tensor-comprehensions-framework-agnostic-high","title":"Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions","date":"2018-02-13","arxiv_id":"1802.04730","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tensor-comprehensions-framework-agnostic-high#ran","syntology_url":"https://syntology.ai/paper/1802.04730","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.04730"}},"official":null}},{"url":"/paper/joint-2d-3d-semantic-data-for-indoor-scene","slug":"joint-2d-3d-semantic-data-for-indoor-scene","title":"Joint 2D-3D-Semantic Data for Indoor Scene Understanding","date":"2017-02-03","arxiv_id":"1702.01105","repositories_listed":4,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":1,"n_honours":3,"n_violates":3,"n_no_contract":5,"n_pointer_only":4,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 3 honoured, 3 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/joint-2d-3d-semantic-data-for-indoor-scene#ran","syntology_url":"https://syntology.ai/paper/1702.01105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.01105"}},"official":{"repos":["alexsax/2D-3D-Semantics"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/coco-text-dataset-and-benchmark-for-text","slug":"coco-text-dataset-and-benchmark-for-text","title":"COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images","date":"2016-01-26","arxiv_id":"1601.07140","repositories_listed":4,"syntology":null},{"url":"/paper/iam-enhancing-rgb-d-instance-segmentation","slug":"iam-enhancing-rgb-d-instance-segmentation","title":"IAM: Enhancing RGB-D Instance Segmentation with New Benchmarks","date":"2025-01-03","arxiv_id":"2501.01685","repositories_listed":3,"syntology":null},{"url":"/paper/root-vlm-based-system-for-indoor-scene","slug":"root-vlm-based-system-for-indoor-scene","title":"ROOT: VLM based System for Indoor Scene Understanding and Beyond","date":"2024-11-24","arxiv_id":"2411.15714","repositories_listed":3,"syntology":null},{"url":"/paper/on-deep-learning-for-geometric-and-semantic","slug":"on-deep-learning-for-geometric-and-semantic","title":"On Deep Learning for Geometric and Semantic Scene Understanding Using On-Vehicle 3D LiDAR","date":"2024-11-01","arxiv_id":"2411.00600","repositories_listed":3,"syntology":null},{"url":"/paper/4d-panoptic-scene-graph-generation-1","slug":"4d-panoptic-scene-graph-generation-1","title":"4D Panoptic Scene Graph Generation","date":"2024-05-16","arxiv_id":"2405.10305","repositories_listed":3,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":1,"n_honours":3,"n_violates":1,"n_no_contract":5,"n_pointer_only":10,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 1 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/4d-panoptic-scene-graph-generation-1#ran","syntology_url":"https://syntology.ai/paper/2405.10305","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.10305"}},"official":{"repos":["jingkang50/psg4d","Jingkang50/OpenPSG","jingkang50/openpvsg"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/prismatic-vlms-investigating-the-design-space","slug":"prismatic-vlms-investigating-the-design-space","title":"Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models","date":"2024-02-12","arxiv_id":"2402.07865","repositories_listed":3,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/prismatic-vlms-investigating-the-design-space#ran","syntology_url":"https://syntology.ai/paper/2402.07865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07865"}},"official":{"repos":["tri-ml/prismatic-vlms","tri-ml/vlm-evaluation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/pixel-wise-recognition-for-holistic-surgical","slug":"pixel-wise-recognition-for-holistic-surgical","title":"Pixel-Wise Recognition for Holistic Surgical Scene Understanding","date":"2024-01-20","arxiv_id":"2401.11174","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":6,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/pixel-wise-recognition-for-holistic-surgical#ran","syntology_url":"https://syntology.ai/paper/2401.11174","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.11174"}},"official":{"repos":["bcv-uniandes/grasp","bcv-uniandes/matis","bcv-uniandes/tapir"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/panoptic-video-scene-graph-generation-1","slug":"panoptic-video-scene-graph-generation-1","title":"Panoptic Video Scene Graph Generation","date":"2023-11-28","arxiv_id":"2311.17058","repositories_listed":3,"syntology":{"n":11,"n_ran":11,"n_constructed":2,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":3,"phrase":"11 ran (of which 2 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/panoptic-video-scene-graph-generation-1#ran","syntology_url":"https://syntology.ai/paper/2311.17058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17058"}},"official":{"repos":["jingkang50/openpvsg","lilydaytoy/openpvsg","lilydaytoy/pvsgannotation"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":2,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hoc-search-efficient-cad-model-and-pose","slug":"hoc-search-efficient-cad-model-and-pose","title":"HOC-Search: Efficient CAD Model and Pose Retrieval from RGB-D Scans","date":"2023-09-12","arxiv_id":"2309.06107","repositories_listed":3,"syntology":null},{"url":"/paper/sgdraw-scene-graph-drawing-interface-using","slug":"sgdraw-scene-graph-drawing-interface-using","title":"SGDraw: Scene Graph Drawing Interface Using Object-Oriented Representation","date":"2022-11-30","arxiv_id":"2211.16697","repositories_listed":3,"syntology":null},{"url":"/paper/cenet-toward-concise-and-efficient-lidar","slug":"cenet-toward-concise-and-efficient-lidar","title":"CENet: Toward Concise and Efficient LiDAR Semantic Segmentation for Autonomous Driving","date":"2022-07-26","arxiv_id":"2207.12691","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/cenet-toward-concise-and-efficient-lidar#ran","syntology_url":"https://syntology.ai/paper/2207.12691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.12691"}},"official":{"repos":["huixiancheng/cenet"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/mcts-with-refinement-for-proposals-selection","slug":"mcts-with-refinement-for-proposals-selection","title":"MCTS with Refinement for Proposals Selection Games in Scene Understanding","date":"2022-07-07","arxiv_id":"2207.03204","repositories_listed":3,"syntology":null},{"url":"/paper/collaborative-transformers-for-grounded","slug":"collaborative-transformers-for-grounded","title":"Collaborative Transformers for Grounded Situation Recognition","date":"2022-03-30","arxiv_id":"2203.16518","repositories_listed":3,"syntology":{"n":7,"n_ran":5,"n_constructed":3,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/collaborative-transformers-for-grounded#ran","syntology_url":"https://syntology.ai/paper/2203.16518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16518"}},"official":{"repos":["jhcho99/coformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/hake-a-knowledge-engine-foundation-for-human","slug":"hake-a-knowledge-engine-foundation-for-human","title":"HAKE: A Knowledge Engine Foundation for Human Activity Understanding","date":"2022-02-14","arxiv_id":"2202.06851","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/hake-a-knowledge-engine-foundation-for-human#ran","syntology_url":"https://syntology.ai/paper/2202.06851","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.06851"}},"official":{"repos":["DirtyHarryLYL/HAKE-Action-Torch"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/transformer-in-convolutional-neural-networks","slug":"transformer-in-convolutional-neural-networks","title":"Vision Transformers with Hierarchical Attention","date":"2021-06-06","arxiv_id":"2106.03180","repositories_listed":3,"syntology":null},{"url":"/paper/rellis-3d-dataset-data-benchmarks-and","slug":"rellis-3d-dataset-data-benchmarks-and","title":"RELLIS-3D Dataset: Data, Benchmarks and Analysis","date":"2020-11-17","arxiv_id":"2011.12954","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rellis-3d-dataset-data-benchmarks-and#ran","syntology_url":"https://syntology.ai/paper/2011.12954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.12954"}},"official":{"repos":["unmannedlab/RELLIS-3D"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/semi-supervised-learning-for-multi-task-scene","slug":"semi-supervised-learning-for-multi-task-scene","title":"Semi-Supervised Learning for Multi-Task Scene Understanding by Neural Graph Consensus","date":"2020-10-02","arxiv_id":"2010.01086","repositories_listed":3,"syntology":null},{"url":"/paper/semantic-segmentation-of-underwater-imagery","slug":"semantic-segmentation-of-underwater-imagery","title":"Semantic Segmentation of Underwater Imagery: Dataset and Benchmark","date":"2020-04-02","arxiv_id":"2004.01241","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/semantic-segmentation-of-underwater-imagery#ran","syntology_url":"https://syntology.ai/paper/2004.01241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.01241"}},"official":null}},{"url":"/paper/underwater-image-super-resolution-using-deep","slug":"underwater-image-super-resolution-using-deep","title":"Underwater Image Super-Resolution using Deep Residual Multipliers","date":"2019-09-20","arxiv_id":"1909.09437","repositories_listed":3,"syntology":null},{"url":"/paper/the-uavid-dataset-for-video-semantic","slug":"the-uavid-dataset-for-video-semantic","title":"UAVid: A Semantic Segmentation Dataset for UAV Imagery","date":"2018-10-24","arxiv_id":"1810.10438","repositories_listed":3,"syntology":null},{"url":"/paper/bold5000-a-public-fmri-dataset-of-5000-images","slug":"bold5000-a-public-fmri-dataset-of-5000-images","title":"BOLD5000: A public fMRI dataset of 5000 images","date":"2018-09-05","arxiv_id":"1809.01281","repositories_listed":3,"syntology":null},{"url":"/paper/single-shot-scene-text-retrieval","slug":"single-shot-scene-text-retrieval","title":"Single Shot Scene Text Retrieval","date":"2018-08-27","arxiv_id":"1808.09044","repositories_listed":3,"syntology":null},{"url":"/paper/auxiliary-tasks-in-multi-task-learning","slug":"auxiliary-tasks-in-multi-task-learning","title":"Auxiliary Tasks in Multi-task Learning","date":"2018-05-16","arxiv_id":"1805.06334","repositories_listed":3,"syntology":null},{"url":"/paper/efficient-convnet-for-real-time-semantic","slug":"efficient-convnet-for-real-time-semantic","title":"Efficient ConvNet for Real-time Semantic Segmentation","date":"2017-06-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/dilated-residual-networks","slug":"dilated-residual-networks","title":"Dilated Residual Networks","date":"2017-05-28","arxiv_id":"1705.09914","repositories_listed":3,"syntology":null},{"url":"/paper/the-cityscapes-dataset-for-semantic-urban","slug":"the-cityscapes-dataset-for-semantic-urban","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","date":"2016-04-06","arxiv_id":"1604.01685","repositories_listed":3,"syntology":null},{"url":"/paper/iref-vla-a-benchmark-for-interactive","slug":"iref-vla-a-benchmark-for-interactive","title":"IRef-VLA: A Benchmark for Interactive Referential Grounding with Imperfect Language in 3D Scenes","date":"2025-03-20","arxiv_id":"2503.17406","repositories_listed":2,"syntology":null},{"url":"/paper/a-survey-of-world-models-for-autonomous","slug":"a-survey-of-world-models-for-autonomous","title":"A Survey of World Models for Autonomous Driving","date":"2025-01-20","arxiv_id":"2501.11260","repositories_listed":2,"syntology":null},{"url":"/paper/crossmodalitydiffusion-multi-modal-novel-view","slug":"crossmodalitydiffusion-multi-modal-novel-view","title":"CrossModalityDiffusion: Multi-Modal Novel View Synthesis with Unified Intermediate Representation","date":"2025-01-16","arxiv_id":"2501.09838","repositories_listed":2,"syntology":null},{"url":"/paper/embodiedocc-embodied-3d-occupancy-prediction","slug":"embodiedocc-embodied-3d-occupancy-prediction","title":"EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding","date":"2024-12-05","arxiv_id":"2412.04380","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/embodiedocc-embodied-3d-occupancy-prediction#ran","syntology_url":"https://syntology.ai/paper/2412.04380","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.04380"}},"official":{"repos":["ykiwu/embodiedocc"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/procedure-aware-surgical-video-language","slug":"procedure-aware-surgical-video-language","title":"Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation","date":"2024-09-30","arxiv_id":"2410.00263","repositories_listed":2,"syntology":{"n":15,"n_ran":9,"n_constructed":1,"n_ran_checked":7,"n_instrument":2,"n_unverified":6,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":15,"phrase":"9 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/procedure-aware-surgical-video-language#ran","syntology_url":"https://syntology.ai/paper/2410.00263","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00263"}},"official":null}},{"url":"/paper/hierarchical-spatial-proximity-reasoning-for","slug":"hierarchical-spatial-proximity-reasoning-for","title":"Hierarchical Spatial Proximity Reasoning for Vision-and-Language Navigation","date":"2024-03-18","arxiv_id":"2403.11541","repositories_listed":2,"syntology":null},{"url":"/paper/chat-3d-v2-bridging-3d-scene-and-large","slug":"chat-3d-v2-bridging-3d-scene-and-large","title":"Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers","date":"2023-12-13","arxiv_id":"2312.08168","repositories_listed":2,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/chat-3d-v2-bridging-3d-scene-and-large#ran","syntology_url":"https://syntology.ai/paper/2312.08168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08168"}},"official":{"repos":["chat-3d/chat-3d-v2"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/splatam-splat-track-map-3d-gaussians-for","slug":"splatam-splat-track-map-3d-gaussians-for","title":"SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM","date":"2023-12-04","arxiv_id":"2312.02126","repositories_listed":2,"syntology":null},{"url":"/paper/learning-point-wise-abstaining-penalty-for","slug":"learning-point-wise-abstaining-penalty-for","title":"LiON: Learning Point-wise Abstaining Penalty for LiDAR Outlier DetectioN Using Diverse Synthetic Data","date":"2023-09-19","arxiv_id":"2309.10230","repositories_listed":2,"syntology":null},{"url":"/paper/chat-3d-data-efficiently-tuning-large","slug":"chat-3d-data-efficiently-tuning-large","title":"Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes","date":"2023-08-17","arxiv_id":"2308.08769","repositories_listed":2,"syntology":null},{"url":"/paper/oafuser-towards-omni-aperture-fusion-for","slug":"oafuser-towards-omni-aperture-fusion-for","title":"OAFuser: Towards Omni-Aperture Fusion for Light Field Semantic Segmentation","date":"2023-07-28","arxiv_id":"2307.15588","repositories_listed":2,"syntology":null},{"url":"/paper/bi-level-dynamic-learning-for-jointly-multi","slug":"bi-level-dynamic-learning-for-jointly-multi","title":"Bi-level Dynamic Learning for Jointly Multi-modality Image Fusion and Beyond","date":"2023-05-11","arxiv_id":"2305.06720","repositories_listed":2,"syntology":null},{"url":"/paper/learning-how-to-robustly-estimate-camera-pose","slug":"learning-how-to-robustly-estimate-camera-pose","title":"Learning How To Robustly Estimate Camera Pose in Endoscopic Videos","date":"2023-04-17","arxiv_id":"2304.08023","repositories_listed":2,"syntology":null},{"url":"/paper/swin3d-a-pretrained-transformer-backbone-for","slug":"swin3d-a-pretrained-transformer-backbone-for","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","date":"2023-04-14","arxiv_id":"2304.06906","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/swin3d-a-pretrained-transformer-backbone-for#ran","syntology_url":"https://syntology.ai/paper/2304.06906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.06906"}},"official":{"repos":["microsoft/swin3d"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/idisc-internal-discretization-for-monocular","slug":"idisc-internal-discretization-for-monocular","title":"iDisc: Internal Discretization for Monocular Depth Estimation","date":"2023-04-13","arxiv_id":"2304.06334","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":2,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/idisc-internal-discretization-for-monocular#ran","syntology_url":"https://syntology.ai/paper/2304.06334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.06334"}},"official":{"repos":["SysCV/idisc"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/surroundocc-multi-camera-3d-occupancy","slug":"surroundocc-multi-camera-3d-occupancy","title":"SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving","date":"2023-03-16","arxiv_id":"2303.09551","repositories_listed":2,"syntology":{"n":24,"n_ran":18,"n_constructed":0,"n_ran_checked":8,"n_instrument":10,"n_unverified":6,"n_honours":4,"n_violates":0,"n_no_contract":4,"n_pointer_only":21,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 0 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/surroundocc-multi-camera-3d-occupancy#ran","syntology_url":"https://syntology.ai/paper/2303.09551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09551"}},"official":{"repos":["weiyithu/surroundocc"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/galip-generative-adversarial-clips-for-text","slug":"galip-generative-adversarial-clips-for-text","title":"GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis","date":"2023-01-30","arxiv_id":"2301.12959","repositories_listed":2,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/galip-generative-adversarial-clips-for-text#ran","syntology_url":"https://syntology.ai/paper/2301.12959","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12959"}},"official":{"repos":["tobran/galip"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/diffusion-based-generation-optimization-and","slug":"diffusion-based-generation-optimization-and","title":"Diffusion-based Generation, Optimization, and Planning in 3D Scenes","date":"2023-01-15","arxiv_id":"2301.06015","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":4,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/diffusion-based-generation-optimization-and#ran","syntology_url":"https://syntology.ai/paper/2301.06015","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.06015"}},"official":{"repos":["scenediffuser/Scene-Diffuser"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/peakconv-learning-peak-receptive-field-for","slug":"peakconv-learning-peak-receptive-field-for","title":"PeakConv: Learning Peak Receptive Field for Radar Semantic Segmentation","date":"2023-01-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/dynamic-graph-message-passing-networks-for","slug":"dynamic-graph-message-passing-networks-for","title":"Dynamic Graph Message Passing Networks for Visual Recognition","date":"2022-09-20","arxiv_id":"2209.09760","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-multi-task-rgb-d-scene-analysis-for","slug":"efficient-multi-task-rgb-d-scene-analysis-for","title":"Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments","date":"2022-07-10","arxiv_id":"2207.04526","repositories_listed":2,"syntology":null},{"url":"/paper/mgnet-monocular-geometric-scene-understanding-1","slug":"mgnet-monocular-geometric-scene-understanding-1","title":"MGNet: Monocular Geometric Scene Understanding for Autonomous Driving","date":"2022-06-27","arxiv_id":"2206.13199","repositories_listed":2,"syntology":null},{"url":"/paper/binsformer-revisiting-adaptive-bins-for","slug":"binsformer-revisiting-adaptive-bins-for","title":"BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation","date":"2022-04-03","arxiv_id":"2204.00987","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/binsformer-revisiting-adaptive-bins-for#ran","syntology_url":"https://syntology.ai/paper/2204.00987","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.00987"}},"official":{"repos":["zhyever/monocular-depth-estimation-toolbox"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/transformer-based-knowledge-distillation-for","slug":"transformer-based-knowledge-distillation-for","title":"TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation","date":"2022-02-27","arxiv_id":"2202.13393","repositories_listed":2,"syntology":null},{"url":"/paper/global-reasoned-multi-task-learning-model-for","slug":"global-reasoned-multi-task-learning-model-for","title":"Global-Reasoned Multi-Task Learning Model for Surgical Scene Understanding","date":"2022-01-28","arxiv_id":"2201.11957","repositories_listed":2,"syntology":{"n":8,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":8,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/global-reasoned-multi-task-learning-model-for#ran","syntology_url":"https://syntology.ai/paper/2201.11957","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.11957"}},"official":{"repos":["lalithjets/global-reasoned-multi-task-model"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/mseg-a-composite-dataset-for-multi-domain-1","slug":"mseg-a-composite-dataset-for-multi-domain-1","title":"MSeg: A Composite Dataset for Multi-domain Semantic Segmentation","date":"2021-12-27","arxiv_id":"2112.13762","repositories_listed":2,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":10,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":4,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mseg-a-composite-dataset-for-multi-domain-1#ran","syntology_url":"https://syntology.ai/paper/2112.13762","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.13762"}},"official":{"repos":["mseg-dataset/mseg-semantic"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/behind-the-curtain-learning-occluded-shapes","slug":"behind-the-curtain-learning-occluded-shapes","title":"Behind the Curtain: Learning Occluded Shapes for 3D Object Detection","date":"2021-12-04","arxiv_id":"2112.02205","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/behind-the-curtain-learning-occluded-shapes#ran","syntology_url":"https://syntology.ai/paper/2112.02205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.02205"}},"official":{"repos":["xharlie/btcdet"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/model-a-modularized-end-to-end-reinforcement","slug":"model-a-modularized-end-to-end-reinforcement","title":"A Versatile and Efficient Reinforcement Learning Framework for Autonomous Driving","date":"2021-10-22","arxiv_id":"2110.11573","repositories_listed":2,"syntology":null},{"url":"/paper/planerecnet-multi-task-learning-with-cross","slug":"planerecnet-multi-task-learning-with-cross","title":"PlaneRecNet: Multi-Task Learning with Cross-Task Consistency for Piece-Wise Plane Detection and Reconstruction from a Single RGB Image","date":"2021-10-21","arxiv_id":"2110.11219","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/planerecnet-multi-task-learning-with-cross#ran","syntology_url":"https://syntology.ai/paper/2110.11219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.11219"}},"official":{"repos":["eryixie/planerecnet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/structured-bird-s-eye-view-traffic-scene-1","slug":"structured-bird-s-eye-view-traffic-scene-1","title":"Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Images","date":"2021-10-05","arxiv_id":"2110.01997","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/structured-bird-s-eye-view-traffic-scene-1#ran","syntology_url":"https://syntology.ai/paper/2110.01997","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.01997"}},"official":{"repos":["ybarancan/stsu"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/kitti-360-a-novel-dataset-and-benchmarks-for","slug":"kitti-360-a-novel-dataset-and-benchmarks-for","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","date":"2021-09-28","arxiv_id":"2109.13410","repositories_listed":2,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":2,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/kitti-360-a-novel-dataset-and-benchmarks-for#ran","syntology_url":"https://syntology.ai/paper/2109.13410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.13410"}},"official":{"repos":["autonomousvision/kitti360labeltool","autonomousvision/kitti360scripts"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/arabic-scene-text-recognition-in-the-deep","slug":"arabic-scene-text-recognition-in-the-deep","title":"Arabic Scene Text Recognition in the Deep Learning Era: Analysis on A Novel Dataset","date":"2021-07-27","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/affordance-transfer-learning-for-human-object","slug":"affordance-transfer-learning-for-human-object","title":"Affordance Transfer Learning for Human-Object Interaction Detection","date":"2021-04-07","arxiv_id":"2104.02867","repositories_listed":2,"syntology":null},{"url":"/paper/scenegraphfusion-incremental-3d-scene-graph","slug":"scenegraphfusion-incremental-3d-scene-graph","title":"SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences","date":"2021-03-27","arxiv_id":"2103.14898","repositories_listed":2,"syntology":null},{"url":"/paper/monte-carlo-scene-search-for-3d-scene","slug":"monte-carlo-scene-search-for-3d-scene","title":"Monte Carlo Scene Search for 3D Scene Understanding","date":"2021-03-14","arxiv_id":"2103.07969","repositories_listed":2,"syntology":null},{"url":"/paper/affect2mm-affective-analysis-of-multimedia","slug":"affect2mm-affective-analysis-of-multimedia","title":"Affect2MM: Affective Analysis of Multimedia Content Using Emotion Causality","date":"2021-03-11","arxiv_id":"2103.06541","repositories_listed":2,"syntology":null},{"url":"/paper/feature-pyramid-network-with-multi-head","slug":"feature-pyramid-network-with-multi-head","title":"A2-FPN for Semantic Segmentation of Fine-Resolution Remotely Sensed Images","date":"2021-02-16","arxiv_id":"2102.07997","repositories_listed":2,"syntology":null},{"url":"/paper/ikshana-a-theory-of-human-scene-understanding","slug":"ikshana-a-theory-of-human-scene-understanding","title":"The Ikshana Hypothesis of Human Scene Understanding","date":"2021-01-21","arxiv_id":"2101.10837","repositories_listed":2,"syntology":null},{"url":"/paper/automatic-extrinsic-calibration-method-for","slug":"automatic-extrinsic-calibration-method-for","title":"Automatic Extrinsic Calibration Method for LiDAR and Camera Sensor Setups","date":"2021-01-12","arxiv_id":"2101.04431","repositories_listed":2,"syntology":null},{"url":"/paper/exploring-data-efficient-3d-scene","slug":"exploring-data-efficient-3d-scene","title":"Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts","date":"2020-12-16","arxiv_id":"2012.09165","repositories_listed":2,"syntology":null},{"url":"/paper/hypersim-a-photorealistic-synthetic-dataset","slug":"hypersim-a-photorealistic-synthetic-dataset","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","date":"2020-11-04","arxiv_id":"2011.02523","repositories_listed":2,"syntology":null},{"url":"/paper/auto-panoptic-cooperative-multi-component","slug":"auto-panoptic-cooperative-multi-component","title":"Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation","date":"2020-10-30","arxiv_id":"2010.16119","repositories_listed":2,"syntology":null}],"syntology_records":44,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":208,"papers_where_code_ran_first_page":"/task/scene-understanding/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":18,"url":"/task/scene-understanding/papers/2","json":"/task/scene-understanding/papers/2.json","rows":100},{"order":"archive","page":3,"of":18,"url":"/task/scene-understanding/papers/3","json":"/task/scene-understanding/papers/3.json","rows":100},{"order":"archive","page":4,"of":18,"url":"/task/scene-understanding/papers/4","json":"/task/scene-understanding/papers/4.json","rows":100},{"order":"archive","page":5,"of":18,"url":"/task/scene-understanding/papers/5","json":"/task/scene-understanding/papers/5.json","rows":100},{"order":"archive","page":6,"of":18,"url":"/task/scene-understanding/papers/6","json":"/task/scene-understanding/papers/6.json","rows":100},{"order":"archive","page":7,"of":18,"url":"/task/scene-understanding/papers/7","json":"/task/scene-understanding/papers/7.json","rows":100},{"order":"archive","page":8,"of":18,"url":"/task/scene-understanding/papers/8","json":"/task/scene-understanding/papers/8.json","rows":100},{"order":"archive","page":9,"of":18,"url":"/task/scene-understanding/papers/9","json":"/task/scene-understanding/papers/9.json","rows":100},{"order":"archive","page":10,"of":18,"url":"/task/scene-understanding/papers/10","json":"/task/scene-understanding/papers/10.json","rows":100},{"order":"archive","page":11,"of":18,"url":"/task/scene-understanding/papers/11","json":"/task/scene-understanding/papers/11.json","rows":100},{"order":"archive","page":12,"of":18,"url":"/task/scene-understanding/papers/12","json":"/task/scene-understanding/papers/12.json","rows":100},{"order":"archive","page":13,"of":18,"url":"/task/scene-understanding/papers/13","json":"/task/scene-understanding/papers/13.json","rows":100},{"order":"archive","page":14,"of":18,"url":"/task/scene-understanding/papers/14","json":"/task/scene-understanding/papers/14.json","rows":100},{"order":"archive","page":15,"of":18,"url":"/task/scene-understanding/papers/15","json":"/task/scene-understanding/papers/15.json","rows":100},{"order":"archive","page":16,"of":18,"url":"/task/scene-understanding/papers/16","json":"/task/scene-understanding/papers/16.json","rows":100},{"order":"archive","page":17,"of":18,"url":"/task/scene-understanding/papers/17","json":"/task/scene-understanding/papers/17.json","rows":100},{"order":"archive","page":18,"of":18,"url":"/task/scene-understanding/papers/18","json":"/task/scene-understanding/papers/18.json","rows":23},{"order":"ran","page":1,"of":3,"url":"/task/scene-understanding/papers/ran/1","json":"/task/scene-understanding/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":3,"url":"/task/scene-understanding/papers/ran/2","json":"/task/scene-understanding/papers/ran/2.json","rows":100},{"order":"ran","page":3,"of":3,"url":"/task/scene-understanding/papers/ran/3","json":"/task/scene-understanding/papers/ran/3.json","rows":8}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"e70fa6b994e01eaad70c32ce6b6553c94f73245b7ea11c12b974ea1608259cba","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}