{"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-recognition","name":"Scene Recognition","slug":"scene-recognition","description_markdown":null,"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":207,"papers_with_code":68,"benchmarks":8,"benchmark_tables_in_archive":8,"benchmark_tables_shown":8,"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":16,"subtasks":0,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/scene-recognition-on-yup","slug":"scene-recognition-on-yup","dataset":"YUP++","dataset_url":"/dataset/yup","rows_in_archive":5,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"DEEP-HAL with ODF+SDF (I3D)","paper_title":"Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors","paper_url":"/paper/hallucinating-statistical-moment-and-subspace","paper_date":"2020-01-14","arxiv_id":"2001.04627","code_links":[],"syntology":null}},{"leaderboard":"/sota/scene-recognition-on-aid","slug":"scene-recognition-on-aid","dataset":"AID","dataset_url":"/dataset/aid","rows_in_archive":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"AGOS","paper_title":"All Grains, One Scheme (AGOS): Learning Multi-grain Instance Representation for Aerial Scene Classification","paper_url":"/paper/all-grains-one-scheme-agos-learning-multi","paper_date":"2022-05-06","arxiv_id":"2205.03371","code_links":[{"title":"biqiwhu/agos","url":"https://github.com/biqiwhu/agos"}],"syntology":null}},{"leaderboard":"/sota/scene-recognition-on-mit-indoors-scenes","slug":"scene-recognition-on-mit-indoors-scenes","dataset":"MIT Indoor Scenes","dataset_url":"/dataset/mit-indoors-scenes","rows_in_archive":3,"metrics":["Accuracy","10-stage average accuracy"],"first_row_in_archive_order":{"model":"FOSNet","paper_title":"FOSNet: An End-to-End Trainable Deep Neural Network for Scene Recognition","paper_url":"/paper/fosnet-an-end-to-end-trainable-deep-neural","paper_date":"2019-07-17","arxiv_id":"1907.07570","code_links":[],"syntology":null}},{"leaderboard":"/sota/scene-recognition-on-places365","slug":"scene-recognition-on-places365","dataset":"Places365","dataset_url":"/dataset/places365","rows_in_archive":2,"metrics":["Top 1 Accuracy","Top 5 Accuracy"],"first_row_in_archive_order":{"model":"FOSNet","paper_title":"FOSNet: An End-to-End Trainable Deep Neural Network for Scene Recognition","paper_url":"/paper/fosnet-an-end-to-end-trainable-deep-neural","paper_date":"2019-07-17","arxiv_id":"1907.07570","code_links":[],"syntology":null}},{"leaderboard":"/sota/scene-recognition-on-sun-rgbd","slug":"scene-recognition-on-sun-rgbd","dataset":"SUN-RGBD","dataset_url":"/dataset/sun-rgb-d","rows_in_archive":2,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"OMNIVORE (Swin-B)","paper_title":"Omnivore: A Single Model for Many Visual Modalities","paper_url":"/paper/omnivore-a-single-model-for-many-visual","paper_date":"2022-01-20","arxiv_id":"2201.08377","code_links":[{"title":"towhee-io/towhee","url":"https://github.com/towhee-io/towhee"},{"title":"facebookresearch/omnivore","url":"https://github.com/facebookresearch/omnivore"}],"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/omnivore-a-single-model-for-many-visual#ran","syntology_url":"https://syntology.ai/paper/2201.08377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.08377"}},"official":{"repos":["facebookresearch/omnivore"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/scene-recognition-on-sun397","slug":"scene-recognition-on-sun397","dataset":"SUN397","dataset_url":"/dataset/sun397","rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"FOSNet","paper_title":"FOSNet: An End-to-End Trainable Deep Neural Network for Scene Recognition","paper_url":"/paper/fosnet-an-end-to-end-trainable-deep-neural","paper_date":"2019-07-17","arxiv_id":"1907.07570","code_links":[],"syntology":null}},{"leaderboard":"/sota/scene-recognition-on-ade20k","slug":"scene-recognition-on-ade20k","dataset":"ADE20K","dataset_url":"/dataset/ade20k","rows_in_archive":1,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"Semantic-Aware Scene Recogniton (ResNet-18)","paper_title":"Semantic-Aware Scene Recognition","paper_url":"/paper/semantic-aware-scene-recognition","paper_date":"2019-09-05","arxiv_id":"1909.02410","code_links":[{"title":"vpulab/Semantic-Aware-Scene-Recognition","url":"https://github.com/vpulab/Semantic-Aware-Scene-Recognition"}],"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/semantic-aware-scene-recognition#ran","syntology_url":"https://syntology.ai/paper/1909.02410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.02410"}},"official":{"repos":["vpulab/Semantic-Aware-Scene-Recognition"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/scene-recognition-on-scannet","slug":"scene-recognition-on-scannet","dataset":"ScanNet","dataset_url":"/dataset/scannet","rows_in_archive":1,"metrics":["Average Recall"],"first_row_in_archive_order":{"model":"SSMA","paper_title":"Self-Supervised Model Adaptation for Multimodal Semantic Segmentation","paper_url":"/paper/self-supervised-model-adaptation-for","paper_date":"2018-08-11","arxiv_id":"1808.03833","code_links":[{"title":"DeepSceneSeg/SSMA","url":"https://github.com/DeepSceneSeg/SSMA"}],"syntology":null}}],"datasets":[{"url":"/dataset/scannet","name":"ScanNet","full_name":"","num_papers_in_archive":1595},{"url":"/dataset/ade20k","name":"ADE20K","full_name":"","num_papers_in_archive":1213},{"url":"/dataset/places205","name":"Places205","full_name":"","num_papers_in_archive":525},{"url":"/dataset/sun-rgb-d","name":"SUN RGB-D","full_name":"SUN RGB-D","num_papers_in_archive":477},{"url":"/dataset/places365","name":"Places365","full_name":"","num_papers_in_archive":65},{"url":"/dataset/sun397","name":"SUN397","full_name":"SUN397","num_papers_in_archive":52},{"url":"/dataset/aid","name":"AID","full_name":"Aerial Image Dataset","num_papers_in_archive":40},{"url":"/dataset/yup","name":"YUP++","full_name":"YUP++ Dynamic Scenes dataset","num_papers_in_archive":13},{"url":"/dataset/mit-indoors-scenes","name":"MIT Indoor Scenes","full_name":"","num_papers_in_archive":9},{"url":"/dataset/advance","name":"ADVANCE","full_name":"AuDio Visual Aerial sceNe reCognition datasEt","num_papers_in_archive":6},{"url":"/dataset/hsd","name":"HSD","full_name":"Honda Scenes Dataset","num_papers_in_archive":3},{"url":"/dataset/hows","name":"HOWS","full_name":"HOWS-CL-25","num_papers_in_archive":1},{"url":"/dataset/mai","name":"MAI","full_name":"Multi-scene Aerial Image","num_papers_in_archive":1},{"url":"/dataset/indian-food-image-dataset","name":"Indian Food Image Dataset","full_name":"datacluster.ai","num_papers_in_archive":0},{"url":"/dataset/kitti-360-sr","name":"KITTI-360-SR","full_name":"KITTI-360 modification for Scene Recognition task","num_papers_in_archive":0},{"url":"/dataset/stairs-image-dataset-parts-of-house-indoor","name":"Stairs Image Dataset | Parts of House | Indoor","full_name":"datacluster.ai","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[{"url":"/task/3d-character-animation-from-a-single-photo","name":"3D Character Animation From A Single Photo"},{"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":3,"rows_per_page":100,"shown":100,"of":207,"of_with_code":68,"tagged_in_all":207,"counts":{"archive_papers_tagged":207,"with_a_code_link":68,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":207,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":7,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/csrnet-dilated-convolutional-neural-networks","slug":"csrnet-dilated-convolutional-neural-networks","title":"CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes","date":"2018-02-27","arxiv_id":"1802.10062","repositories_listed":11,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":2,"n_honours":3,"n_violates":1,"n_no_contract":8,"n_pointer_only":6,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 1 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/csrnet-dilated-convolutional-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1802.10062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.10062"}},"official":null}},{"url":"/paper/decaf-a-deep-convolutional-activation-feature","slug":"decaf-a-deep-convolutional-activation-feature","title":"DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition","date":"2013-10-06","arxiv_id":"1310.1531","repositories_listed":8,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":4,"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, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/decaf-a-deep-convolutional-activation-feature#ran","syntology_url":"https://syntology.ai/paper/1310.1531","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1310.1531"}},"official":null}},{"url":"/paper/bilinear-cnns-for-fine-grained-visual","slug":"bilinear-cnns-for-fine-grained-visual","title":"Bilinear CNNs for Fine-grained Visual Recognition","date":"2015-04-29","arxiv_id":"1504.07889","repositories_listed":4,"syntology":null},{"url":"/paper/cnn-features-off-the-shelf-an-astounding","slug":"cnn-features-off-the-shelf-an-astounding","title":"CNN Features off-the-shelf: an Astounding Baseline for Recognition","date":"2014-03-23","arxiv_id":"1403.6382","repositories_listed":4,"syntology":null},{"url":"/paper/visual-memorability-for-robotic","slug":"visual-memorability-for-robotic","title":"Visual Memorability for Robotic Interestingness via Unsupervised Online Learning","date":"2020-05-18","arxiv_id":"2005.08829","repositories_listed":3,"syntology":null},{"url":"/paper/an-empirical-study-of-remote-sensing","slug":"an-empirical-study-of-remote-sensing","title":"An Empirical Study of Remote Sensing Pretraining","date":"2022-04-06","arxiv_id":"2204.02825","repositories_listed":2,"syntology":null},{"url":"/paper/omnivore-a-single-model-for-many-visual","slug":"omnivore-a-single-model-for-many-visual","title":"Omnivore: A Single Model for Many Visual Modalities","date":"2022-01-20","arxiv_id":"2201.08377","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/omnivore-a-single-model-for-many-visual#ran","syntology_url":"https://syntology.ai/paper/2201.08377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.08377"}},"official":{"repos":["facebookresearch/omnivore"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/self-supervised-video-representation-learning-5","slug":"self-supervised-video-representation-learning-5","title":"Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics","date":"2020-08-31","arxiv_id":"2008.13426","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-supervised-video-representation-learning-5#ran","syntology_url":"https://syntology.ai/paper/2008.13426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.13426"}},"official":{"repos":["laura-wang/video_repres_sts"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/indoor-scene-recognition-in-3d","slug":"indoor-scene-recognition-in-3d","title":"Indoor Scene Recognition in 3D","date":"2020-02-28","arxiv_id":"2002.12819","repositories_listed":2,"syntology":null},{"url":"/paper/hallucinet-ing-spatiotemporal-representations","slug":"hallucinet-ing-spatiotemporal-representations","title":"HalluciNet-ing Spatiotemporal Representations Using a 2D-CNN","date":"2019-12-10","arxiv_id":"1912.04430","repositories_listed":2,"syntology":null},{"url":"/paper/learning-from-less-data-a-unified-data-subset","slug":"learning-from-less-data-a-unified-data-subset","title":"Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Vision","date":"2019-01-03","arxiv_id":"1901.01151","repositories_listed":2,"syntology":null},{"url":"/paper/knowledge-guided-disambiguation-for-large","slug":"knowledge-guided-disambiguation-for-large","title":"Knowledge Guided Disambiguation for Large-Scale Scene Classification with Multi-Resolution CNNs","date":"2016-10-04","arxiv_id":"1610.01119","repositories_listed":2,"syntology":null},{"url":"/paper/places205-vggnet-models-for-scene-recognition","slug":"places205-vggnet-models-for-scene-recognition","title":"Places205-VGGNet Models for Scene Recognition","date":"2015-08-07","arxiv_id":"1508.01667","repositories_listed":2,"syntology":null},{"url":"/paper/advancing-als-applications-with-large-scale","slug":"advancing-als-applications-with-large-scale","title":"Advancing ALS Applications with Large-Scale Pre-training: Dataset Development and Downstream Assessment","date":"2025-01-09","arxiv_id":"2501.05095","repositories_listed":1,"syntology":null},{"url":"/paper/sound-bridge-associating-egocentric-and","slug":"sound-bridge-associating-egocentric-and","title":"Sound Bridge: Associating Egocentric and Exocentric Videos via Audio Cues","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/model-developmental-safety-a-safety-centric","slug":"model-developmental-safety-a-safety-centric","title":"A Retention-Centric Framework for Continual Learning with Guaranteed Model Developmental Safety","date":"2024-10-04","arxiv_id":"2410.03955","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":9,"phrase":"5 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; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/model-developmental-safety-a-safety-centric#ran","syntology_url":"https://syntology.ai/paper/2410.03955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03955"}},"official":{"repos":["ganglii/devsafety"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/pir-remote-sensing-image-text-retrieval-with","slug":"pir-remote-sensing-image-text-retrieval-with","title":"PIR: Remote Sensing Image-Text Retrieval with Prior Instruction Representation Learning","date":"2024-05-16","arxiv_id":"2405.10160","repositories_listed":1,"syntology":null},{"url":"/paper/nuscenes-mqa-integrated-evaluation-of","slug":"nuscenes-mqa-integrated-evaluation-of","title":"NuScenes-MQA: Integrated Evaluation of Captions and QA for Autonomous Driving Datasets using Markup Annotations","date":"2023-12-11","arxiv_id":"2312.06352","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-road-with-gpt-4v-ision-early","slug":"on-the-road-with-gpt-4v-ision-early","title":"On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous Driving","date":"2023-11-09","arxiv_id":"2311.05332","repositories_listed":1,"syntology":null},{"url":"/paper/counting-manatee-aggregations-using-deep","slug":"counting-manatee-aggregations-using-deep","title":"Counting Manatee Aggregations using Deep Neural Networks and Anisotropic Gaussian Kernel","date":"2023-11-04","arxiv_id":"2311.02315","repositories_listed":1,"syntology":null},{"url":"/paper/a-prior-instruction-representation-framework","slug":"a-prior-instruction-representation-framework","title":"A Prior Instruction Representation Framework for Remote Sensing Image-text Retrieval","date":"2023-10-27","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/disasternets-embedding-machine-learning-in","slug":"disasternets-embedding-machine-learning-in","title":"DisasterNets: Embedding Machine Learning in Disaster Mapping","date":"2023-06-16","arxiv_id":"2306.09815","repositories_listed":1,"syntology":null},{"url":"/paper/narrative-xl-a-large-scale-dataset-for-long","slug":"narrative-xl-a-large-scale-dataset-for-long","title":"NarrativeXL: A Large-scale Dataset For Long-Term Memory Models","date":"2023-05-23","arxiv_id":"2305.13877","repositories_listed":1,"syntology":null},{"url":"/paper/srrm-semantic-region-relation-model-for","slug":"srrm-semantic-region-relation-model-for","title":"SRRM: Semantic Region Relation Model for Indoor Scene Recognition","date":"2023-05-15","arxiv_id":"2305.08540","repositories_listed":1,"syntology":null},{"url":"/paper/designing-deep-networks-for-scene-recognition","slug":"designing-deep-networks-for-scene-recognition","title":"Designing Deep Networks for Scene Recognition","date":"2023-03-13","arxiv_id":"2303.07402","repositories_listed":1,"syntology":null},{"url":"/paper/comae-single-model-hybrid-pre-training-on","slug":"comae-single-model-hybrid-pre-training-on","title":"CoMAE: Single Model Hybrid Pre-training on Small-Scale RGB-D Datasets","date":"2023-02-13","arxiv_id":"2302.06148","repositories_listed":1,"syntology":null},{"url":"/paper/nevis-22-a-stream-of-100-tasks-sampled-from","slug":"nevis-22-a-stream-of-100-tasks-sampled-from","title":"NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research","date":"2022-11-15","arxiv_id":"2211.11747","repositories_listed":1,"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/nevis-22-a-stream-of-100-tasks-sampled-from#ran","syntology_url":"https://syntology.ai/paper/2211.11747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.11747"}},"official":{"repos":["deepmind/dm_nevis"],"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/movieclip-visual-scene-recognition-in-movies","slug":"movieclip-visual-scene-recognition-in-movies","title":"MovieCLIP: Visual Scene Recognition in Movies","date":"2022-10-20","arxiv_id":"2210.11065","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/movieclip-visual-scene-recognition-in-movies#ran","syntology_url":"https://syntology.ai/paper/2210.11065","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11065"}},"official":{"repos":["usc-sail/mica-MovieCLIP"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/capsule-networks-as-generative-models","slug":"capsule-networks-as-generative-models","title":"Capsule Networks as Generative Models","date":"2022-09-06","arxiv_id":"2209.02567","repositories_listed":1,"syntology":null},{"url":"/paper/all-grains-one-scheme-agos-learning-multi","slug":"all-grains-one-scheme-agos-learning-multi","title":"All Grains, One Scheme (AGOS): Learning Multi-grain Instance Representation for Aerial Scene Classification","date":"2022-05-06","arxiv_id":"2205.03371","repositories_listed":1,"syntology":null},{"url":"/paper/where-in-the-world-is-this-image-transformer","slug":"where-in-the-world-is-this-image-transformer","title":"Where in the World is this Image? Transformer-based Geo-localization in the Wild","date":"2022-04-29","arxiv_id":"2204.13861","repositories_listed":1,"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":0,"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/where-in-the-world-is-this-image-transformer#ran","syntology_url":"https://syntology.ai/paper/2204.13861","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.13861"}},"official":{"repos":["shramanpramanick/transformer_based_geo-localization"],"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/instaindoor-and-multi-modal-deep-learning-for","slug":"instaindoor-and-multi-modal-deep-learning-for","title":"InstaIndoor and Multi-modal Deep Learning for Indoor Scene Recognition","date":"2021-12-23","arxiv_id":"2112.12409","repositories_listed":1,"syntology":null},{"url":"/paper/an-embarrassingly-simple-comparison-of","slug":"an-embarrassingly-simple-comparison-of","title":"An embarrassingly simple comparison of machine learning algorithms for indoor scene classification","date":"2021-09-25","arxiv_id":"2109.12261","repositories_listed":1,"syntology":null},{"url":"/paper/borm-bayesian-object-relation-model-for","slug":"borm-bayesian-object-relation-model-for","title":"BORM: Bayesian Object Relation Model for Indoor Scene Recognition","date":"2021-08-01","arxiv_id":"2108.00397","repositories_listed":1,"syntology":null},{"url":"/paper/object-to-scene-learning-to-transfer-object","slug":"object-to-scene-learning-to-transfer-object","title":"Object-to-Scene: Learning to Transfer Object Knowledge to Indoor Scene Recognition","date":"2021-08-01","arxiv_id":"2108.00399","repositories_listed":1,"syntology":null},{"url":"/paper/local-semantic-enhanced-convnet-for-aerial","slug":"local-semantic-enhanced-convnet-for-aerial","title":"Local semantic enhanced convnet for aerial scene recognition","date":"2021-07-08","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/aerial-scene-understanding-in-the-wild-multi","slug":"aerial-scene-understanding-in-the-wild-multi","title":"Aerial Scene Understanding in The Wild: Multi-Scene Recognition via Prototype-based Memory Networks","date":"2021-04-22","arxiv_id":"2104.11200","repositories_listed":1,"syntology":null},{"url":"/paper/multiscene-a-large-scale-dataset-and","slug":"multiscene-a-large-scale-dataset-and","title":"MultiScene: A Large-scale Dataset and Benchmark for Multi-scene Recognition in Single Aerial Images","date":"2021-04-07","arxiv_id":"2104.02846","repositories_listed":1,"syntology":null},{"url":"/paper/bidirectional-projection-network-for-cross","slug":"bidirectional-projection-network-for-cross","title":"Bidirectional Projection Network for Cross Dimension Scene Understanding","date":"2021-03-26","arxiv_id":"2103.14326","repositories_listed":1,"syntology":null},{"url":"/paper/translate-to-adapt-rgb-d-scene-recognition","slug":"translate-to-adapt-rgb-d-scene-recognition","title":"Multi-Modal RGB-D Scene Recognition Across Domains","date":"2021-03-26","arxiv_id":"2103.14672","repositories_listed":1,"syntology":null},{"url":"/paper/a-study-of-face-obfuscation-in-imagenet","slug":"a-study-of-face-obfuscation-in-imagenet","title":"A Study of Face Obfuscation in ImageNet","date":"2021-03-10","arxiv_id":"2103.06191","repositories_listed":1,"syntology":null},{"url":"/paper/stochastic-partial-swap-enhanced-model","slug":"stochastic-partial-swap-enhanced-model","title":"Stochastic Partial Swap: Enhanced Model Generalization and Interpretability for Fine-Grained Recognition","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cross-task-transfer-for-multimodal-aerial","slug":"cross-task-transfer-for-multimodal-aerial","title":"Cross-Task Transfer for Geotagged Audiovisual Aerial Scene Recognition","date":"2020-05-18","arxiv_id":"2005.08449","repositories_listed":1,"syntology":null},{"url":"/paper/when-cnns-meet-random-rnns-towards-multi","slug":"when-cnns-meet-random-rnns-towards-multi","title":"When CNNs Meet Random RNNs: Towards Multi-Level Analysis for RGB-D Object and Scene Recognition","date":"2020-04-26","arxiv_id":"2004.12349","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-model-personalization-while","slug":"unsupervised-model-personalization-while","title":"Unsupervised Model Personalization while Preserving Privacy and Scalability: An Open Problem","date":"2020-03-30","arxiv_id":"2003.13296","repositories_listed":1,"syntology":null},{"url":"/paper/a-multiple-instance-densely-connected-convnet","slug":"a-multiple-instance-densely-connected-convnet","title":"A multiple-instance densely-connected ConvNet for aerial scene classification","date":"2020-03-03","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/semantic-aware-scene-recognition","slug":"semantic-aware-scene-recognition","title":"Semantic-Aware Scene Recognition","date":"2019-09-05","arxiv_id":"1909.02410","repositories_listed":1,"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/semantic-aware-scene-recognition#ran","syntology_url":"https://syntology.ai/paper/1909.02410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.02410"}},"official":{"repos":["vpulab/Semantic-Aware-Scene-Recognition"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dfpenet-geology-a-deep-learning-framework-for","slug":"dfpenet-geology-a-deep-learning-framework-for","title":"DFPENet-geology: A Deep Learning Framework for High Precision Recognition and Segmentation of Co-seismic Landslides","date":"2019-08-28","arxiv_id":"1908.10907","repositories_listed":1,"syntology":null},{"url":"/paper/deduce-diverse-scene-detection-methods-in","slug":"deduce-diverse-scene-detection-methods-in","title":"DEDUCE: Diverse scEne Detection methods in Unseen Challenging Environments","date":"2019-08-01","arxiv_id":"1908.00191","repositories_listed":1,"syntology":null},{"url":"/paper/user-preference-prediction-in-visual-data-on","slug":"user-preference-prediction-in-visual-data-on","title":"Preferences Prediction using a Gallery of Mobile Device based on Scene Recognition and Object Detection","date":"2019-07-10","arxiv_id":"1907.04519","repositories_listed":1,"syntology":null},{"url":"/paper/translate-to-recognize-networks-for-rgb-d","slug":"translate-to-recognize-networks-for-rgb-d","title":"Translate-to-Recognize Networks for RGB-D Scene Recognition","date":"2019-04-28","arxiv_id":"1904.12254","repositories_listed":1,"syntology":null},{"url":"/paper/local-aggregation-for-unsupervised-learning","slug":"local-aggregation-for-unsupervised-learning","title":"Local Aggregation for Unsupervised Learning of Visual Embeddings","date":"2019-03-29","arxiv_id":"1903.12355","repositories_listed":1,"syntology":null},{"url":"/paper/plugin-networks-for-inference-under-partial","slug":"plugin-networks-for-inference-under-partial","title":"Plugin Networks for Inference under Partial Evidence","date":"2019-01-02","arxiv_id":"1901.00326","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-model-adaptation-for","slug":"self-supervised-model-adaptation-for","title":"Self-Supervised Model Adaptation for Multimodal Semantic Segmentation","date":"2018-08-11","arxiv_id":"1808.03833","repositories_listed":1,"syntology":null},{"url":"/paper/from-volcano-to-toyshop-adaptive","slug":"from-volcano-to-toyshop-adaptive","title":"From Volcano to Toyshop: Adaptive Discriminative Region Discovery for Scene Recognition","date":"2018-07-23","arxiv_id":"1807.08624","repositories_listed":1,"syntology":null},{"url":"/paper/deep-attentional-structured-representation","slug":"deep-attentional-structured-representation","title":"Deep Attentional Structured Representation Learning for Visual Recognition","date":"2018-05-14","arxiv_id":"1805.05389","repositories_listed":1,"syntology":null},{"url":"/paper/empirical-analysis-of-foundational","slug":"empirical-analysis-of-foundational","title":"Empirical Analysis of Foundational Distinctions in Linked Open Data","date":"2018-03-26","arxiv_id":"1803.09840","repositories_listed":1,"syntology":null},{"url":"/paper/depth-cnns-for-rgb-d-scene-recognition","slug":"depth-cnns-for-rgb-d-scene-recognition","title":"Depth CNNs for RGB-D scene recognition: learning from scratch better than transferring from RGB-CNNs","date":"2018-01-21","arxiv_id":"1801.06797","repositories_listed":1,"syntology":null},{"url":"/paper/aga-attribute-guided-augmentation-1","slug":"aga-attribute-guided-augmentation-1","title":"AGA: Attribute-Guided Augmentation","date":"2017-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/temporal-residual-networks-for-dynamic-scene","slug":"temporal-residual-networks-for-dynamic-scene","title":"Temporal Residual Networks for Dynamic Scene Recognition","date":"2017-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/scene-recognition-by-combining-local-and","slug":"scene-recognition-by-combining-local-and","title":"Scene Recognition by Combining Local and Global Image Descriptors","date":"2017-02-21","arxiv_id":"1702.06850","repositories_listed":1,"syntology":null},{"url":"/paper/aga-attribute-guided-augmentation","slug":"aga-attribute-guided-augmentation","title":"AGA: Attribute Guided Augmentation","date":"2016-12-08","arxiv_id":"1612.02559","repositories_listed":1,"syntology":null},{"url":"/paper/word-recognition-with-deep-conditional-random","slug":"word-recognition-with-deep-conditional-random","title":"Word Recognition with Deep Conditional Random Fields","date":"2016-12-04","arxiv_id":"1612.01072","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-patchnets-describing-and","slug":"weakly-supervised-patchnets-describing-and","title":"Weakly Supervised PatchNets: Describing and Aggregating Local Patches for Scene Recognition","date":"2016-09-01","arxiv_id":"1609.00153","repositories_listed":1,"syntology":null},{"url":"/paper/classifying-variable-length-audio-files-with","slug":"classifying-variable-length-audio-files-with","title":"Classifying Variable-Length Audio Files with All-Convolutional Networks and Masked Global Pooling","date":"2016-07-11","arxiv_id":"1607.02857","repositories_listed":1,"syntology":null},{"url":"/paper/deep-filter-banks-for-texture-recognition-and","slug":"deep-filter-banks-for-texture-recognition-and","title":"Deep Filter Banks for Texture Recognition and Segmentation","date":"2015-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-image-representations-tied-to-ego","slug":"learning-image-representations-tied-to-ego","title":"Learning image representations tied to ego-motion","date":"2015-05-08","arxiv_id":"1505.02206","repositories_listed":1,"syntology":null},{"url":"/paper/object-detectors-emerge-in-deep-scene-cnns","slug":"object-detectors-emerge-in-deep-scene-cnns","title":"Object Detectors Emerge in Deep Scene CNNs","date":"2014-12-22","arxiv_id":"1412.6856","repositories_listed":1,"syntology":null},{"url":null,"slug":"open-vocabulary-semantic-segmentation-with-3","title":"Open-Vocabulary Semantic Segmentation with Uncertainty Alignment for Robotic Scene Understanding in Indoor Building Environments","date":"2025-03-29","arxiv_id":"2503.23105","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-multimodal-artificial","title":"Lightweight Multimodal Artificial Intelligence Framework for Maritime Multi-Scene Recognition","date":"2025-03-10","arxiv_id":"2503.06978","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-visual-data-augmentation","title":"Contrastive Visual Data Augmentation","date":"2025-02-24","arxiv_id":"2502.17709","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-with-partial-certainty-conformal","title":"Seeing with Partial Certainty: Conformal Prediction for Robotic Scene Recognition in Built Environments","date":"2025-01-09","arxiv_id":"2501.04947","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-language-models-for-autonomous-driving","title":"Vision-Language Models for Autonomous Driving: CLIP-Based Dynamic Scene Understanding","date":"2025-01-09","arxiv_id":"2501.05566","repositories_listed":0,"syntology":null},{"url":null,"slug":"saist-segment-any-infrared-small-target-model","title":"SAIST: Segment Any Infrared Small Target Model Guided by Contrastive Language-Image Pretraining","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"movement-control-of-smart-mosque-s-domes","title":"Movement Control of Smart Mosque's Domes using CSRNet and Fuzzy Logic Techniques","date":"2024-10-13","arxiv_id":"2410.18123","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-vlms-and-llms-for-image","title":"Rethinking VLMs and LLMs for Image Classification","date":"2024-10-03","arxiv_id":"2410.14690","repositories_listed":0,"syntology":null},{"url":null,"slug":"less-yet-robust-crucial-region-selection-for","title":"Less yet robust: crucial region selection for scene recognition","date":"2024-09-23","arxiv_id":"2409.14741","repositories_listed":0,"syntology":null},{"url":null,"slug":"carin-constraint-aware-and-responsive","title":"CARIn: Constraint-Aware and Responsive Inference on Heterogeneous Devices for Single- and Multi-DNN Workloads","date":"2024-09-02","arxiv_id":"2409.01089","repositories_listed":0,"syntology":null},{"url":null,"slug":"indoor-scene-recognition-from-images-under","title":"Indoor scene recognition from images under visual corruptions","date":"2024-08-23","arxiv_id":"2408.13029","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-language-model-for-interpretable-and","title":"Vision Language Model for Interpretable and Fine-grained Detection of Safety Compliance in Diverse Workplaces","date":"2024-08-13","arxiv_id":"2408.07146","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-prompt-words-learning-for-social","title":"Multi-task Prompt Words Learning for Social Media Content Generation","date":"2024-07-10","arxiv_id":"2407.07771","repositories_listed":0,"syntology":null},{"url":null,"slug":"channel-twinning-an-enabler-for-next","title":"Advancing Ubiquitous Wireless Connectivity through Channel Twinning","date":"2024-06-18","arxiv_id":"2406.12268","repositories_listed":0,"syntology":null},{"url":null,"slug":"non-negative-subspace-feature-representation","title":"Non-negative Subspace Feature Representation for Few-shot Learning in Medical Imaging","date":"2024-04-03","arxiv_id":"2404.02656","repositories_listed":0,"syntology":null},{"url":null,"slug":"textblockv2-towards-precise-detection-free","title":"TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model","date":"2024-03-15","arxiv_id":"2403.10047","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-vision-transformers-in-autonomous","title":"A Survey of Vision Transformers in Autonomous Driving: Current Trends and Future Directions","date":"2024-03-12","arxiv_id":"2403.07542","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-self-supervised-learning-for-scene","title":"Leveraging Self-Supervised Learning for Scene Classification in Child Sexual Abuse Imagery","date":"2024-03-02","arxiv_id":"2403.01183","repositories_listed":0,"syntology":null},{"url":null,"slug":"digital-divides-in-scene-recognition","title":"Digital Divides in Scene Recognition: Uncovering Socioeconomic Biases in Deep Learning Systems","date":"2024-01-23","arxiv_id":"2401.13097","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-enhanced-multi-perspective-video","title":"Knowledge-enhanced Multi-perspective Video Representation Learning for Scene Recognition","date":"2024-01-09","arxiv_id":"2401.04354","repositories_listed":0,"syntology":null},{"url":null,"slug":"inter-object-discriminative-graph-modeling","title":"Inter-object Discriminative Graph Modeling for Indoor Scene Recognition","date":"2023-11-10","arxiv_id":"2311.05919","repositories_listed":0,"syntology":null},{"url":null,"slug":"vispercep-a-vision-language-approach-to","title":"A Multi-Modal Foundation Model to Assist People with Blindness and Low Vision in Environmental Interaction","date":"2023-10-31","arxiv_id":"2310.20225","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-scene-location-recognition-with-neural","title":"Video Scene Location Recognition with Neural Networks","date":"2023-09-21","arxiv_id":"2309.11928","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-embedded-similarity-prototype-for","title":"Semantic-embedded Similarity Prototype for Scene Recognition","date":"2023-08-11","arxiv_id":"2308.05896","repositories_listed":0,"syntology":null},{"url":null,"slug":"entri-ensemble-learning-with-tri-level","title":"EnTri: Ensemble Learning with Tri-level Representations for Explainable Scene Recognition","date":"2023-07-23","arxiv_id":"2307.12442","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-query-vehicle-re-identification","title":"Multi-query Vehicle Re-identification: Viewpoint-conditioned Network, Unified Dataset and New Metric","date":"2023-05-25","arxiv_id":"2305.15764","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-guided-context-modeling-for-indoor","title":"Semantic-guided modeling of spatial relation and object co-occurrence for indoor scene recognition","date":"2023-05-22","arxiv_id":"2305.12661","repositories_listed":0,"syntology":null},{"url":null,"slug":"geonet-benchmarking-unsupervised-adaptation","title":"GeoNet: Benchmarking Unsupervised Adaptation across Geographies","date":"2023-03-27","arxiv_id":"2303.15443","repositories_listed":0,"syntology":null},{"url":null,"slug":"synergy-between-human-and-machine-approaches","title":"Synergy between human and machine approaches to sound/scene recognition and processing: An overview of ICASSP special session","date":"2023-02-20","arxiv_id":"2302.09719","repositories_listed":0,"syntology":null},{"url":null,"slug":"attentional-graph-convolutional-network-for","title":"Attentional Graph Convolutional Network for Structure-aware Audio-Visual Scene Classification","date":"2022-12-31","arxiv_id":"2301.00145","repositories_listed":0,"syntology":null},{"url":null,"slug":"coarse-to-fine-task-driven-inpainting-for","title":"Coarse-to-fine Task-driven Inpainting for Geoscience Images","date":"2022-11-20","arxiv_id":"2211.11059","repositories_listed":0,"syntology":null},{"url":null,"slug":"ambiguity-aware-multi-object-pose","title":"Ambiguity-Aware Multi-Object Pose Optimization for Visually-Assisted Robot Manipulation","date":"2022-11-02","arxiv_id":"2211.00960","repositories_listed":0,"syntology":null}],"syntology_records":9,"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":2,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/scene-recognition-on-aid","since_archive":"/sota/scene-recognition-on-aid#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/scene-recognition-on-sun-rgbd","since_archive":"/sota/scene-recognition-on-sun-rgbd#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":8,"papers_where_code_ran_first_page":"/task/scene-recognition/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":3,"url":"/task/scene-recognition/papers/2","json":"/task/scene-recognition/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/task/scene-recognition/papers/3","json":"/task/scene-recognition/papers/3.json","rows":7},{"order":"ran","page":1,"of":1,"url":"/task/scene-recognition/papers/ran/1","json":"/task/scene-recognition/papers/ran/1.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":"8d82c6eca622b5fc2dffc96218bbfe52801cfa8495bb9c00753b0feae90a0131","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}