{"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/video-object-detection","name":"Video Object Detection","slug":"video-object-detection","description_markdown":"Video object detection is the task of detecting objects from a video as opposed to images.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Learning Motion Priors for Efficient Video Object Detection](https://arxiv.org/pdf/1911.05253v1.pdf) )</span>","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":147,"papers_with_code":72,"benchmarks":7,"benchmark_tables_in_archive":8,"benchmark_tables_shown":7,"benchmark_tables_withheld_as_spam":1,"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":13,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/video-object-detection-on-imagenet-vid","slug":"video-object-detection-on-imagenet-vid","dataset":"ImageNet VID","dataset_url":"/dataset/imagenet-vid","rows_in_archive":33,"metrics":["MAP "],"first_row_in_archive_order":{"model":"YOLOV++","paper_title":"Practical Video Object Detection via Feature Selection and Aggregation","paper_url":"/paper/practical-video-object-detection-via-feature","paper_date":"2024-07-29","arxiv_id":"2407.19650","code_links":[{"title":"yuhengsss/yolov","url":"https://github.com/yuhengsss/yolov"}],"syntology":null}},{"leaderboard":"/sota/video-object-detection-on-epic-kitchens-1","slug":"video-object-detection-on-epic-kitchens-1","dataset":"EPIC KITCHENS-unseen splits","dataset_url":null,"rows_in_archive":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"Temporal ROI Align","paper_title":"Temporal RoI Align for Video Object Recognition","paper_url":"/paper/temporal-roi-align-for-video-object","paper_date":"2021-09-08","arxiv_id":"2109.03495","code_links":[{"title":"open-mmlab/mmtracking","url":"https://github.com/open-mmlab/mmtracking"}],"syntology":null}},{"leaderboard":"/sota/video-object-detection-on-epic-kitchens-55","slug":"video-object-detection-on-epic-kitchens-55","dataset":"EPIC-KITCHENS-55","dataset_url":"/dataset/epic-kitchens","rows_in_archive":1,"metrics":["mAP@.5"],"first_row_in_archive_order":{"model":"Ours (Faster RCNN)","paper_title":"Objects do not disappear: Video object detection by single-frame object location anticipation","paper_url":"/paper/objects-do-not-disappear-video-object","paper_date":"2023-08-09","arxiv_id":"2308.04770","code_links":[{"title":"l-kid/video-object-detection-by-location-anticipation","url":"https://github.com/l-kid/video-object-detection-by-location-anticipation"},{"title":"Elstuhn/Video-object-detection-by-location-anticipation","url":"https://github.com/Elstuhn/Video-object-detection-by-location-anticipation"}],"syntology":null}},{"leaderboard":"/sota/video-object-detection-on-epic-kitchens-seen","slug":"video-object-detection-on-epic-kitchens-seen","dataset":"EPIC KITCHENS-seen splits","dataset_url":null,"rows_in_archive":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"Temporal ROI Align","paper_title":"Temporal RoI Align for Video Object Recognition","paper_url":"/paper/temporal-roi-align-for-video-object","paper_date":"2021-09-08","arxiv_id":"2109.03495","code_links":[{"title":"open-mmlab/mmtracking","url":"https://github.com/open-mmlab/mmtracking"}],"syntology":null}},{"leaderboard":"/sota/video-object-detection-on-usc-grad-stddb","slug":"video-object-detection-on-usc-grad-stddb","dataset":"USC-GRAD-STDdb","dataset_url":"/dataset/usc-grad-stddb","rows_in_archive":1,"metrics":["AP","AP 0.5"],"first_row_in_archive_order":{"model":"SLTnet FPN-X101","paper_title":"Short-term anchor linking and long-term self-guided attention for video object detection","paper_url":"/paper/short-term-anchor-linking-and-long-term-self","paper_date":"2021-04-18","arxiv_id":null,"code_links":[{"title":"daniel-cores/SLTnet","url":"https://github.com/daniel-cores/SLTnet"}],"syntology":null}},{"leaderboard":"/sota/video-object-detection-on-waymo-open-dataset","slug":"video-object-detection-on-waymo-open-dataset","dataset":"Waymo Open Dataset","dataset_url":"/dataset/waymo-open-dataset","rows_in_archive":1,"metrics":["AP"],"first_row_in_archive_order":{"model":null,"paper_title":"Objects do not disappear: Video object detection by single-frame object location anticipation","paper_url":"/paper/objects-do-not-disappear-video-object","paper_date":"2023-08-09","arxiv_id":"2308.04770","code_links":[{"title":"l-kid/video-object-detection-by-location-anticipation","url":"https://github.com/l-kid/video-object-detection-by-location-anticipation"},{"title":"Elstuhn/Video-object-detection-by-location-anticipation","url":"https://github.com/Elstuhn/Video-object-detection-by-location-anticipation"}],"syntology":null}},{"leaderboard":"/sota/video-object-detection-on-yt-bb","slug":"video-object-detection-on-yt-bb","dataset":"YT-BB","dataset_url":"/dataset/youtube-boundingboxes","rows_in_archive":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":null,"paper_title":"Objects do not disappear: Video object detection by single-frame object location anticipation","paper_url":"/paper/objects-do-not-disappear-video-object","paper_date":"2023-08-09","arxiv_id":"2308.04770","code_links":[{"title":"l-kid/video-object-detection-by-location-anticipation","url":"https://github.com/l-kid/video-object-detection-by-location-anticipation"},{"title":"Elstuhn/Video-object-detection-by-location-anticipation","url":"https://github.com/Elstuhn/Video-object-detection-by-location-anticipation"}],"syntology":null}}],"datasets":[{"url":"/dataset/waymo-open-dataset","name":"Waymo Open Dataset","full_name":"","num_papers_in_archive":481},{"url":"/dataset/epic-kitchens","name":"EPIC-KITCHENS-55","full_name":"","num_papers_in_archive":42},{"url":"/dataset/imagenet-vid","name":"ImageNet VID","full_name":"","num_papers_in_archive":26},{"url":"/dataset/gen1-detection","name":"GEN1 Detection","full_name":"Prophesee GEN1 Automotive Detection Dataset","num_papers_in_archive":13},{"url":"/dataset/dttd2","name":"DTTD-Mobile","full_name":"","num_papers_in_archive":8},{"url":"/dataset/youtube-boundingboxes","name":"YT-BB","full_name":"YouTube-BoundingBoxes","num_papers_in_archive":7},{"url":"/dataset/oak","name":"OAK","full_name":"Objects Around Krishna","num_papers_in_archive":5},{"url":"/dataset/synthia-al","name":"SYNTHIA-AL","full_name":"","num_papers_in_archive":5},{"url":"/dataset/5011-images-human-frontal-face-data-male","name":"5,011 Images – Human Frontal face Data (Male)","full_name":"5,011 Images – Human Frontal face Data (Male)","num_papers_in_archive":2},{"url":"/dataset/underwater-trash-detection","name":"Underwater Trash Detection","full_name":"","num_papers_in_archive":2},{"url":"/dataset/thgp","name":"THGP","full_name":"Temporal Hands Guns and Phones Dataset","num_papers_in_archive":1},{"url":"/dataset/usc-grad-stddb","name":"USC-GRAD-STDdb","full_name":"Small Target Detection database","num_papers_in_archive":1},{"url":"/dataset/visem-tracking","name":"VISEM-Tracking","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/object-detection","name":"Object Detection"}],"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":2,"rows_per_page":100,"shown":100,"of":147,"of_with_code":72,"tagged_in_all":147,"counts":{"archive_papers_tagged":147,"with_a_code_link":72,"where_syntology_ran_a_sample":12,"not_listed_spam_title":0,"listed":147,"listed_where_code_ran":12,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":11,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":11,"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/emerging-properties-in-self-supervised-vision","slug":"emerging-properties-in-self-supervised-vision","title":"Emerging Properties in Self-Supervised Vision Transformers","date":"2021-04-29","arxiv_id":"2104.14294","repositories_listed":32,"syntology":{"n":20,"n_ran":14,"n_constructed":0,"n_ran_checked":10,"n_instrument":4,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":9,"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, 1 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/emerging-properties-in-self-supervised-vision#ran","syntology_url":"https://syntology.ai/paper/2104.14294","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14294"}},"official":{"repos":["facebookresearch/dino"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/temporal-shift-module-for-efficient-video","slug":"temporal-shift-module-for-efficient-video","title":"TSM: Temporal Shift Module for Efficient Video Understanding","date":"2018-11-20","arxiv_id":"1811.08383","repositories_listed":13,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":6,"n_honours":1,"n_violates":0,"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: 1 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/temporal-shift-module-for-efficient-video#ran","syntology_url":"https://syntology.ai/paper/1811.08383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.08383"}},"official":{"repos":["MIT-HAN-LAB/temporal-shift-module"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/transvod-end-to-end-video-object-detection","slug":"transvod-end-to-end-video-object-detection","title":"TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers","date":"2022-01-13","arxiv_id":"2201.05047","repositories_listed":3,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/transvod-end-to-end-video-object-detection#ran","syntology_url":"https://syntology.ai/paper/2201.05047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.05047"}},"official":{"repos":["qianyuzqy/TransVOD_Lite"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["named_in_paper","official"]}}},{"url":"/paper/houghnet-integrating-near-and-long-range-1","slug":"houghnet-integrating-near-and-long-range-1","title":"HoughNet: Integrating near and long-range evidence for visual detection","date":"2021-04-14","arxiv_id":"2104.06773","repositories_listed":3,"syntology":null},{"url":"/paper/long-term-temporal-context-for-per-camera","slug":"long-term-temporal-context-for-per-camera","title":"Context R-CNN: Long Term Temporal Context for Per-Camera Object Detection","date":"2019-12-07","arxiv_id":"1912.03538","repositories_listed":3,"syntology":null},{"url":"/paper/transferable-adversarial-attacks-for-image","slug":"transferable-adversarial-attacks-for-image","title":"Transferable Adversarial Attacks for Image and Video Object Detection","date":"2018-11-30","arxiv_id":"1811.12641","repositories_listed":3,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/transferable-adversarial-attacks-for-image#ran","syntology_url":"https://syntology.ai/paper/1811.12641","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.12641"}},"official":null}},{"url":"/paper/towards-high-performance-video-object","slug":"towards-high-performance-video-object","title":"Towards High Performance Video Object Detection for Mobiles","date":"2018-04-16","arxiv_id":"1804.05830","repositories_listed":3,"syntology":null},{"url":"/paper/mobile-video-object-detection-with-temporally","slug":"mobile-video-object-detection-with-temporally","title":"Mobile Video Object Detection with Temporally-Aware Feature Maps","date":"2017-11-17","arxiv_id":"1711.06368","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mobile-video-object-detection-with-temporally#ran","syntology_url":"https://syntology.ai/paper/1711.06368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.06368"}},"official":null}},{"url":"/paper/spatio-temporal-prompting-network-for-robust-1","slug":"spatio-temporal-prompting-network-for-robust-1","title":"Spatio-temporal Prompting Network for Robust Video Feature Extraction","date":"2024-02-04","arxiv_id":"2402.02574","repositories_listed":2,"syntology":null},{"url":"/paper/objects-do-not-disappear-video-object","slug":"objects-do-not-disappear-video-object","title":"Objects do not disappear: Video object detection by single-frame object location anticipation","date":"2023-08-09","arxiv_id":"2308.04770","repositories_listed":2,"syntology":null},{"url":"/paper/instance-aware-context-focused-and-memory","slug":"instance-aware-context-focused-and-memory","title":"Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection","date":"2020-04-09","arxiv_id":"2004.04725","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/instance-aware-context-focused-and-memory#ran","syntology_url":"https://syntology.ai/paper/2004.04725","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04725"}},"official":{"repos":["NVlabs/wetectron"],"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/memory-enhanced-global-local-aggregation-for","slug":"memory-enhanced-global-local-aggregation-for","title":"Memory Enhanced Global-Local Aggregation for Video Object Detection","date":"2020-03-26","arxiv_id":"2003.12063","repositories_listed":2,"syntology":null},{"url":"/paper/plug-play-convolutional-regression-tracker","slug":"plug-play-convolutional-regression-tracker","title":"Plug & Play Convolutional Regression Tracker for Video Object Detection","date":"2020-03-02","arxiv_id":"2003.00981","repositories_listed":2,"syntology":null},{"url":"/paper/vision-meets-drones-past-present-and-future","slug":"vision-meets-drones-past-present-and-future","title":"Detection and Tracking Meet Drones Challenge","date":"2020-01-16","arxiv_id":"2001.06303","repositories_listed":2,"syntology":null},{"url":"/paper/relation-distillation-networks-for-video","slug":"relation-distillation-networks-for-video","title":"Relation Distillation Networks for Video Object Detection","date":"2019-08-26","arxiv_id":"1908.09511","repositories_listed":2,"syntology":null},{"url":"/paper/sequence-level-semantics-aggregation-for","slug":"sequence-level-semantics-aggregation-for","title":"Sequence Level Semantics Aggregation for Video Object Detection","date":"2019-07-15","arxiv_id":"1907.06390","repositories_listed":2,"syntology":null},{"url":"/paper/looking-fast-and-slow-memory-guided-mobile","slug":"looking-fast-and-slow-memory-guided-mobile","title":"Looking Fast and Slow: Memory-Guided Mobile Video Object Detection","date":"2019-03-25","arxiv_id":"1903.10172","repositories_listed":2,"syntology":null},{"url":"/paper/flow-guided-feature-aggregation-for-video","slug":"flow-guided-feature-aggregation-for-video","title":"Flow-Guided Feature Aggregation for Video Object Detection","date":"2017-03-29","arxiv_id":"1703.10025","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 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) · 1 unverified","sample_list":"/paper/flow-guided-feature-aggregation-for-video#ran","syntology_url":"https://syntology.ai/paper/1703.10025","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.10025"}},"official":{"repos":["msracver/Flow-Guided-Feature-Aggregation"],"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":["official"]}}},{"url":"/paper/fade-a-dataset-for-detecting-falling-objects","slug":"fade-a-dataset-for-detecting-falling-objects","title":"FADE: A Dataset for Detecting Falling Objects around Buildings in Video","date":"2024-08-11","arxiv_id":"2408.05750","repositories_listed":1,"syntology":null},{"url":"/paper/practical-video-object-detection-via-feature","slug":"practical-video-object-detection-via-feature","title":"Practical Video Object Detection via Feature Selection and Aggregation","date":"2024-07-29","arxiv_id":"2407.19650","repositories_listed":1,"syntology":null},{"url":"/paper/multi-resolution-rescored-bytetrack-for-video","slug":"multi-resolution-rescored-bytetrack-for-video","title":"Multi-resolution Rescored ByteTrack for Video Object Detection on Ultra-low-power Embedded Systems","date":"2024-04-17","arxiv_id":"2404.11488","repositories_listed":1,"syntology":null},{"url":"/paper/camera-clustering-for-scalable-stream-based","slug":"camera-clustering-for-scalable-stream-based","title":"Camera clustering for scalable stream-based active distillation","date":"2024-04-16","arxiv_id":"2404.10411","repositories_listed":1,"syntology":null},{"url":"/paper/detection-of-micromobility-vehicles-in-urban","slug":"detection-of-micromobility-vehicles-in-urban","title":"Detection of Micromobility Vehicles in Urban Traffic Videos","date":"2024-02-28","arxiv_id":"2402.18503","repositories_listed":1,"syntology":null},{"url":"/paper/stf-spatio-temporal-fusion-module-for","slug":"stf-spatio-temporal-fusion-module-for","title":"STF: Spatio-Temporal Fusion Module for Improving Video Object Detection","date":"2024-02-16","arxiv_id":"2402.10752","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-one-stage-video-object-detection-by","slug":"efficient-one-stage-video-object-detection-by","title":"Efficient One-stage Video Object Detection by Exploiting Temporal Consistency","date":"2024-02-14","arxiv_id":"2402.09241","repositories_listed":1,"syntology":null},{"url":"/paper/tdvit-temporal-dilated-video-transformer-for","slug":"tdvit-temporal-dilated-video-transformer-for","title":"TDViT: Temporal Dilated Video Transformer for Dense Video Tasks","date":"2024-02-14","arxiv_id":"2402.09257","repositories_listed":1,"syntology":null},{"url":"/paper/mamba-multi-level-aggregation-via-memory-bank","slug":"mamba-multi-level-aggregation-via-memory-bank","title":"MAMBA: Multi-level Aggregation via Memory Bank for Video Object Detection","date":"2024-01-18","arxiv_id":"2401.09923","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mamba-multi-level-aggregation-via-memory-bank#ran","syntology_url":"https://syntology.ai/paper/2401.09923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09923"}},"official":{"repos":["guanxiongsun/vfe.pytorch"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/diffusionvid-denoising-object-boxes-with","slug":"diffusionvid-denoising-object-boxes-with","title":"DiffusionVID: Denoising Object Boxes with Spatio-temporal Conditioning for Video Object Detection","date":"2023-10-30","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/eventful-transformers-leveraging-temporal","slug":"eventful-transformers-leveraging-temporal","title":"Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformers","date":"2023-08-25","arxiv_id":"2308.13494","repositories_listed":1,"syntology":{"n":25,"n_ran":7,"n_constructed":1,"n_ran_checked":3,"n_instrument":4,"n_unverified":18,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 18 unverified","sample_list":"/paper/eventful-transformers-leveraging-temporal#ran","syntology_url":"https://syntology.ai/paper/2308.13494","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.13494"}},"official":{"repos":["WISION-Lab/eventful-transformer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":18,"ran_from_kinds":["official"]}}},{"url":"/paper/object-detection-difficulty-suppressing-over","slug":"object-detection-difficulty-suppressing-over","title":"Object Detection Difficulty: Suppressing Over-aggregation for Faster and Better Video Object Detection","date":"2023-08-22","arxiv_id":"2308.11327","repositories_listed":1,"syntology":null},{"url":"/paper/identity-consistent-aggregation-for-video","slug":"identity-consistent-aggregation-for-video","title":"Identity-Consistent Aggregation for Video Object Detection","date":"2023-08-15","arxiv_id":"2308.07737","repositories_listed":1,"syntology":null},{"url":"/paper/featenhancer-enhancing-hierarchical-features","slug":"featenhancer-enhancing-hierarchical-features","title":"FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision","date":"2023-08-07","arxiv_id":"2308.03594","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 1 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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/featenhancer-enhancing-hierarchical-features#ran","syntology_url":"https://syntology.ai/paper/2308.03594","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.03594"}},"official":{"repos":["khurramHashmi/FeatEnHancer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/video-object-detection-for-privacy-preserving","slug":"video-object-detection-for-privacy-preserving","title":"Video object detection for privacy-preserving patient monitoring in intensive care","date":"2023-06-26","arxiv_id":"2306.14620","repositories_listed":1,"syntology":null},{"url":"/paper/3d-video-object-detection-with-learnable","slug":"3d-video-object-detection-with-learnable","title":"3D Video Object Detection with Learnable Object-Centric Global Optimization","date":"2023-03-27","arxiv_id":"2303.15416","repositories_listed":1,"syntology":null},{"url":"/paper/faq-feature-aggregated-queries-for","slug":"faq-feature-aggregated-queries-for","title":"FAQ: Feature Aggregated Queries for Transformer-based Video Object Detectors","date":"2023-03-15","arxiv_id":"2303.08319","repositories_listed":1,"syntology":null},{"url":"/paper/feature-aggregated-queries-for-transformer","slug":"feature-aggregated-queries-for-transformer","title":"Feature Aggregated Queries for Transformer-Based Video Object Detectors","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fewer-is-more-efficient-object-detection-in","slug":"fewer-is-more-efficient-object-detection-in","title":"Fewer is More: Efficient Object Detection in Large Aerial Images","date":"2022-12-26","arxiv_id":"2212.13136","repositories_listed":1,"syntology":null},{"url":"/paper/roboflow-100-a-rich-multi-domain-object","slug":"roboflow-100-a-rich-multi-domain-object","title":"Roboflow 100: A Rich, Multi-Domain Object Detection Benchmark","date":"2022-11-24","arxiv_id":"2211.13523","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/roboflow-100-a-rich-multi-domain-object#ran","syntology_url":"https://syntology.ai/paper/2211.13523","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.13523"}},"official":{"repos":["roboflow-ai/roboflow-100-benchmark"],"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/deep-learning-based-computer-vision-approach","slug":"deep-learning-based-computer-vision-approach","title":"Deep-Learning-Based Computer Vision Approach For The Segmentation Of Ball Deliveries And Tracking In Cricket","date":"2022-11-22","arxiv_id":"2211.12009","repositories_listed":1,"syntology":null},{"url":"/paper/ptseformer-progressive-temporal-spatial","slug":"ptseformer-progressive-temporal-spatial","title":"PTSEFormer: Progressive Temporal-Spatial Enhanced TransFormer Towards Video Object Detection","date":"2022-09-06","arxiv_id":"2209.02242","repositories_listed":1,"syntology":{"n":21,"n_ran":14,"n_constructed":11,"n_ran_checked":13,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"14 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/ptseformer-progressive-temporal-spatial#ran","syntology_url":"https://syntology.ai/paper/2209.02242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.02242"}},"official":{"repos":["hon-wong/ptseformer"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":11,"n_ran_no_instrument_failure":13,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/yolov-making-still-image-object-detectors","slug":"yolov-making-still-image-object-detectors","title":"YOLOV: Making Still Image Object Detectors Great at Video Object Detection","date":"2022-08-20","arxiv_id":"2208.09686","repositories_listed":1,"syntology":null},{"url":"/paper/video-sparse-transformer-with-attention","slug":"video-sparse-transformer-with-attention","title":"Video Sparse Transformer With Attention-Guided Memory for Video Object Detection","date":"2022-06-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/streaming-multiscale-deep-equilibrium-models","slug":"streaming-multiscale-deep-equilibrium-models","title":"Representation Recycling for Streaming Video Analysis","date":"2022-04-28","arxiv_id":"2204.13492","repositories_listed":1,"syntology":null},{"url":"/paper/delta-distillation-for-efficient-video","slug":"delta-distillation-for-efficient-video","title":"Delta Distillation for Efficient Video Processing","date":"2022-03-17","arxiv_id":"2203.09594","repositories_listed":1,"syntology":null},{"url":"/paper/tyolov5-a-temporal-yolov5-detector-based-on","slug":"tyolov5-a-temporal-yolov5-detector-based-on","title":"TYolov5: A Temporal Yolov5 Detector Based on Quasi-Recurrent Neural Networks for Real-Time Handgun Detection in Video","date":"2021-11-17","arxiv_id":"2111.08867","repositories_listed":1,"syntology":null},{"url":"/paper/ai-accelerator-survey-and-trends","slug":"ai-accelerator-survey-and-trends","title":"AI Accelerator Survey and Trends","date":"2021-09-18","arxiv_id":"2109.08957","repositories_listed":1,"syntology":null},{"url":"/paper/ffavod-feature-fusion-architecture-for-video","slug":"ffavod-feature-fusion-architecture-for-video","title":"FFAVOD: Feature Fusion Architecture for Video Object Detection","date":"2021-09-15","arxiv_id":"2109.07298","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-roi-align-for-video-object","slug":"temporal-roi-align-for-video-object","title":"Temporal RoI Align for Video Object Recognition","date":"2021-09-08","arxiv_id":"2109.03495","repositories_listed":1,"syntology":null},{"url":"/paper/tf-blender-temporal-feature-blender-for-video","slug":"tf-blender-temporal-feature-blender-for-video","title":"TF-Blender: Temporal Feature Blender for Video Object Detection","date":"2021-08-12","arxiv_id":"2108.05821","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-video-object-detection-with","slug":"end-to-end-video-object-detection-with","title":"End-to-End Video Object Detection with Spatial-Temporal Transformers","date":"2021-05-23","arxiv_id":"2105.10920","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-video-object-detection","slug":"few-shot-video-object-detection","title":"Few-Shot Video Object Detection","date":"2021-04-30","arxiv_id":"2104.14805","repositories_listed":1,"syntology":null},{"url":"/paper/motion-vector-extrapolation-for-video-object","slug":"motion-vector-extrapolation-for-video-object","title":"Motion Vector Extrapolation for Video Object Detection","date":"2021-04-18","arxiv_id":"2104.08918","repositories_listed":1,"syntology":null},{"url":"/paper/short-term-anchor-linking-and-long-term-self","slug":"short-term-anchor-linking-and-long-term-self","title":"Short-term anchor linking and long-term self-guided attention for video object detection","date":"2021-04-18","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/real-time-and-accurate-object-detection-in","slug":"real-time-and-accurate-object-detection-in","title":"Real-Time and Accurate Object Detection in Compressed Video by Long Short-term Feature Aggregation","date":"2021-03-25","arxiv_id":"2103.14529","repositories_listed":1,"syntology":null},{"url":"/paper/patchnet-short-range-template-matching-for","slug":"patchnet-short-range-template-matching-for","title":"PatchNet -- Short-range Template Matching for Efficient Video Processing","date":"2021-03-10","arxiv_id":"2103.07371","repositories_listed":1,"syntology":null},{"url":"/paper/joint-representation-of-temporal-image","slug":"joint-representation-of-temporal-image","title":"Joint Representation of Temporal Image Sequences and Object Motion for Video Object Detection","date":"2020-11-20","arxiv_id":"2011.10278","repositories_listed":1,"syntology":null},{"url":"/paper/approxdet-content-and-contention-aware","slug":"approxdet-content-and-contention-aware","title":"ApproxDet: Content and Contention-Aware Approximate Object Detection for Mobiles","date":"2020-10-21","arxiv_id":"2010.10754","repositories_listed":1,"syntology":null},{"url":"/paper/robust-and-efficient-post-processing-for","slug":"robust-and-efficient-post-processing-for","title":"Robust and Efficient Post-Processing for Video Object Detection (REPP)","date":"2020-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/robust-and-efficient-post-processing-for-1","slug":"robust-and-efficient-post-processing-for-1","title":"Robust and efficient post-processing for video object detection","date":"2020-09-23","arxiv_id":"2009.11050","repositories_listed":1,"syntology":null},{"url":"/paper/mining-inter-video-proposal-relations-for","slug":"mining-inter-video-proposal-relations-for","title":"Mining Inter-Video Proposal Relations for Video Object Detection","date":"2020-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/lidar-based-online-3d-video-object-detection","slug":"lidar-based-online-3d-video-object-detection","title":"LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention","date":"2020-04-03","arxiv_id":"2004.01389","repositories_listed":1,"syntology":null},{"url":"/paper/rn-vid-a-feature-fusion-architecture-for","slug":"rn-vid-a-feature-fusion-architecture-for","title":"RN-VID: A Feature Fusion Architecture for Video Object Detection","date":"2020-03-24","arxiv_id":"2003.10898","repositories_listed":1,"syntology":null},{"url":"/paper/argus-efficient-activity-detection-system-for","slug":"argus-efficient-activity-detection-system-for","title":"Argus: Efficient Activity Detection System for Extended Video Analysis","date":"2020-03-02","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-motion-priors-for-efficient-video","slug":"learning-motion-priors-for-efficient-video","title":"Learning Where to Focus for Efficient Video Object Detection","date":"2019-11-13","arxiv_id":"1911.05253","repositories_listed":1,"syntology":null},{"url":"/paper/a-delay-metric-for-video-object-detection","slug":"a-delay-metric-for-video-object-detection","title":"A Delay Metric for Video Object Detection: What Average Precision Fails to Tell","date":"2019-08-18","arxiv_id":"1908.06368","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-spatio-temporally-grounding","slug":"weakly-supervised-spatio-temporally-grounding","title":"Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video","date":"2019-06-06","arxiv_id":"1906.02549","repositories_listed":1,"syntology":null},{"url":"/paper/a-systematic-framework-for-natural","slug":"a-systematic-framework-for-natural","title":"Do Image Classifiers Generalize Across Time?","date":"2019-06-05","arxiv_id":"1906.02168","repositories_listed":1,"syntology":null},{"url":"/paper/road-user-detection-in-videos","slug":"road-user-detection-in-videos","title":"Road User Detection in Videos","date":"2019-03-28","arxiv_id":"1903.12049","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-video-object-detection-via-a-scale","slug":"optimizing-video-object-detection-via-a-scale","title":"Optimizing Video Object Detection via a Scale-Time Lattice","date":"2018-04-16","arxiv_id":"1804.05472","repositories_listed":1,"syntology":null},{"url":"/paper/video-object-detection-with-an-aligned","slug":"video-object-detection-with-an-aligned","title":"Video Object Detection with an Aligned Spatial-Temporal Memory","date":"2017-12-18","arxiv_id":"1712.06317","repositories_listed":1,"syntology":null},{"url":"/paper/structure-measure-a-new-way-to-evaluate","slug":"structure-measure-a-new-way-to-evaluate","title":"Structure-measure: A New Way to Evaluate Foreground Maps","date":"2017-08-02","arxiv_id":"1708.00786","repositories_listed":1,"syntology":null},{"url":"/paper/seq-nms-for-video-object-detection","slug":"seq-nms-for-video-object-detection","title":"Seq-NMS for Video Object Detection","date":"2016-02-26","arxiv_id":"1602.08465","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/seq-nms-for-video-object-detection#ran","syntology_url":"https://syntology.ai/paper/1602.08465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.08465"}},"official":null}},{"url":null,"slug":"lightweight-multi-frame-integration-for","title":"Lightweight Multi-Frame Integration for Robust YOLO Object Detection in Videos","date":"2025-06-25","arxiv_id":"2506.20550","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-spatio-temporal-graph-learning-for","title":"Multimodal Spatio-temporal Graph Learning for Alignment-free RGBT Video Object Detection","date":"2025-04-16","arxiv_id":"2504.11779","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-in-object-detection-a-systematic","title":"Context in object detection: a systematic literature review","date":"2025-03-29","arxiv_id":"2503.23249","repositories_listed":0,"syntology":null},{"url":null,"slug":"region-masking-to-accelerate-video-processing","title":"Region Masking to Accelerate Video Processing on Neuromorphic Hardware","date":"2025-03-21","arxiv_id":"2503.16775","repositories_listed":0,"syntology":null},{"url":"/paper/tgbformer-transformer-graphformer-blender","slug":"tgbformer-transformer-graphformer-blender","title":"TGBFormer: Transformer-GraphFormer Blender Network for Video Object Detection","date":"2025-03-18","arxiv_id":"2503.13903","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-boxes-mask-guided-spatio-temporal","title":"Beyond Boxes: Mask-Guided Spatio-Temporal Feature Aggregation for Video Object Detection","date":"2024-12-06","arxiv_id":"2412.04915","repositories_listed":0,"syntology":null},{"url":null,"slug":"estimation-of-psychosocial-work-environment","title":"Estimation of Psychosocial Work Environment Exposures Through Video Object Detection. Proof of Concept Using CCTV Footage","date":"2024-11-06","arxiv_id":"2411.03724","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-the-limits-of-alignment-multi-modal","title":"Mixture of Scale Experts for Alignment-free RGBT Video Object Detection and A Unified Benchmark","date":"2024-10-16","arxiv_id":"2410.12143","repositories_listed":0,"syntology":null},{"url":null,"slug":"xs-vid-an-extremely-small-video-object","title":"XS-VID: An Extremely Small Video Object Detection Dataset","date":"2024-07-25","arxiv_id":"2407.18137","repositories_listed":0,"syntology":null},{"url":null,"slug":"maskvd-region-masking-for-efficient-video","title":"MaskVD: Region Masking for Efficient Video Object Detection","date":"2024-07-16","arxiv_id":"2407.12067","repositories_listed":0,"syntology":null},{"url":null,"slug":"ssga-net-stepwise-spatial-global-local","title":"SSGA-Net: Stepwise Spatial Global-local Aggregation Networks for for Autonomous Driving","date":"2024-05-29","arxiv_id":"2405.18857","repositories_listed":0,"syntology":null},{"url":null,"slug":"source-free-domain-adaptation-for-video","title":"Source-free Domain Adaptation for Video Object Detection Under Adverse Image Conditions","date":"2024-04-23","arxiv_id":"2404.15252","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-enhanced-analysis-of-lung-cancer","title":"Towards Enhanced Analysis of Lung Cancer Lesions in EBUS-TBNA -- A Semi-Supervised Video Object Detection Method","date":"2024-04-02","arxiv_id":"2404.01929","repositories_listed":0,"syntology":null},{"url":"/paper/0-1-laws-for-pattern-occurrences-in","slug":"0-1-laws-for-pattern-occurrences-in","title":"0-1 laws for pattern occurrences in phylogenetic trees and networks","date":"2024-02-07","arxiv_id":"2402.04499","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-enhanced-transformer-for-single-image","title":"Context Enhanced Transformer for Single Image Object Detection","date":"2023-12-22","arxiv_id":"2312.14492","repositories_listed":0,"syntology":null},{"url":null,"slug":"traffic-video-object-detection-using-motion","title":"Traffic Video Object Detection using Motion Prior","date":"2023-11-16","arxiv_id":"2311.10092","repositories_listed":0,"syntology":null},{"url":null,"slug":"erasure-based-interaction-network-for-rgbt","title":"Erasure-based Interaction Network for RGBT Video Object Detection and A Unified Benchmark","date":"2023-08-03","arxiv_id":"2308.01630","repositories_listed":0,"syntology":null},{"url":null,"slug":"deteksi-sampah-di-permukaan-dan-dalam","title":"Deteksi Sampah di Permukaan dan Dalam Perairan pada Objek Video dengan Metode Robust and Efficient Post-Processing dan Tubelet-Level Bounding Box Linking","date":"2023-07-14","arxiv_id":"2307.10039","repositories_listed":0,"syntology":null},{"url":null,"slug":"transflow-transformer-as-flow-learner","title":"TransFlow: Transformer as Flow Learner","date":"2023-04-23","arxiv_id":"2304.11523","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-maps-for-video-object-detection-and","title":"Memory Maps for Video Object Detection and Tracking on UAVs","date":"2023-03-06","arxiv_id":"2303.03508","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-images-and-videos-a-simple-learning","title":"Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detection","date":"2022-12-20","arxiv_id":"2212.10147","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-model-for-tracking-and-image-video","title":"Unifying Tracking and Image-Video Object Detection","date":"2022-11-20","arxiv_id":"2211.11077","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-unsupervised-video-object","title":"Efficient Unsupervised Video Object Segmentation Network Based on Motion Guidance","date":"2022-11-10","arxiv_id":"2211.05364","repositories_listed":0,"syntology":null},{"url":"/paper/boxmask-revisiting-bounding-box-supervision","slug":"boxmask-revisiting-bounding-box-supervision","title":"BoxMask: Revisiting Bounding Box Supervision for Video Object Detection","date":"2022-10-12","arxiv_id":"2210.06008","repositories_listed":0,"syntology":null},{"url":"/paper/spatio-temporal-learnable-proposals-for-end","slug":"spatio-temporal-learnable-proposals-for-end","title":"Spatio-Temporal Learnable Proposals for End-to-End Video Object Detection","date":"2022-10-05","arxiv_id":"2210.02368","repositories_listed":0,"syntology":null},{"url":null,"slug":"dfa-dynamic-feature-aggregation-for-efficient","title":"DFA: Dynamic Feature Aggregation for Efficient Video Object Detection","date":"2022-10-02","arxiv_id":"2210.00588","repositories_listed":0,"syntology":null},{"url":"/paper/dafa-diversity-aware-feature-aggregation-for","slug":"dafa-diversity-aware-feature-aggregation-for","title":"DAFA: Diversity-Aware Feature Aggregation for Attention-Based Video Object Detection","date":"2022-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"temporalnet-real-time-2d-3d-video-object","title":"TemporalNet: Real-time 2D-3D Video Object Detection","date":"2022-08-29","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":13,"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":12,"papers_where_code_ran_first_page":"/task/video-object-detection/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":2,"url":"/task/video-object-detection/papers/2","json":"/task/video-object-detection/papers/2.json","rows":47},{"order":"ran","page":1,"of":1,"url":"/task/video-object-detection/papers/ran/1","json":"/task/video-object-detection/papers/ran/1.json","rows":12}],"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":"9ac3dc2f435b5752ab7dd8c81b4d7c8e716789778557cef7a48648abc28a2634","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}