{"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/papers/2","list_of":"/task/video-object-detection","task":"Video Object Detection","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":2,"rows_per_page":100,"rows":[101,147],"of":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":12,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":12,"listed_every_run_a_failure_of_syntologys_instrument":0,"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"},"first_page":"/task/video-object-detection","prev":"/task/video-object-detection","next":null,"papers":[{"url":null,"slug":"real-time-robust-video-object-detection","title":"Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks","date":"2022-08-19","arxiv_id":"2208.09195","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-neural-network-and-spatiotemporal","title":"Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Clouds","date":"2022-07-26","arxiv_id":"2207.12659","repositories_listed":0,"syntology":null},{"url":null,"slug":"queryprop-object-query-propagation-for-high","title":"QueryProp: Object Query Propagation for High-Performance Video Object Detection","date":"2022-07-22","arxiv_id":"2207.10959","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-temporally-dynamic-data","title":"Exploring Temporally Dynamic Data Augmentation for Video Recognition","date":"2022-06-30","arxiv_id":"2206.15015","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-object-tracking-research-a-survey","title":"Single Object Tracking Research: A Survey","date":"2022-04-25","arxiv_id":"2204.11410","repositories_listed":0,"syntology":null},{"url":null,"slug":"salisa-saliency-based-input-sampling-for","title":"SALISA: Saliency-based Input Sampling for Efficient Video Object Detection","date":"2022-04-05","arxiv_id":"2204.02397","repositories_listed":0,"syntology":null},{"url":null,"slug":"smartadapt-multi-branch-object-detection","title":"SmartAdapt: Multi-Branch Object Detection Framework for Videos on Mobiles","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"virtuoso-video-based-intelligence-for-real","title":"Virtuoso: Video-based Intelligence for real-time tuning on SOCs","date":"2021-12-24","arxiv_id":"2112.13076","repositories_listed":0,"syntology":null},{"url":null,"slug":"siampolar-semi-supervised-realtime-video","title":"SiamPolar: Semi-supervised Realtime Video Object Segmentation with Polar Representation","date":"2021-10-27","arxiv_id":"2110.14773","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-early-exits-for-efficient-video","title":"Temporal Early Exits for Efficient Video Object Detection","date":"2021-06-21","arxiv_id":"2106.11208","repositories_listed":0,"syntology":null},{"url":null,"slug":"sge-net-video-object-detection-with-squeezed","title":"SGE net: Video object detection with squeezed GRU and information entropy map","date":"2021-06-14","arxiv_id":"2106.07224","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-learning-for-video-object-detection","title":"When Few-Shot Learning Meets Video Object Detection","date":"2021-03-26","arxiv_id":"2103.14724","repositories_listed":0,"syntology":null},{"url":null,"slug":"new-generation-deep-learning-for-video-object","title":"New Generation Deep Learning For Video Object Dection:A Survery","date":"2021-02-03","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-channel-transformer-for-3d-lidar","title":"Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving","date":"2020-11-27","arxiv_id":"2011.13628","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-analysis-of-deep-object-detectors-for","title":"An Analysis of Deep Object Detectors For Diver Detection","date":"2020-11-25","arxiv_id":"2012.05701","repositories_listed":0,"syntology":null},{"url":null,"slug":"recurrent-neural-networks-for-video-object","title":"Recurrent Neural Networks for video object detection","date":"2020-10-29","arxiv_id":"2010.15740","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-aware-feature-aggregation-for-video","title":"Object-aware Feature Aggregation for Video Object Detection","date":"2020-10-23","arxiv_id":"2010.12573","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-flow-in-network-feature-flow","title":"Feature Flow: In-network Feature Flow Estimation for Video Object Detection","date":"2020-09-21","arxiv_id":"2009.09660","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-semantic-fusion-network-for-video-object","title":"Dual Semantic Fusion Network for Video Object Detection","date":"2020-09-16","arxiv_id":"2009.07498","repositories_listed":0,"syntology":null},{"url":null,"slug":"survey-of-machine-learning-accelerators","title":"Survey of Machine Learning Accelerators","date":"2020-09-01","arxiv_id":"2009.00993","repositories_listed":0,"syntology":null},{"url":null,"slug":"centernet-heatmap-propagation-for-real-time","title":"CenterNet Heatmap Propagation for Real-time Video Object Detection","date":"2020-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"video-object-detection-via-object-level","title":"Video Object Detection via Object-level Temporal Aggregation","date":"2020-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"continuity-stability-and-integration-novel","title":"Rethinking Temporal Object Detection from Robotic Perspectives","date":"2019-12-22","arxiv_id":"1912.10406","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-long-range-temporal-relationships","title":"Leveraging Long-Range Temporal Relationships Between Proposals for Video Object Detection","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"object-guided-external-memory-network-for","title":"Object Guided External Memory Network for Video Object Detection","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"geometry-aware-video-object-detection-for","title":"Geometry-Aware Video Object Detection for Static Cameras","date":"2019-09-06","arxiv_id":"1909.03140","repositories_listed":0,"syntology":null},{"url":"/paper/temporal-coherence-for-active-learning-in","slug":"temporal-coherence-for-active-learning-in","title":"Temporal Coherence for Active Learning in Videos","date":"2019-08-30","arxiv_id":"1908.11757","repositories_listed":0,"syntology":null},{"url":null,"slug":"great-ape-detection-in-challenging-jungle","title":"Great Ape Detection in Challenging Jungle Camera Trap Footage via Attention-Based Spatial and Temporal Feature Blending","date":"2019-08-29","arxiv_id":"1908.11240","repositories_listed":0,"syntology":null},{"url":null,"slug":"report-on-ug2-challenge-track-1-assessing","title":"Report on UG^2+ Challenge Track 1: Assessing Algorithms to Improve Video Object Detection and Classification from Unconstrained Mobility Platforms","date":"2019-07-26","arxiv_id":"1907.11529","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-detection-in-video-with-spatial","title":"Object Detection in Video with Spatial-temporal Context Aggregation","date":"2019-07-11","arxiv_id":"1907.04988","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-systematic-framework-for-natural-1","title":"A Systematic Framework for Natural Perturbations from Videos","date":"2019-05-28","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"patchwork-a-patch-wise-attention-network-for","title":"Patchwork: A Patch-wise Attention Network for Efficient Object Detection and Segmentation in Video Streams","date":"2019-04-03","arxiv_id":"1904.01784","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-sparse-local-attention-for-video","title":"Progressive Sparse Local Attention for Video object detection","date":"2019-03-21","arxiv_id":"1903.09126","repositories_listed":0,"syntology":null},{"url":null,"slug":"scnn-a-general-distribution-based-statistical","title":"SCNN: A General Distribution based Statistical Convolutional Neural Network with Application to Video Object Detection","date":"2019-03-15","arxiv_id":"1903.07663","repositories_listed":0,"syntology":null},{"url":null,"slug":"adascale-towards-real-time-video-object","title":"AdaScale: Towards Real-time Video Object Detection Using Adaptive Scaling","date":"2019-02-08","arxiv_id":"1902.02910","repositories_listed":0,"syntology":null},{"url":"/paper/integrated-object-detection-and-tracking-with","slug":"integrated-object-detection-and-tracking-with","title":"Integrated Object Detection and Tracking with Tracklet-Conditioned Detection","date":"2018-11-27","arxiv_id":"1811.11167","repositories_listed":0,"syntology":null},{"url":null,"slug":"detect-or-track-towards-cost-effective-video","title":"Detect or Track: Towards Cost-Effective Video Object Detection/Tracking","date":"2018-11-13","arxiv_id":"1811.05340","repositories_listed":0,"syntology":null},{"url":null,"slug":"pack-and-detect-fast-object-detection-in","title":"Pack and Detect: Fast Object Detection in Videos Using Region-of-Interest Packing","date":"2018-09-05","arxiv_id":"1809.01701","repositories_listed":0,"syntology":null},{"url":null,"slug":"fully-motion-aware-network-for-video-object","title":"Fully Motion-Aware Network for Video Object Detection","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"object-detection-in-video-with-spatiotemporal","title":"Object Detection in Video with Spatiotemporal Sampling Networks","date":"2018-03-15","arxiv_id":"1803.05549","repositories_listed":0,"syntology":null},{"url":null,"slug":"recurrent-residual-module-for-fast-inference","title":"Recurrent Residual Module for Fast Inference in Videos","date":"2018-02-27","arxiv_id":"1802.09723","repositories_listed":0,"syntology":null},{"url":null,"slug":"impression-network-for-video-object-detection","title":"Impression Network for Video Object Detection","date":"2017-12-16","arxiv_id":"1712.05896","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-high-performance-video-object-1","title":"Towards High Performance Video Object Detection","date":"2017-11-30","arxiv_id":"1711.11577","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-video-object-detection-using","title":"Online Video Object Detection Using Association LSTM","date":"2017-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-united-video-dehazing-and","title":"End-to-End United Video Dehazing and Detection","date":"2017-09-12","arxiv_id":"1709.03919","repositories_listed":0,"syntology":null},{"url":"/paper/temporal-dynamic-graph-lstm-for-action-driven","slug":"temporal-dynamic-graph-lstm-for-action-driven","title":"Temporal Dynamic Graph LSTM for Action-driven Video Object Detection","date":"2017-08-02","arxiv_id":"1708.00666","repositories_listed":0,"syntology":null},{"url":"/paper/youtube-boundingboxes-a-large-high-precision","slug":"youtube-boundingboxes-a-large-high-precision","title":"YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video","date":"2017-02-02","arxiv_id":"1702.00824","repositories_listed":0,"syntology":null}],"record_sha256":"c41b84a2fa6e61a005ec1bb9b2647454ec34d7ad3fd1831fcc8d4bc17e6181c9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}