{"url":"/task/video-similarity","name":"Video Similarity","slug":"video-similarity","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":"derived"},"counts":{"papers_tagged":24,"papers_with_code":14,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/video","name":"Video"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":14,"of":14,"tagged_in_all":24,"items":[{"url":"/paper/feature-compatible-progressive-learning-for","title":"Feature-compatible Progressive Learning for Video Copy Detection","date":"2023-04-20","arxiv_id":"2304.10305","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/visual-spatio-temporal-relation-enhanced","title":"BiC-Net: Learning Efficient Spatio-Temporal Relation for Text-Video Retrieval","date":"2021-10-29","arxiv_id":"2110.15609","repositories_listed":2,"syntology":null},{"url":"/paper/pose-selective-max-pooling-for-measuring","title":"Pose-Selective Max Pooling for Measuring Similarity","date":"2016-09-22","arxiv_id":"1609.07042","repositories_listed":2,"syntology":null},{"url":"/paper/the-2023-video-similarity-dataset-and","title":"The 2023 Video Similarity Dataset and Challenge","date":"2023-06-15","arxiv_id":"2306.09489","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":4}},{"url":"/paper/a-similarity-alignment-model-for-video-copy","title":"A Similarity Alignment Model for Video Copy Segment Matching","date":"2023-05-25","arxiv_id":"2305.15679","repositories_listed":1,"syntology":{"n":12,"n_ran":0,"n_unverified":12,"n_pointer_only":12}},{"url":"/paper/a-dual-level-detection-method-for-video-copy","title":"A Dual-level Detection Method for Video Copy Detection","date":"2023-05-21","arxiv_id":"2305.12361","repositories_listed":1,"syntology":null},{"url":"/paper/3rd-place-solution-to-meta-ai-video","title":"3rd Place Solution to Meta AI Video Similarity Challenge","date":"2023-04-24","arxiv_id":"2304.11964","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-video-similarity-learning","title":"Self-Supervised Video Similarity Learning","date":"2023-04-06","arxiv_id":"2304.03378","repositories_listed":1,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/contrastive-masked-autoencoders-for-self","title":"Contrastive Masked Autoencoders for Self-Supervised Video Hashing","date":"2022-11-21","arxiv_id":"2211.11210","repositories_listed":1,"syntology":null},{"url":"/paper/3d-csl-self-supervised-3d-context-similarity","title":"3D-CSL: self-supervised 3D context similarity learning for Near-Duplicate Video Retrieval","date":"2022-11-10","arxiv_id":"2211.05352","repositories_listed":1,"syntology":null},{"url":"/paper/c2kd-cross-lingual-cross-modal-knowledge","title":"C2KD: Cross-Lingual Cross-Modal Knowledge Distillation for Multilingual Text-Video Retrieval","date":"2022-10-07","arxiv_id":"2210.03625","repositories_listed":1,"syntology":null},{"url":"/paper/top1-solution-of-qq-browser-2021-ai-algorithm","title":"Top1 Solution of QQ Browser 2021 Ai Algorithm Competition Track 1 : Multimodal Video Similarity","date":"2021-10-30","arxiv_id":"2111.01677","repositories_listed":1,"syntology":null},{"url":"/paper/pdq-tmk-pdqf-a-test-drive-of-facebooks","title":"PDQ & TMK + PDQF -- A Test Drive of Facebook's Perceptual Hashing Algorithms","date":"2019-12-16","arxiv_id":"1912.07745","repositories_listed":1,"syntology":null},{"url":"/paper/visil-fine-grained-spatio-temporal-video","title":"ViSiL: Fine-grained Spatio-Temporal Video Similarity Learning","date":"2019-08-20","arxiv_id":"1908.07410","repositories_listed":1,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}}],"syntology_records":5,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}