{"url":"/task/multi-instance-retrieval","name":"Multi-Instance Retrieval","slug":"multi-instance-retrieval","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":19,"papers_with_code":15,"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":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/epic-kitchens-100","name":"EPIC-KITCHENS-100","full_name":"","num_papers_in_archive":162}],"subtasks":[],"parent_tasks":[],"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":15,"of":15,"tagged_in_all":19,"items":[{"url":"/paper/learning-video-representations-from-large","title":"Learning Video Representations from Large Language Models","date":"2022-12-08","arxiv_id":"2212.04501","repositories_listed":3,"syntology":{"n":20,"n_ran":6,"n_unverified":14,"n_pointer_only":20}},{"url":"/paper/egocentric-video-language-pretraining","title":"Egocentric Video-Language Pretraining","date":"2022-06-03","arxiv_id":"2206.01670","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/learning-video-retrieval-models-with","title":"Learning video retrieval models with relevance-aware online mining","date":"2022-03-16","arxiv_id":"2203.08688","repositories_listed":2,"syntology":null},{"url":"/paper/eva02-at-egocentric-video-language","title":"EVA02-AT: Egocentric Video-Language Understanding with Spatial-Temporal Rotary Positional Embeddings and Symmetric Optimization","date":"2025-06-17","arxiv_id":"2506.14356","repositories_listed":1,"syntology":null},{"url":"/paper/contextrefine-clip-for-epic-kitchens-100","title":"ContextRefine-CLIP for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2025","date":"2025-06-12","arxiv_id":"2506.10550","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-fine-grained-hand-object-dynamics","title":"Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning","date":"2025-03-02","arxiv_id":"2503.00986","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/egovideo-exploring-egocentric-foundation","title":"EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation","date":"2024-06-26","arxiv_id":"2406.18070","repositories_listed":1,"syntology":{"n":15,"n_ran":11,"n_unverified":4,"n_pointer_only":15}},{"url":"/paper/symmetric-multi-similarity-loss-for-epic","title":"Symmetric Multi-Similarity Loss for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2024","date":"2024-06-18","arxiv_id":"2406.12256","repositories_listed":1,"syntology":null},{"url":"/paper/egonce-do-egocentric-video-language-models","title":"EgoNCE++: Do Egocentric Video-Language Models Really Understand Hand-Object Interactions?","date":"2024-05-28","arxiv_id":"2405.17719","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":5}},{"url":"/paper/training-a-large-video-model-on-a-single","title":"Training a Large Video Model on a Single Machine in a Day","date":"2023-09-28","arxiv_id":"2309.16669","repositories_listed":1,"syntology":null},{"url":"/paper/egovlpv2-egocentric-video-language-pre","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","date":"2023-07-11","arxiv_id":"2307.05463","repositories_listed":1,"syntology":null},{"url":"/paper/hiervl-learning-hierarchical-video-language","title":"HierVL: Learning Hierarchical Video-Language Embeddings","date":"2023-01-05","arxiv_id":"2301.02311","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}},{"url":"/paper/egocentric-video-language-pretraining-epic","title":"Egocentric Video-Language Pretraining @ EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022","date":"2022-07-04","arxiv_id":"2207.01334","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-semantic-role-contextualized-video","title":"Exploiting Semantic Role Contextualized Video Features for Multi-Instance Text-Video Retrieval EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022","date":"2022-06-29","arxiv_id":"2206.14381","repositories_listed":1,"syntology":null},{"url":"/paper/relevance-based-margin-for-contrastively","title":"Relevance-based Margin for Contrastively-trained Video Retrieval Models","date":"2022-04-27","arxiv_id":"2204.13001","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}}],"syntology_records":7,"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"}}