{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/objectnlq-ego4d-episodic-memory-challenge","title":"ObjectNLQ @ Ego4D Episodic Memory Challenge 2024","arxiv_id":"2406.15778","date":"2024-06-22","proceeding":null,"authors":["Yisen Feng","Haoyu Zhang","Yuquan Xie","Zaijing Li","Meng Liu","Liqiang Nie"],"abstract":"In this report, we present our approach for the Natural Language Query track and Goal Step track of the Ego4D Episodic Memory Benchmark at CVPR 2024. Both challenges require the localization of actions within long video sequences using textual queries. To enhance localization accuracy, our method not only processes the temporal information of videos but also identifies fine-grained objects spatially within the frames. To this end, we introduce a novel approach, termed ObjectNLQ, which incorporates an object branch to augment the video representation with detailed object information, thereby improving grounding efficiency. ObjectNLQ achieves a mean R@1 of 23.15, ranking 2nd in the Natural Language Queries Challenge, and gains 33.00 in terms of the metric R@1, IoU=0.3, ranking 3rd in the Goal Step Challenge. Our code will be released at https://github.com/Yisen-Feng/ObjectNLQ.","url_abs":"https://arxiv.org/abs/2406.15778v2","url_pdf":"https://arxiv.org/pdf/2406.15778v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"objectnlq-ego4d-episodic-memory-challenge","repo_url":"https://github.com/yisen-feng/objectnlq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"natural-language-queries","task_name":"Natural Language Queries"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.15778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.15778"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yisen-feng/objectnlq","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"ran_fixture":1,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"ea2ba2c075c6b18b","entry":"compute_temporal_iou","repo":"yisen-feng/objectnlq","repo_kind":"official","path":"temporal_nms.py","file_url":"https://github.com/yisen-feng/objectnlq/blob/HEAD/temporal_nms.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ea2ba2c075c6b18b"}},{"code_sha256_prefix":"a34c005ba2203f35","entry":"drop_path","repo":"yisen-feng/objectnlq","repo_kind":"official","path":"libs/modeling/blocks.py","file_url":"https://github.com/yisen-feng/objectnlq/blob/HEAD/libs/modeling/blocks.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a34c005ba2203f35"}},{"code_sha256_prefix":"3531df7b0c9b0791","entry":"get_sinusoid_encoding","repo":"yisen-feng/objectnlq","repo_kind":"official","path":"libs/modeling/blocks.py","file_url":"https://github.com/yisen-feng/objectnlq/blob/HEAD/libs/modeling/blocks.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3531df7b0c9b0791"}},{"code_sha256_prefix":"efe17d3458806d84","entry":"get_videos_in_directory","repo":"yisen-feng/objectnlq","repo_kind":"official","path":"basic_utils.py","file_url":"https://github.com/yisen-feng/objectnlq/blob/HEAD/basic_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"efe17d3458806d84"}},{"code_sha256_prefix":"37bec4b8d7a97c61","entry":"reformat_nlq_data","repo":"yisen-feng/objectnlq","repo_kind":"official","path":"ego4d_data/reformat_data.py","file_url":"https://github.com/yisen-feng/objectnlq/blob/HEAD/ego4d_data/reformat_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"37bec4b8d7a97c61"}},{"code_sha256_prefix":"3eb80dc0984b649c","entry":"temporal_nms","repo":"yisen-feng/objectnlq","repo_kind":"official","path":"temporal_nms.py","file_url":"https://github.com/yisen-feng/objectnlq/blob/HEAD/temporal_nms.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3eb80dc0984b649c"}},{"code_sha256_prefix":"a8740db7c0fffa49","entry":"top1_generator","repo":"yisen-feng/objectnlq","repo_kind":"official","path":"ensemble.py","file_url":"https://github.com/yisen-feng/objectnlq/blob/HEAD/ensemble.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a8740db7c0fffa49"}},{"code_sha256_prefix":"8ee4d7644d2d1423","entry":"load_config","repo":"yisen-feng/objectnlq","repo_kind":"official","path":"libs/core/config.py","file_url":"https://github.com/yisen-feng/objectnlq/blob/HEAD/libs/core/config.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8ee4d7644d2d1423"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}