{"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/object-shot-enhanced-grounding-network-for","title":"Object-Shot Enhanced Grounding Network for Egocentric Video","arxiv_id":"2505.04270","date":"2025-05-07","proceeding":"CVPR 2025 1","authors":["Yisen Feng","Haoyu Zhang","Meng Liu","Weili Guan","Liqiang Nie"],"abstract":"Egocentric video grounding is a crucial task for embodied intelligence applications, distinct from exocentric video moment localization. Existing methods primarily focus on the distributional differences between egocentric and exocentric videos but often neglect key characteristics of egocentric videos and the fine-grained information emphasized by question-type queries. To address these limitations, we propose OSGNet, an Object-Shot enhanced Grounding Network for egocentric video. Specifically, we extract object information from videos to enrich video representation, particularly for objects highlighted in the textual query but not directly captured in the video features. Additionally, we analyze the frequent shot movements inherent to egocentric videos, leveraging these features to extract the wearer's attention information, which enhances the model's ability to perform modality alignment. Experiments conducted on three datasets demonstrate that OSGNet achieves state-of-the-art performance, validating the effectiveness of our approach. Our code can be found at https://github.com/Yisen-Feng/OSGNet.","url_abs":"https://arxiv.org/abs/2505.04270v1","url_pdf":"https://arxiv.org/pdf/2505.04270v1.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":"object-shot-enhanced-grounding-network-for","repo_url":"https://github.com/yisen-feng/osgnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"video-grounding","task_name":"Video Grounding"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.04270","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.04270"}},"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/osgnet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Yisen-Feng/OSGNet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"ran_fixture":1,"ran_honours":1,"unverified":13},"by_repo_kind":{"official":{"samples":17,"ran":4,"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/OSGNet","repo_kind":"official","path":"ensemble.py","file_url":"https://github.com/Yisen-Feng/OSGNet/blob/HEAD/ensemble.py","link_basis":"harvester_set","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/OSGNet","repo_kind":"official","path":"libs/modeling/blocks.py","file_url":"https://github.com/Yisen-Feng/OSGNet/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/OSGNet","repo_kind":"official","path":"libs/modeling/blocks.py","file_url":"https://github.com/Yisen-Feng/OSGNet/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":"3eb80dc0984b649c","entry":"temporal_nms","repo":"Yisen-Feng/OSGNet","repo_kind":"official","path":"ensemble.py","file_url":"https://github.com/Yisen-Feng/OSGNet/blob/HEAD/ensemble.py","link_basis":"harvester_set","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":"89f1e77c4bd67262","entry":"ctr_diou_loss_1d","repo":"Yisen-Feng/OSGNet","repo_kind":"official","path":"libs/modeling/losses.py","file_url":"https://github.com/Yisen-Feng/OSGNet/blob/HEAD/libs/modeling/losses.py","link_basis":"harvester_set","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":"89f1e77c4bd67262"}},{"code_sha256_prefix":"60dec8ca40e3f03e","entry":"ctr_giou_loss_1d","repo":"Yisen-Feng/OSGNet","repo_kind":"official","path":"libs/modeling/losses.py","file_url":"https://github.com/Yisen-Feng/OSGNet/blob/HEAD/libs/modeling/losses.py","link_basis":"harvester_set","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":"60dec8ca40e3f03e"}},{"code_sha256_prefix":"da8d3429729c5832","entry":"iou","repo":"Yisen-Feng/OSGNet","repo_kind":"official","path":"basic_utils.py","file_url":"https://github.com/Yisen-Feng/OSGNet/blob/HEAD/basic_utils.py","link_basis":"harvester_set","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":"da8d3429729c5832"}},{"code_sha256_prefix":"8ee4d7644d2d1423","entry":"load_config","repo":"Yisen-Feng/OSGNet","repo_kind":"official","path":"libs/core/config.py","file_url":"https://github.com/Yisen-Feng/OSGNet/blob/HEAD/libs/core/config.py","link_basis":"harvester_set","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"}},{"code_sha256_prefix":"86e28fb79c074fa8","entry":"min_max","repo":"Yisen-Feng/OSGNet","repo_kind":"official","path":"basic_utils.py","file_url":"https://github.com/Yisen-Feng/OSGNet/blob/HEAD/basic_utils.py","link_basis":"harvester_set","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":"86e28fb79c074fa8"}},{"code_sha256_prefix":"1848461b3ee1415e","entry":"minmax_normalize","repo":"Yisen-Feng/OSGNet","repo_kind":"official","path":"libs/modeling/my_archs.py","file_url":"https://github.com/Yisen-Feng/OSGNet/blob/HEAD/libs/modeling/my_archs.py","link_basis":"harvester_set","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":"1848461b3ee1415e"}},{"code_sha256_prefix":"a45cc1bfbdab6de8","entry":"post_processing_mr_nms","repo":"Yisen-Feng/OSGNet","repo_kind":"official","path":"ensemble.py","file_url":"https://github.com/Yisen-Feng/OSGNet/blob/HEAD/ensemble.py","link_basis":"harvester_set","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":"a45cc1bfbdab6de8"}},{"code_sha256_prefix":"cee845f405ecf37e","entry":"register_backbone","repo":"Yisen-Feng/OSGNet","repo_kind":"official","path":"libs/modeling/models.py","file_url":"https://github.com/Yisen-Feng/OSGNet/blob/HEAD/libs/modeling/models.py","link_basis":"harvester_set","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":"cee845f405ecf37e"}},{"code_sha256_prefix":"3db1c5ab5f3f0198","entry":"register_generator","repo":"Yisen-Feng/OSGNet","repo_kind":"official","path":"libs/modeling/models.py","file_url":"https://github.com/Yisen-Feng/OSGNet/blob/HEAD/libs/modeling/models.py","link_basis":"harvester_set","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":"3db1c5ab5f3f0198"}},{"code_sha256_prefix":"e5ef13b176081594","entry":"register_neck","repo":"Yisen-Feng/OSGNet","repo_kind":"official","path":"libs/modeling/models.py","file_url":"https://github.com/Yisen-Feng/OSGNet/blob/HEAD/libs/modeling/models.py","link_basis":"harvester_set","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":"e5ef13b176081594"}},{"code_sha256_prefix":"c30b2d92d92e5923","entry":"reverse_tensor_based_on_mask","repo":"Yisen-Feng/OSGNet","repo_kind":"official","path":"libs/modeling/mamba_blocks.py","file_url":"https://github.com/Yisen-Feng/OSGNet/blob/HEAD/libs/modeling/mamba_blocks.py","link_basis":"harvester_set","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":"c30b2d92d92e5923"}},{"code_sha256_prefix":"cb7608e384b5c1d7","entry":"sigmoid_focal_loss","repo":"Yisen-Feng/OSGNet","repo_kind":"official","path":"libs/modeling/losses.py","file_url":"https://github.com/Yisen-Feng/OSGNet/blob/HEAD/libs/modeling/losses.py","link_basis":"harvester_set","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":"cb7608e384b5c1d7"}},{"code_sha256_prefix":"e539e65d347e2386","entry":"sigmoid_inverse","repo":"Yisen-Feng/OSGNet","repo_kind":"official","path":"libs/modeling/my_archs.py","file_url":"https://github.com/Yisen-Feng/OSGNet/blob/HEAD/libs/modeling/my_archs.py","link_basis":"harvester_set","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":"e539e65d347e2386"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}