{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4VDAQ5IEMA4FMDZMXBIVMUMYNH","short_pith_number":"pith:4VDAQ5IE","schema_version":"1.0","canonical_sha256":"e5460875046038560f2cb85156519869e90353dbe0453a791ca85936475e192d","source":{"kind":"arxiv","id":"2503.00986","version":1},"attestation_state":"computed","paper":{"title":"Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoqi Pei, Fei Wu, Guo Chen, Jilan Xu, Lijin Yang, Limin Wang, Weidi Xie, Yali Wang, Yifei Huang, Yuping He, Yu Qiao","submitted_at":"2025-03-02T18:49:48Z","abstract_excerpt":"In egocentric video understanding, the motion of hands and objects as well as their interactions play a significant role by nature. However, existing egocentric video representation learning methods mainly focus on aligning video representation with high-level narrations, overlooking the intricate dynamics between hands and objects. In this work, we aim to integrate the modeling of fine-grained hand-object dynamics into the video representation learning process. Since no suitable data is available, we introduce HOD, a novel pipeline employing a hand-object detector and a large language model t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2503.00986","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-02T18:49:48Z","cross_cats_sorted":[],"title_canon_sha256":"a93d8e356dd3222038e4250bd629df2f1ba14608f238f26c1602441d96216459","abstract_canon_sha256":"9ae3d8ee273de0346e54b4f46224efb9e7618cd91beea06f552cbd6be08e7a10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:34.084955Z","signature_b64":"jxak65vDRm+mIBj7Ow7NdUKjnI2uosXessh5uPqLXtTM0BnAr062N2jDGCkE9kRnOz3LyYYYl0HDHh1EvsoYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5460875046038560f2cb85156519869e90353dbe0453a791ca85936475e192d","last_reissued_at":"2026-07-05T10:22:34.084465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:34.084465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoqi Pei, Fei Wu, Guo Chen, Jilan Xu, Lijin Yang, Limin Wang, Weidi Xie, Yali Wang, Yifei Huang, Yuping He, Yu Qiao","submitted_at":"2025-03-02T18:49:48Z","abstract_excerpt":"In egocentric video understanding, the motion of hands and objects as well as their interactions play a significant role by nature. However, existing egocentric video representation learning methods mainly focus on aligning video representation with high-level narrations, overlooking the intricate dynamics between hands and objects. In this work, we aim to integrate the modeling of fine-grained hand-object dynamics into the video representation learning process. Since no suitable data is available, we introduce HOD, a novel pipeline employing a hand-object detector and a large language model t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00986","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.00986/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2503.00986","created_at":"2026-07-05T10:22:34.084527+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.00986v1","created_at":"2026-07-05T10:22:34.084527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00986","created_at":"2026-07-05T10:22:34.084527+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VDAQ5IEMA4F","created_at":"2026-07-05T10:22:34.084527+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VDAQ5IEMA4FMDZM","created_at":"2026-07-05T10:22:34.084527+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VDAQ5IE","created_at":"2026-07-05T10:22:34.084527+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08514","citing_title":"Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02962","citing_title":"Hand Trajectory Fusion for Egocentric Natural Language Query Grounding","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2507.23682","citing_title":"villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4VDAQ5IEMA4FMDZMXBIVMUMYNH","json":"https://pith.science/pith/4VDAQ5IEMA4FMDZMXBIVMUMYNH.json","graph_json":"https://pith.science/api/pith-number/4VDAQ5IEMA4FMDZMXBIVMUMYNH/graph.json","events_json":"https://pith.science/api/pith-number/4VDAQ5IEMA4FMDZMXBIVMUMYNH/events.json","paper":"https://pith.science/paper/4VDAQ5IE"},"agent_actions":{"view_html":"https://pith.science/pith/4VDAQ5IEMA4FMDZMXBIVMUMYNH","download_json":"https://pith.science/pith/4VDAQ5IEMA4FMDZMXBIVMUMYNH.json","view_paper":"https://pith.science/paper/4VDAQ5IE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.00986&json=true","fetch_graph":"https://pith.science/api/pith-number/4VDAQ5IEMA4FMDZMXBIVMUMYNH/graph.json","fetch_events":"https://pith.science/api/pith-number/4VDAQ5IEMA4FMDZMXBIVMUMYNH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VDAQ5IEMA4FMDZMXBIVMUMYNH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VDAQ5IEMA4FMDZMXBIVMUMYNH/action/storage_attestation","attest_author":"https://pith.science/pith/4VDAQ5IEMA4FMDZMXBIVMUMYNH/action/author_attestation","sign_citation":"https://pith.science/pith/4VDAQ5IEMA4FMDZMXBIVMUMYNH/action/citation_signature","submit_replication":"https://pith.science/pith/4VDAQ5IEMA4FMDZMXBIVMUMYNH/action/replication_record"}},"created_at":"2026-07-05T10:22:34.084527+00:00","updated_at":"2026-07-05T10:22:34.084527+00:00"}