{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K6JFBWGT3QQUFHEP2TYWO4REXF","short_pith_number":"pith:K6JFBWGT","schema_version":"1.0","canonical_sha256":"579250d8d3dc21429c8fd4f1677224b94aced77925af6c84022181776968a654","source":{"kind":"arxiv","id":"2502.11594","version":2},"attestation_state":"computed","paper":{"title":"iMOVE: Instance-Motion-Aware Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Zhang, Fan Yang, Feng Cheng, Haoran Xu, Huihui Xiao, Jiaze Li, Ruiwen Kang, Tingting Gao, Yaya Shi, Zongyang Ma","submitted_at":"2025-02-17T09:28:31Z","abstract_excerpt":"Enhancing the fine-grained instance spatiotemporal motion perception capabilities of Video Large Language Models is crucial for improving their temporal and general video understanding. However, current models struggle to perceive detailed and complex instance motions. To address these challenges, we have made improvements from both data and model perspectives. In terms of data, we have meticulously curated iMOVE-IT, the first large-scale instance-motion-aware video instruction-tuning dataset. This dataset is enriched with comprehensive instance motion annotations and spatiotemporal mutual-sup"},"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":"2502.11594","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-17T09:28:31Z","cross_cats_sorted":[],"title_canon_sha256":"5b5f34a1a73e9c3a3e1cd58b79f61b15507eaa0230b5be3ee8a27fa34a4ad358","abstract_canon_sha256":"fd98855d039bf8831f2be0b326c40b53ddd28a4ef01c7c37761cc7304a1a0274"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:50.105039Z","signature_b64":"TNHGZ2agGvgxNk37c8qPLuGh19sL+NVEDIP26bQVPqhTjNgNDiGI8uTW41fh40avObCCEpAFX2EgWaSaGbySDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"579250d8d3dc21429c8fd4f1677224b94aced77925af6c84022181776968a654","last_reissued_at":"2026-07-05T10:15:50.104435Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:50.104435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"iMOVE: Instance-Motion-Aware Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Zhang, Fan Yang, Feng Cheng, Haoran Xu, Huihui Xiao, Jiaze Li, Ruiwen Kang, Tingting Gao, Yaya Shi, Zongyang Ma","submitted_at":"2025-02-17T09:28:31Z","abstract_excerpt":"Enhancing the fine-grained instance spatiotemporal motion perception capabilities of Video Large Language Models is crucial for improving their temporal and general video understanding. However, current models struggle to perceive detailed and complex instance motions. To address these challenges, we have made improvements from both data and model perspectives. In terms of data, we have meticulously curated iMOVE-IT, the first large-scale instance-motion-aware video instruction-tuning dataset. This dataset is enriched with comprehensive instance motion annotations and spatiotemporal mutual-sup"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11594","kind":"arxiv","version":2},"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/2502.11594/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":"2502.11594","created_at":"2026-07-05T10:15:50.104575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11594v2","created_at":"2026-07-05T10:15:50.104575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11594","created_at":"2026-07-05T10:15:50.104575+00:00"},{"alias_kind":"pith_short_12","alias_value":"K6JFBWGT3QQU","created_at":"2026-07-05T10:15:50.104575+00:00"},{"alias_kind":"pith_short_16","alias_value":"K6JFBWGT3QQUFHEP","created_at":"2026-07-05T10:15:50.104575+00:00"},{"alias_kind":"pith_short_8","alias_value":"K6JFBWGT","created_at":"2026-07-05T10:15:50.104575+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.13377","citing_title":"Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13310","citing_title":"Visual Para-Thinker: Divide-and-Conquer Reasoning for Visual Comprehension","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K6JFBWGT3QQUFHEP2TYWO4REXF","json":"https://pith.science/pith/K6JFBWGT3QQUFHEP2TYWO4REXF.json","graph_json":"https://pith.science/api/pith-number/K6JFBWGT3QQUFHEP2TYWO4REXF/graph.json","events_json":"https://pith.science/api/pith-number/K6JFBWGT3QQUFHEP2TYWO4REXF/events.json","paper":"https://pith.science/paper/K6JFBWGT"},"agent_actions":{"view_html":"https://pith.science/pith/K6JFBWGT3QQUFHEP2TYWO4REXF","download_json":"https://pith.science/pith/K6JFBWGT3QQUFHEP2TYWO4REXF.json","view_paper":"https://pith.science/paper/K6JFBWGT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11594&json=true","fetch_graph":"https://pith.science/api/pith-number/K6JFBWGT3QQUFHEP2TYWO4REXF/graph.json","fetch_events":"https://pith.science/api/pith-number/K6JFBWGT3QQUFHEP2TYWO4REXF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K6JFBWGT3QQUFHEP2TYWO4REXF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K6JFBWGT3QQUFHEP2TYWO4REXF/action/storage_attestation","attest_author":"https://pith.science/pith/K6JFBWGT3QQUFHEP2TYWO4REXF/action/author_attestation","sign_citation":"https://pith.science/pith/K6JFBWGT3QQUFHEP2TYWO4REXF/action/citation_signature","submit_replication":"https://pith.science/pith/K6JFBWGT3QQUFHEP2TYWO4REXF/action/replication_record"}},"created_at":"2026-07-05T10:15:50.104575+00:00","updated_at":"2026-07-05T10:15:50.104575+00:00"}