{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MRMXTXHTNDNOAS55OXDE66V3MG","short_pith_number":"pith:MRMXTXHT","schema_version":"1.0","canonical_sha256":"645979dcf368dae04bbd75c64f7abb61a32a1bf4173854d0846decde98a4f42c","source":{"kind":"arxiv","id":"2506.16701","version":1},"attestation_state":"computed","paper":{"title":"Language-driven Description Generation and Common Sense Reasoning for Video Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuhang Zou, Jaechul Kim, Narendra Ahuja, Suchen Wang, Xiaodan Hu","submitted_at":"2025-06-20T02:43:53Z","abstract_excerpt":"Recent video action recognition methods have shown excellent performance by adapting large-scale pre-trained language-image models to the video domain. However, language models contain rich common sense priors - the scene contexts that humans use to constitute an understanding of objects, human-object interactions, and activities - that have not been fully exploited. In this paper, we introduce a framework incorporating language-driven common sense priors to identify cluttered video action sequences from monocular views that are often heavily occluded. We propose: (1) A video context summary c"},"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":"2506.16701","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-20T02:43:53Z","cross_cats_sorted":[],"title_canon_sha256":"78ee5b76de1b588fc2e784d1bae9721c24bd634df0660255956adc96a725290f","abstract_canon_sha256":"444ac3cc1075efc2b45dd7cf878d038cfaaf2c4e9e86ec101feb91d014a960bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:41.277887Z","signature_b64":"zVO7AMxR6Xhkn5u8CcCPCPoSbF/We7ctTR8YExP5EKlTOqZr5fdc/4yqAntvuk2SDsgibDYR2Sb+T1NijiwMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"645979dcf368dae04bbd75c64f7abb61a32a1bf4173854d0846decde98a4f42c","last_reissued_at":"2026-07-05T11:24:41.277381Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:41.277381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language-driven Description Generation and Common Sense Reasoning for Video Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuhang Zou, Jaechul Kim, Narendra Ahuja, Suchen Wang, Xiaodan Hu","submitted_at":"2025-06-20T02:43:53Z","abstract_excerpt":"Recent video action recognition methods have shown excellent performance by adapting large-scale pre-trained language-image models to the video domain. However, language models contain rich common sense priors - the scene contexts that humans use to constitute an understanding of objects, human-object interactions, and activities - that have not been fully exploited. In this paper, we introduce a framework incorporating language-driven common sense priors to identify cluttered video action sequences from monocular views that are often heavily occluded. We propose: (1) A video context summary c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16701","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/2506.16701/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":"2506.16701","created_at":"2026-07-05T11:24:41.277440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.16701v1","created_at":"2026-07-05T11:24:41.277440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16701","created_at":"2026-07-05T11:24:41.277440+00:00"},{"alias_kind":"pith_short_12","alias_value":"MRMXTXHTNDNO","created_at":"2026-07-05T11:24:41.277440+00:00"},{"alias_kind":"pith_short_16","alias_value":"MRMXTXHTNDNOAS55","created_at":"2026-07-05T11:24:41.277440+00:00"},{"alias_kind":"pith_short_8","alias_value":"MRMXTXHT","created_at":"2026-07-05T11:24:41.277440+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MRMXTXHTNDNOAS55OXDE66V3MG","json":"https://pith.science/pith/MRMXTXHTNDNOAS55OXDE66V3MG.json","graph_json":"https://pith.science/api/pith-number/MRMXTXHTNDNOAS55OXDE66V3MG/graph.json","events_json":"https://pith.science/api/pith-number/MRMXTXHTNDNOAS55OXDE66V3MG/events.json","paper":"https://pith.science/paper/MRMXTXHT"},"agent_actions":{"view_html":"https://pith.science/pith/MRMXTXHTNDNOAS55OXDE66V3MG","download_json":"https://pith.science/pith/MRMXTXHTNDNOAS55OXDE66V3MG.json","view_paper":"https://pith.science/paper/MRMXTXHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.16701&json=true","fetch_graph":"https://pith.science/api/pith-number/MRMXTXHTNDNOAS55OXDE66V3MG/graph.json","fetch_events":"https://pith.science/api/pith-number/MRMXTXHTNDNOAS55OXDE66V3MG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MRMXTXHTNDNOAS55OXDE66V3MG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MRMXTXHTNDNOAS55OXDE66V3MG/action/storage_attestation","attest_author":"https://pith.science/pith/MRMXTXHTNDNOAS55OXDE66V3MG/action/author_attestation","sign_citation":"https://pith.science/pith/MRMXTXHTNDNOAS55OXDE66V3MG/action/citation_signature","submit_replication":"https://pith.science/pith/MRMXTXHTNDNOAS55OXDE66V3MG/action/replication_record"}},"created_at":"2026-07-05T11:24:41.277440+00:00","updated_at":"2026-07-05T11:24:41.277440+00:00"}