{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HUD6CCV2V6NJI5FGF3WS3IWWBI","short_pith_number":"pith:HUD6CCV2","schema_version":"1.0","canonical_sha256":"3d07e10abaaf9a9474a62eed2da2d60a3c4e738c9aef1e0260a8f8912622a3e8","source":{"kind":"arxiv","id":"2507.12426","version":2},"attestation_state":"computed","paper":{"title":"DVFL-Net: A Lightweight Distilled Video Focal Modulation Network for Spatio-Temporal Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abbas Khan, Arslan Munir, Hayat Ullah, Muhammad Ali Shafique","submitted_at":"2025-07-16T17:15:06Z","abstract_excerpt":"The landscape of video recognition has evolved significantly, shifting from traditional Convolutional Neural Networks (CNNs) to Transformer-based architectures for improved accuracy. While 3D CNNs have been effective at capturing spatiotemporal dynamics, recent Transformer models leverage self-attention to model long-range spatial and temporal dependencies. Despite achieving state-of-the-art performance on major benchmarks, Transformers remain computationally expensive, particularly with dense video data. To address this, we propose a lightweight Video Focal Modulation Network, DVFL-Net, which"},"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":"2507.12426","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-16T17:15:06Z","cross_cats_sorted":[],"title_canon_sha256":"e282150a5959a87bbfbc2dfbdb59f921aac9972683426e99c84a7f41ef755723","abstract_canon_sha256":"72a814c95b255486fa3f570fec13080d4bdd7adc2a4b7976000b31a0eb68aa30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:14.897005Z","signature_b64":"TmSFilLdmt6Wm26jpxw6l1Ba+5MNUrLI3WL4m1U+usPUVDrKNl6RI0KGQPpY5uCLjrG2bDNBrcJnFRvH0+olDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d07e10abaaf9a9474a62eed2da2d60a3c4e738c9aef1e0260a8f8912622a3e8","last_reissued_at":"2026-07-05T11:39:14.896574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:14.896574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DVFL-Net: A Lightweight Distilled Video Focal Modulation Network for Spatio-Temporal Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abbas Khan, Arslan Munir, Hayat Ullah, Muhammad Ali Shafique","submitted_at":"2025-07-16T17:15:06Z","abstract_excerpt":"The landscape of video recognition has evolved significantly, shifting from traditional Convolutional Neural Networks (CNNs) to Transformer-based architectures for improved accuracy. While 3D CNNs have been effective at capturing spatiotemporal dynamics, recent Transformer models leverage self-attention to model long-range spatial and temporal dependencies. Despite achieving state-of-the-art performance on major benchmarks, Transformers remain computationally expensive, particularly with dense video data. To address this, we propose a lightweight Video Focal Modulation Network, DVFL-Net, which"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12426","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/2507.12426/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":"2507.12426","created_at":"2026-07-05T11:39:14.896634+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12426v2","created_at":"2026-07-05T11:39:14.896634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12426","created_at":"2026-07-05T11:39:14.896634+00:00"},{"alias_kind":"pith_short_12","alias_value":"HUD6CCV2V6NJ","created_at":"2026-07-05T11:39:14.896634+00:00"},{"alias_kind":"pith_short_16","alias_value":"HUD6CCV2V6NJI5FG","created_at":"2026-07-05T11:39:14.896634+00:00"},{"alias_kind":"pith_short_8","alias_value":"HUD6CCV2","created_at":"2026-07-05T11:39:14.896634+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/HUD6CCV2V6NJI5FGF3WS3IWWBI","json":"https://pith.science/pith/HUD6CCV2V6NJI5FGF3WS3IWWBI.json","graph_json":"https://pith.science/api/pith-number/HUD6CCV2V6NJI5FGF3WS3IWWBI/graph.json","events_json":"https://pith.science/api/pith-number/HUD6CCV2V6NJI5FGF3WS3IWWBI/events.json","paper":"https://pith.science/paper/HUD6CCV2"},"agent_actions":{"view_html":"https://pith.science/pith/HUD6CCV2V6NJI5FGF3WS3IWWBI","download_json":"https://pith.science/pith/HUD6CCV2V6NJI5FGF3WS3IWWBI.json","view_paper":"https://pith.science/paper/HUD6CCV2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12426&json=true","fetch_graph":"https://pith.science/api/pith-number/HUD6CCV2V6NJI5FGF3WS3IWWBI/graph.json","fetch_events":"https://pith.science/api/pith-number/HUD6CCV2V6NJI5FGF3WS3IWWBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HUD6CCV2V6NJI5FGF3WS3IWWBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HUD6CCV2V6NJI5FGF3WS3IWWBI/action/storage_attestation","attest_author":"https://pith.science/pith/HUD6CCV2V6NJI5FGF3WS3IWWBI/action/author_attestation","sign_citation":"https://pith.science/pith/HUD6CCV2V6NJI5FGF3WS3IWWBI/action/citation_signature","submit_replication":"https://pith.science/pith/HUD6CCV2V6NJI5FGF3WS3IWWBI/action/replication_record"}},"created_at":"2026-07-05T11:39:14.896634+00:00","updated_at":"2026-07-05T11:39:14.896634+00:00"}