{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3IQG2DGNTC3URRMZ6XVMQEH36M","short_pith_number":"pith:3IQG2DGN","schema_version":"1.0","canonical_sha256":"da206d0ccd98b748c599f5eac810fbf334c375b8ce8bb2a6ed56393303e72830","source":{"kind":"arxiv","id":"2311.15619","version":3},"attestation_state":"computed","paper":{"title":"Align before Adapt: Leveraging Entity-to-Region Alignments for Generalizable Video Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dapeng Chen, Ruijin Liu, Sai Zhou, Wei Peng, Wenyuan Xue, Yifei Chen","submitted_at":"2023-11-27T08:32:28Z","abstract_excerpt":"Large-scale visual-language pre-trained models have achieved significant success in various video tasks. However, most existing methods follow an \"adapt then align\" paradigm, which adapts pre-trained image encoders to model video-level representations and utilizes one-hot or text embedding of the action labels for supervision. This paradigm overlooks the challenge of mapping from static images to complicated activity concepts. In this paper, we propose a novel \"Align before Adapt\" (ALT) paradigm. Prior to adapting to video representation learning, we exploit the entity-to-region alignments for"},"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":"2311.15619","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T08:32:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ab848011e4d11470889e7c76411c45ee9d87cad6b25d2b5181778fb690fcd170","abstract_canon_sha256":"68e11e413996650e3a8d48c578904467449afd9b8138dde9e38f7b6d9a1ee8c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:46.110913Z","signature_b64":"faCV4fqAT7XLsAtlbXhUmFzan16qw10E8EVkwEwzo8PaGTl0WEfyaymB+fZ/iCLhQ60mh2NK1uNlf1k8E9hSDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da206d0ccd98b748c599f5eac810fbf334c375b8ce8bb2a6ed56393303e72830","last_reissued_at":"2026-07-05T07:58:46.110367Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:46.110367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Align before Adapt: Leveraging Entity-to-Region Alignments for Generalizable Video Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dapeng Chen, Ruijin Liu, Sai Zhou, Wei Peng, Wenyuan Xue, Yifei Chen","submitted_at":"2023-11-27T08:32:28Z","abstract_excerpt":"Large-scale visual-language pre-trained models have achieved significant success in various video tasks. However, most existing methods follow an \"adapt then align\" paradigm, which adapts pre-trained image encoders to model video-level representations and utilizes one-hot or text embedding of the action labels for supervision. This paradigm overlooks the challenge of mapping from static images to complicated activity concepts. In this paper, we propose a novel \"Align before Adapt\" (ALT) paradigm. Prior to adapting to video representation learning, we exploit the entity-to-region alignments for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15619","kind":"arxiv","version":3},"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/2311.15619/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":"2311.15619","created_at":"2026-07-05T07:58:46.110441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.15619v3","created_at":"2026-07-05T07:58:46.110441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15619","created_at":"2026-07-05T07:58:46.110441+00:00"},{"alias_kind":"pith_short_12","alias_value":"3IQG2DGNTC3U","created_at":"2026-07-05T07:58:46.110441+00:00"},{"alias_kind":"pith_short_16","alias_value":"3IQG2DGNTC3URRMZ","created_at":"2026-07-05T07:58:46.110441+00:00"},{"alias_kind":"pith_short_8","alias_value":"3IQG2DGN","created_at":"2026-07-05T07:58:46.110441+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/3IQG2DGNTC3URRMZ6XVMQEH36M","json":"https://pith.science/pith/3IQG2DGNTC3URRMZ6XVMQEH36M.json","graph_json":"https://pith.science/api/pith-number/3IQG2DGNTC3URRMZ6XVMQEH36M/graph.json","events_json":"https://pith.science/api/pith-number/3IQG2DGNTC3URRMZ6XVMQEH36M/events.json","paper":"https://pith.science/paper/3IQG2DGN"},"agent_actions":{"view_html":"https://pith.science/pith/3IQG2DGNTC3URRMZ6XVMQEH36M","download_json":"https://pith.science/pith/3IQG2DGNTC3URRMZ6XVMQEH36M.json","view_paper":"https://pith.science/paper/3IQG2DGN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.15619&json=true","fetch_graph":"https://pith.science/api/pith-number/3IQG2DGNTC3URRMZ6XVMQEH36M/graph.json","fetch_events":"https://pith.science/api/pith-number/3IQG2DGNTC3URRMZ6XVMQEH36M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3IQG2DGNTC3URRMZ6XVMQEH36M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3IQG2DGNTC3URRMZ6XVMQEH36M/action/storage_attestation","attest_author":"https://pith.science/pith/3IQG2DGNTC3URRMZ6XVMQEH36M/action/author_attestation","sign_citation":"https://pith.science/pith/3IQG2DGNTC3URRMZ6XVMQEH36M/action/citation_signature","submit_replication":"https://pith.science/pith/3IQG2DGNTC3URRMZ6XVMQEH36M/action/replication_record"}},"created_at":"2026-07-05T07:58:46.110441+00:00","updated_at":"2026-07-05T07:58:46.110441+00:00"}