{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3IQG2DGNTC3URRMZ6XVMQEH36M","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"68e11e413996650e3a8d48c578904467449afd9b8138dde9e38f7b6d9a1ee8c7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T08:32:28Z","title_canon_sha256":"ab848011e4d11470889e7c76411c45ee9d87cad6b25d2b5181778fb690fcd170"},"schema_version":"1.0","source":{"id":"2311.15619","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.15619","created_at":"2026-07-05T07:58:46Z"},{"alias_kind":"arxiv_version","alias_value":"2311.15619v3","created_at":"2026-07-05T07:58:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15619","created_at":"2026-07-05T07:58:46Z"},{"alias_kind":"pith_short_12","alias_value":"3IQG2DGNTC3U","created_at":"2026-07-05T07:58:46Z"},{"alias_kind":"pith_short_16","alias_value":"3IQG2DGNTC3URRMZ","created_at":"2026-07-05T07:58:46Z"},{"alias_kind":"pith_short_8","alias_value":"3IQG2DGN","created_at":"2026-07-05T07:58:46Z"}],"graph_snapshots":[{"event_id":"sha256:547fed729be975f4575f1b73a88fc8baf075125b1b837035a317cec0fd74079e","target":"graph","created_at":"2026-07-05T07:58:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.15619/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dapeng Chen, Ruijin Liu, Sai Zhou, Wei Peng, Wenyuan Xue, Yifei Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T08:32:28Z","title":"Align before Adapt: Leveraging Entity-to-Region Alignments for Generalizable Video Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15619","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:77a5eb8db76cfa646a18935eb10c3dce5f5aa176b124224edc639b17e0164d22","target":"record","created_at":"2026-07-05T07:58:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"68e11e413996650e3a8d48c578904467449afd9b8138dde9e38f7b6d9a1ee8c7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T08:32:28Z","title_canon_sha256":"ab848011e4d11470889e7c76411c45ee9d87cad6b25d2b5181778fb690fcd170"},"schema_version":"1.0","source":{"id":"2311.15619","kind":"arxiv","version":3}},"canonical_sha256":"da206d0ccd98b748c599f5eac810fbf334c375b8ce8bb2a6ed56393303e72830","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da206d0ccd98b748c599f5eac810fbf334c375b8ce8bb2a6ed56393303e72830","first_computed_at":"2026-07-05T07:58:46.110367Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:58:46.110367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"faCV4fqAT7XLsAtlbXhUmFzan16qw10E8EVkwEwzo8PaGTl0WEfyaymB+fZ/iCLhQ60mh2NK1uNlf1k8E9hSDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:58:46.110913Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.15619","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77a5eb8db76cfa646a18935eb10c3dce5f5aa176b124224edc639b17e0164d22","sha256:547fed729be975f4575f1b73a88fc8baf075125b1b837035a317cec0fd74079e"],"state_sha256":"9d2b68e2eb4b2ef105405974e2bddc9e899c973658cbdee5b88e0e442cae4fab"}