{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BSCHRFQPSV4O4XQHZFVT3D25LU","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":"fb7c2043a286fee23a23e206f94aa711f303e131ceb6af8b5052319dd5b61cb7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-11T16:19:07Z","title_canon_sha256":"577091942f764c08a25f8354949351bfeda07e9ca9ce0af72a3ecb48a946e77a"},"schema_version":"1.0","source":{"id":"2105.05165","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.05165","created_at":"2026-07-05T02:39:49Z"},{"alias_kind":"arxiv_version","alias_value":"2105.05165v2","created_at":"2026-07-05T02:39:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.05165","created_at":"2026-07-05T02:39:49Z"},{"alias_kind":"pith_short_12","alias_value":"BSCHRFQPSV4O","created_at":"2026-07-05T02:39:49Z"},{"alias_kind":"pith_short_16","alias_value":"BSCHRFQPSV4O4XQH","created_at":"2026-07-05T02:39:49Z"},{"alias_kind":"pith_short_8","alias_value":"BSCHRFQP","created_at":"2026-07-05T02:39:49Z"}],"graph_snapshots":[{"event_id":"sha256:c5347d2025d3131ea201719a9f844d042bdee228b0029a71a52c2c89e9808893","target":"graph","created_at":"2026-07-05T02:39:49Z","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/2105.05165/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal learning, which focuses on utilizing various modalities to improve the performance of a model, is widely used in video recognition. While traditional multi-modal learning offers excellent recognition results, its computational expense limits its impact for many real-world applications. In this paper, we propose an adaptive multi-modal learning framework, called AdaMML, that selects on-the-fly the optimal modalities for each segment conditioned on the input for efficient video recognition. Specifically, given a video segment, a multi-modal policy network is used to decide what modal","authors_text":"Aude Oliva, Chun-Fu Chen, Kate Saenko, Quanfu Fan, Rameswar Panda, Rogerio Feris, Ximeng Sun","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-11T16:19:07Z","title":"AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.05165","kind":"arxiv","version":2},"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:f8f3817d6702ea8376261e71b0082266c71a8075dae748840491924f8c34cb06","target":"record","created_at":"2026-07-05T02:39:49Z","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":"fb7c2043a286fee23a23e206f94aa711f303e131ceb6af8b5052319dd5b61cb7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-11T16:19:07Z","title_canon_sha256":"577091942f764c08a25f8354949351bfeda07e9ca9ce0af72a3ecb48a946e77a"},"schema_version":"1.0","source":{"id":"2105.05165","kind":"arxiv","version":2}},"canonical_sha256":"0c8478960f9578ee5e07c96b3d8f5d5d25f004120f3dbb414ae947773276b110","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c8478960f9578ee5e07c96b3d8f5d5d25f004120f3dbb414ae947773276b110","first_computed_at":"2026-07-05T02:39:49.056335Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:39:49.056335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KIWypNmtwPt94VFqrtqKIVDhFRXygZeczYN04nJ0ReJXCiKp19d+n2YPQn5IsCuQtZnuaJRY/tgMFG3YnWJvBw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:39:49.056787Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.05165","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8f3817d6702ea8376261e71b0082266c71a8075dae748840491924f8c34cb06","sha256:c5347d2025d3131ea201719a9f844d042bdee228b0029a71a52c2c89e9808893"],"state_sha256":"10f7076990a28f79a2bfb2ff5beb09765a3cebc6a868c610fc343897df80ff5d"}