{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BSCHRFQPSV4O4XQHZFVT3D25LU","short_pith_number":"pith:BSCHRFQP","schema_version":"1.0","canonical_sha256":"0c8478960f9578ee5e07c96b3d8f5d5d25f004120f3dbb414ae947773276b110","source":{"kind":"arxiv","id":"2105.05165","version":2},"attestation_state":"computed","paper":{"title":"AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aude Oliva, Chun-Fu Chen, Kate Saenko, Quanfu Fan, Rameswar Panda, Rogerio Feris, Ximeng Sun","submitted_at":"2021-05-11T16:19:07Z","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"},"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":"2105.05165","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-11T16:19:07Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"577091942f764c08a25f8354949351bfeda07e9ca9ce0af72a3ecb48a946e77a","abstract_canon_sha256":"fb7c2043a286fee23a23e206f94aa711f303e131ceb6af8b5052319dd5b61cb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:39:49.056787Z","signature_b64":"KIWypNmtwPt94VFqrtqKIVDhFRXygZeczYN04nJ0ReJXCiKp19d+n2YPQn5IsCuQtZnuaJRY/tgMFG3YnWJvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c8478960f9578ee5e07c96b3d8f5d5d25f004120f3dbb414ae947773276b110","last_reissued_at":"2026-07-05T02:39:49.056335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:39:49.056335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aude Oliva, Chun-Fu Chen, Kate Saenko, Quanfu Fan, Rameswar Panda, Rogerio Feris, Ximeng Sun","submitted_at":"2021-05-11T16:19:07Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.05165","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/2105.05165/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":"2105.05165","created_at":"2026-07-05T02:39:49.056397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.05165v2","created_at":"2026-07-05T02:39:49.056397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.05165","created_at":"2026-07-05T02:39:49.056397+00:00"},{"alias_kind":"pith_short_12","alias_value":"BSCHRFQPSV4O","created_at":"2026-07-05T02:39:49.056397+00:00"},{"alias_kind":"pith_short_16","alias_value":"BSCHRFQPSV4O4XQH","created_at":"2026-07-05T02:39:49.056397+00:00"},{"alias_kind":"pith_short_8","alias_value":"BSCHRFQP","created_at":"2026-07-05T02:39:49.056397+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/BSCHRFQPSV4O4XQHZFVT3D25LU","json":"https://pith.science/pith/BSCHRFQPSV4O4XQHZFVT3D25LU.json","graph_json":"https://pith.science/api/pith-number/BSCHRFQPSV4O4XQHZFVT3D25LU/graph.json","events_json":"https://pith.science/api/pith-number/BSCHRFQPSV4O4XQHZFVT3D25LU/events.json","paper":"https://pith.science/paper/BSCHRFQP"},"agent_actions":{"view_html":"https://pith.science/pith/BSCHRFQPSV4O4XQHZFVT3D25LU","download_json":"https://pith.science/pith/BSCHRFQPSV4O4XQHZFVT3D25LU.json","view_paper":"https://pith.science/paper/BSCHRFQP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.05165&json=true","fetch_graph":"https://pith.science/api/pith-number/BSCHRFQPSV4O4XQHZFVT3D25LU/graph.json","fetch_events":"https://pith.science/api/pith-number/BSCHRFQPSV4O4XQHZFVT3D25LU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BSCHRFQPSV4O4XQHZFVT3D25LU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BSCHRFQPSV4O4XQHZFVT3D25LU/action/storage_attestation","attest_author":"https://pith.science/pith/BSCHRFQPSV4O4XQHZFVT3D25LU/action/author_attestation","sign_citation":"https://pith.science/pith/BSCHRFQPSV4O4XQHZFVT3D25LU/action/citation_signature","submit_replication":"https://pith.science/pith/BSCHRFQPSV4O4XQHZFVT3D25LU/action/replication_record"}},"created_at":"2026-07-05T02:39:49.056397+00:00","updated_at":"2026-07-05T02:39:49.056397+00:00"}