{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HB7DJXHC2BUIHMCX5OYLIWWNHU","short_pith_number":"pith:HB7DJXHC","schema_version":"1.0","canonical_sha256":"387e34dce2d06883b057ebb0b45acd3d3f8d20e0fb2b5e74545eb01ba2401a3a","source":{"kind":"arxiv","id":"1704.02895","version":1},"attestation_state":"computed","paper":{"title":"ActionVLAD: Learning spatio-temporal aggregation for action classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Gupta, Bryan Russell, Deva Ramanan, Josef Sivic, Rohit Girdhar","submitted_at":"2017-04-10T15:09:41Z","abstract_excerpt":"In this work, we introduce a new video representation for action classification that aggregates local convolutional features across the entire spatio-temporal extent of the video. We do so by integrating state-of-the-art two-stream networks with learnable spatio-temporal feature aggregation. The resulting architecture is end-to-end trainable for whole-video classification. We investigate different strategies for pooling across space and time and combining signals from the different streams. We find that: (i) it is important to pool jointly across space and time, but (ii) appearance and motion "},"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":"1704.02895","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-10T15:09:41Z","cross_cats_sorted":[],"title_canon_sha256":"d668d456070b9569940bdd5c74fdba91bafa74e597ce6a6b689d5dbb6c744748","abstract_canon_sha256":"6f7bc96b0e13689ff8b8d89bd0dc16fb7482af4e791edab61d701f164f3a565d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:43.743122Z","signature_b64":"Fda0jmc9qQMHuqbHGsKTTasNuijnFmpSI1cf5F3iH2n0KHjyg5CJrzfX3IzKhyjvJMyBU+qFt4snEWgdM3qbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"387e34dce2d06883b057ebb0b45acd3d3f8d20e0fb2b5e74545eb01ba2401a3a","last_reissued_at":"2026-05-18T00:46:43.742580Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:43.742580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ActionVLAD: Learning spatio-temporal aggregation for action classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Gupta, Bryan Russell, Deva Ramanan, Josef Sivic, Rohit Girdhar","submitted_at":"2017-04-10T15:09:41Z","abstract_excerpt":"In this work, we introduce a new video representation for action classification that aggregates local convolutional features across the entire spatio-temporal extent of the video. We do so by integrating state-of-the-art two-stream networks with learnable spatio-temporal feature aggregation. The resulting architecture is end-to-end trainable for whole-video classification. We investigate different strategies for pooling across space and time and combining signals from the different streams. We find that: (i) it is important to pool jointly across space and time, but (ii) appearance and motion "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.02895","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1704.02895","created_at":"2026-05-18T00:46:43.742664+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.02895v1","created_at":"2026-05-18T00:46:43.742664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.02895","created_at":"2026-05-18T00:46:43.742664+00:00"},{"alias_kind":"pith_short_12","alias_value":"HB7DJXHC2BUI","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"HB7DJXHC2BUIHMCX","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"HB7DJXHC","created_at":"2026-05-18T12:31:18.294218+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/HB7DJXHC2BUIHMCX5OYLIWWNHU","json":"https://pith.science/pith/HB7DJXHC2BUIHMCX5OYLIWWNHU.json","graph_json":"https://pith.science/api/pith-number/HB7DJXHC2BUIHMCX5OYLIWWNHU/graph.json","events_json":"https://pith.science/api/pith-number/HB7DJXHC2BUIHMCX5OYLIWWNHU/events.json","paper":"https://pith.science/paper/HB7DJXHC"},"agent_actions":{"view_html":"https://pith.science/pith/HB7DJXHC2BUIHMCX5OYLIWWNHU","download_json":"https://pith.science/pith/HB7DJXHC2BUIHMCX5OYLIWWNHU.json","view_paper":"https://pith.science/paper/HB7DJXHC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.02895&json=true","fetch_graph":"https://pith.science/api/pith-number/HB7DJXHC2BUIHMCX5OYLIWWNHU/graph.json","fetch_events":"https://pith.science/api/pith-number/HB7DJXHC2BUIHMCX5OYLIWWNHU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HB7DJXHC2BUIHMCX5OYLIWWNHU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HB7DJXHC2BUIHMCX5OYLIWWNHU/action/storage_attestation","attest_author":"https://pith.science/pith/HB7DJXHC2BUIHMCX5OYLIWWNHU/action/author_attestation","sign_citation":"https://pith.science/pith/HB7DJXHC2BUIHMCX5OYLIWWNHU/action/citation_signature","submit_replication":"https://pith.science/pith/HB7DJXHC2BUIHMCX5OYLIWWNHU/action/replication_record"}},"created_at":"2026-05-18T00:46:43.742664+00:00","updated_at":"2026-05-18T00:46:43.742664+00:00"}