{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:HB7DJXHC2BUIHMCX5OYLIWWNHU","short_pith_number":"pith:HB7DJXHC","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"},"canonical_sha256":"387e34dce2d06883b057ebb0b45acd3d3f8d20e0fb2b5e74545eb01ba2401a3a","source":{"kind":"arxiv","id":"1704.02895","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.02895","created_at":"2026-05-18T00:46:43Z"},{"alias_kind":"arxiv_version","alias_value":"1704.02895v1","created_at":"2026-05-18T00:46:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.02895","created_at":"2026-05-18T00:46:43Z"},{"alias_kind":"pith_short_12","alias_value":"HB7DJXHC2BUI","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"HB7DJXHC2BUIHMCX","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"HB7DJXHC","created_at":"2026-05-18T12:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:HB7DJXHC2BUIHMCX5OYLIWWNHU","target":"record","payload":{"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"},"canonical_sha256":"387e34dce2d06883b057ebb0b45acd3d3f8d20e0fb2b5e74545eb01ba2401a3a","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"},"source_kind":"arxiv","source_id":"1704.02895","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:46:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"COEVfw/JiMrBGPqpTo66dcRDwjBqCnmzcHrQ/zW1oaV9CJwIyeZTnGu+hYbUvBBkqFam24lvBmpuiAP0YRX1Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T10:07:50.874554Z"},"content_sha256":"bb1eb079553780408c1a4a0876d00a924e3de5a1cb3d2504a2d786972307b570","schema_version":"1.0","event_id":"sha256:bb1eb079553780408c1a4a0876d00a924e3de5a1cb3d2504a2d786972307b570"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:HB7DJXHC2BUIHMCX5OYLIWWNHU","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:46:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GZHgiyqTIUd4e/N91So79wr8aJTEJOXyEpylH0NPtl3dJ+HQEfZAj3QtARueNce0B+WNE3zWFB957JdJ0n9hDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T10:07:50.874907Z"},"content_sha256":"c369077d78824d96544eaf92b04fb1ae8c38c8c2225f836c4b55a683bbb0342f","schema_version":"1.0","event_id":"sha256:c369077d78824d96544eaf92b04fb1ae8c38c8c2225f836c4b55a683bbb0342f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HB7DJXHC2BUIHMCX5OYLIWWNHU/bundle.json","state_url":"https://pith.science/pith/HB7DJXHC2BUIHMCX5OYLIWWNHU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HB7DJXHC2BUIHMCX5OYLIWWNHU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T10:07:50Z","links":{"resolver":"https://pith.science/pith/HB7DJXHC2BUIHMCX5OYLIWWNHU","bundle":"https://pith.science/pith/HB7DJXHC2BUIHMCX5OYLIWWNHU/bundle.json","state":"https://pith.science/pith/HB7DJXHC2BUIHMCX5OYLIWWNHU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HB7DJXHC2BUIHMCX5OYLIWWNHU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:HB7DJXHC2BUIHMCX5OYLIWWNHU","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":"6f7bc96b0e13689ff8b8d89bd0dc16fb7482af4e791edab61d701f164f3a565d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-10T15:09:41Z","title_canon_sha256":"d668d456070b9569940bdd5c74fdba91bafa74e597ce6a6b689d5dbb6c744748"},"schema_version":"1.0","source":{"id":"1704.02895","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.02895","created_at":"2026-05-18T00:46:43Z"},{"alias_kind":"arxiv_version","alias_value":"1704.02895v1","created_at":"2026-05-18T00:46:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.02895","created_at":"2026-05-18T00:46:43Z"},{"alias_kind":"pith_short_12","alias_value":"HB7DJXHC2BUI","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"HB7DJXHC2BUIHMCX","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"HB7DJXHC","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:c369077d78824d96544eaf92b04fb1ae8c38c8c2225f836c4b55a683bbb0342f","target":"graph","created_at":"2026-05-18T00:46:43Z","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"},"paper":{"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 ","authors_text":"Abhinav Gupta, Bryan Russell, Deva Ramanan, Josef Sivic, Rohit Girdhar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-10T15:09:41Z","title":"ActionVLAD: Learning spatio-temporal aggregation for action classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.02895","kind":"arxiv","version":1},"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:bb1eb079553780408c1a4a0876d00a924e3de5a1cb3d2504a2d786972307b570","target":"record","created_at":"2026-05-18T00:46:43Z","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":"6f7bc96b0e13689ff8b8d89bd0dc16fb7482af4e791edab61d701f164f3a565d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-10T15:09:41Z","title_canon_sha256":"d668d456070b9569940bdd5c74fdba91bafa74e597ce6a6b689d5dbb6c744748"},"schema_version":"1.0","source":{"id":"1704.02895","kind":"arxiv","version":1}},"canonical_sha256":"387e34dce2d06883b057ebb0b45acd3d3f8d20e0fb2b5e74545eb01ba2401a3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"387e34dce2d06883b057ebb0b45acd3d3f8d20e0fb2b5e74545eb01ba2401a3a","first_computed_at":"2026-05-18T00:46:43.742580Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:46:43.742580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fda0jmc9qQMHuqbHGsKTTasNuijnFmpSI1cf5F3iH2n0KHjyg5CJrzfX3IzKhyjvJMyBU+qFt4snEWgdM3qbBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:46:43.743122Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.02895","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb1eb079553780408c1a4a0876d00a924e3de5a1cb3d2504a2d786972307b570","sha256:c369077d78824d96544eaf92b04fb1ae8c38c8c2225f836c4b55a683bbb0342f"],"state_sha256":"cc715d3784d9ae9a893663df192740010ea94dd3d13ade44c72a3c108e2df694"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nrhqeYt6K/4kr3HlbMvZrcq3ZnXuZ0NsDaAN6kleTS7hBW7r8apK5TnWOulCe+fXROLZdK26ShiVhhEU5mcxAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T10:07:50.876895Z","bundle_sha256":"78f0c95cae130962444c08ab86c064b4c372ac2134b5612c0c26ded92a34a8db"}}