{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:4DLFVPHOVV7BGIC26753G3AIE7","short_pith_number":"pith:4DLFVPHO","canonical_record":{"source":{"id":"1704.06925","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-23T14:10:55Z","cross_cats_sorted":[],"title_canon_sha256":"00fb818ba2d71aed396ca88d6c3386eddc9e606ac73425b2a48545eaeb44552e","abstract_canon_sha256":"c77536661cf19314fbde419b26d392c603067453ef642b989e5b26a3b21d6c62"},"schema_version":"1.0"},"canonical_sha256":"e0d65abceead7e13205af7fbb36c0827e4deb8eadd787508841349520995358c","source":{"kind":"arxiv","id":"1704.06925","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.06925","created_at":"2026-05-18T00:08:48Z"},{"alias_kind":"arxiv_version","alias_value":"1704.06925v2","created_at":"2026-05-18T00:08:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06925","created_at":"2026-05-18T00:08:48Z"},{"alias_kind":"pith_short_12","alias_value":"4DLFVPHOVV7B","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"4DLFVPHOVV7BGIC2","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"4DLFVPHO","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:4DLFVPHOVV7BGIC26753G3AIE7","target":"record","payload":{"canonical_record":{"source":{"id":"1704.06925","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-23T14:10:55Z","cross_cats_sorted":[],"title_canon_sha256":"00fb818ba2d71aed396ca88d6c3386eddc9e606ac73425b2a48545eaeb44552e","abstract_canon_sha256":"c77536661cf19314fbde419b26d392c603067453ef642b989e5b26a3b21d6c62"},"schema_version":"1.0"},"canonical_sha256":"e0d65abceead7e13205af7fbb36c0827e4deb8eadd787508841349520995358c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:48.636407Z","signature_b64":"a10WyB/mgC+F+fpbvN/qAZO6Y3WZPl0WTYLawZqPWFuIEGGJ+UTqocKrg/B4sz5JeYPA+J6vmFM6MWin9uglAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0d65abceead7e13205af7fbb36c0827e4deb8eadd787508841349520995358c","last_reissued_at":"2026-05-18T00:08:48.635726Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:48.635726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.06925","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:08:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DZrt3oco0nkDOWlNhEwOn1Ln2yG2EzVVF4FY/MLpQ5GVh5AOXbrAVmV0oPIglR7GNZH0KLOkCwqffTbUkGP/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T07:37:57.903899Z"},"content_sha256":"bc46694547a3c089b5d58abc72e6a93baaf4dfb698d049171c2eaa246bccd3e3","schema_version":"1.0","event_id":"sha256:bc46694547a3c089b5d58abc72e6a93baaf4dfb698d049171c2eaa246bccd3e3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:4DLFVPHOVV7BGIC26753G3AIE7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Second-order Temporal Pooling for Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anoop Cherian, Stephen Gould","submitted_at":"2017-04-23T14:10:55Z","abstract_excerpt":"Deep learning models for video-based action recognition usually generate features for short clips (consisting of a few frames); such clip-level features are aggregated to video-level representations by computing statistics on these features. Typically zero-th (max) or the first-order (average) statistics are used. In this paper, we explore the benefits of using second-order statistics. Specifically, we propose a novel end-to-end learnable feature aggregation scheme, dubbed temporal correlation pooling that generates an action descriptor for a video sequence by capturing the similarities betwee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06925","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":""},"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":"2026-05-18T00:08:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OHR3t5frMfyjEIWjMHrQOKuBdSypbX6zS3c3UcIpjgjILlD8Iu+3epXoTnu8xB50wsMibBudXHiNO+ChhB6wAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T07:37:57.904539Z"},"content_sha256":"28a7794a5e42c2731b10c6b23b7e2feea5d1d834cb7bc547bf2b2aa190e82dbf","schema_version":"1.0","event_id":"sha256:28a7794a5e42c2731b10c6b23b7e2feea5d1d834cb7bc547bf2b2aa190e82dbf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4DLFVPHOVV7BGIC26753G3AIE7/bundle.json","state_url":"https://pith.science/pith/4DLFVPHOVV7BGIC26753G3AIE7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4DLFVPHOVV7BGIC26753G3AIE7/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":"2026-06-01T07:37:57Z","links":{"resolver":"https://pith.science/pith/4DLFVPHOVV7BGIC26753G3AIE7","bundle":"https://pith.science/pith/4DLFVPHOVV7BGIC26753G3AIE7/bundle.json","state":"https://pith.science/pith/4DLFVPHOVV7BGIC26753G3AIE7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4DLFVPHOVV7BGIC26753G3AIE7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:4DLFVPHOVV7BGIC26753G3AIE7","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":"c77536661cf19314fbde419b26d392c603067453ef642b989e5b26a3b21d6c62","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-23T14:10:55Z","title_canon_sha256":"00fb818ba2d71aed396ca88d6c3386eddc9e606ac73425b2a48545eaeb44552e"},"schema_version":"1.0","source":{"id":"1704.06925","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.06925","created_at":"2026-05-18T00:08:48Z"},{"alias_kind":"arxiv_version","alias_value":"1704.06925v2","created_at":"2026-05-18T00:08:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06925","created_at":"2026-05-18T00:08:48Z"},{"alias_kind":"pith_short_12","alias_value":"4DLFVPHOVV7B","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"4DLFVPHOVV7BGIC2","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"4DLFVPHO","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:28a7794a5e42c2731b10c6b23b7e2feea5d1d834cb7bc547bf2b2aa190e82dbf","target":"graph","created_at":"2026-05-18T00:08:48Z","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":"Deep learning models for video-based action recognition usually generate features for short clips (consisting of a few frames); such clip-level features are aggregated to video-level representations by computing statistics on these features. Typically zero-th (max) or the first-order (average) statistics are used. In this paper, we explore the benefits of using second-order statistics. Specifically, we propose a novel end-to-end learnable feature aggregation scheme, dubbed temporal correlation pooling that generates an action descriptor for a video sequence by capturing the similarities betwee","authors_text":"Anoop Cherian, Stephen Gould","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-23T14:10:55Z","title":"Second-order Temporal Pooling for Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06925","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:bc46694547a3c089b5d58abc72e6a93baaf4dfb698d049171c2eaa246bccd3e3","target":"record","created_at":"2026-05-18T00:08:48Z","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":"c77536661cf19314fbde419b26d392c603067453ef642b989e5b26a3b21d6c62","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-23T14:10:55Z","title_canon_sha256":"00fb818ba2d71aed396ca88d6c3386eddc9e606ac73425b2a48545eaeb44552e"},"schema_version":"1.0","source":{"id":"1704.06925","kind":"arxiv","version":2}},"canonical_sha256":"e0d65abceead7e13205af7fbb36c0827e4deb8eadd787508841349520995358c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0d65abceead7e13205af7fbb36c0827e4deb8eadd787508841349520995358c","first_computed_at":"2026-05-18T00:08:48.635726Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:08:48.635726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a10WyB/mgC+F+fpbvN/qAZO6Y3WZPl0WTYLawZqPWFuIEGGJ+UTqocKrg/B4sz5JeYPA+J6vmFM6MWin9uglAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:08:48.636407Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.06925","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc46694547a3c089b5d58abc72e6a93baaf4dfb698d049171c2eaa246bccd3e3","sha256:28a7794a5e42c2731b10c6b23b7e2feea5d1d834cb7bc547bf2b2aa190e82dbf"],"state_sha256":"ff19eac17da347e2a2a95afeb1d6e06586dce5fcbcdecbfd6a133d1e338a5e8d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x0KMqs4C3BBdCXwWIXm+n+v5kxNVuwuSSc8bd+uU9xQ1oABrXkdZXA2+CfGOkGy+NmxQjhMG9DPZYqlQYmRDCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T07:37:57.907581Z","bundle_sha256":"5175522d829e087e4fd8a2be41a3ff389ae70d96e7a3c56c217ba3798b1f03c9"}}