{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:NQ2LIUIMKS7EX34REZJGKZNBFI","short_pith_number":"pith:NQ2LIUIM","canonical_record":{"source":{"id":"1701.05432","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-19T14:30:49Z","cross_cats_sorted":[],"title_canon_sha256":"b649cbac7fb54429f87da9ef88a7c5f5f1118bc721ea1e7361ad3d4e0ec88670","abstract_canon_sha256":"763771fb2fb6e4bb6f8bae6b0a1830e00e78097466b3b47cffd102e1c4efcb08"},"schema_version":"1.0"},"canonical_sha256":"6c34b4510c54be4bef9126526565a12a0046876f12f953d1bf504251f971b42b","source":{"kind":"arxiv","id":"1701.05432","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.05432","created_at":"2026-05-18T00:52:29Z"},{"alias_kind":"arxiv_version","alias_value":"1701.05432v1","created_at":"2026-05-18T00:52:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.05432","created_at":"2026-05-18T00:52:29Z"},{"alias_kind":"pith_short_12","alias_value":"NQ2LIUIMKS7E","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"NQ2LIUIMKS7EX34R","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"NQ2LIUIM","created_at":"2026-05-18T12:31:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:NQ2LIUIMKS7EX34REZJGKZNBFI","target":"record","payload":{"canonical_record":{"source":{"id":"1701.05432","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-19T14:30:49Z","cross_cats_sorted":[],"title_canon_sha256":"b649cbac7fb54429f87da9ef88a7c5f5f1118bc721ea1e7361ad3d4e0ec88670","abstract_canon_sha256":"763771fb2fb6e4bb6f8bae6b0a1830e00e78097466b3b47cffd102e1c4efcb08"},"schema_version":"1.0"},"canonical_sha256":"6c34b4510c54be4bef9126526565a12a0046876f12f953d1bf504251f971b42b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:29.940523Z","signature_b64":"MGG8z1EbJxJ3GqlrBLxzm9KFGSgIMV5uzyaEPX/FnzvDzEUbqQtSZayQ42zerlc4Uor4Xbffyx4AOYCDua3qDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c34b4510c54be4bef9126526565a12a0046876f12f953d1bf504251f971b42b","last_reissued_at":"2026-05-18T00:52:29.940027Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:29.940027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1701.05432","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":"2026-05-18T00:52:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tndRGT2VrMj6I3qnP+PfX5uc/enSrIlpHktKhQy0yRDV0gBr4dpiZkzpMeKZatLgbZDoOWAQb1wFd4iO2VWxAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T09:32:42.898126Z"},"content_sha256":"6b0e0c090836a655d74396227cfde8190d114939b6fa9925a27576ded7945098","schema_version":"1.0","event_id":"sha256:6b0e0c090836a655d74396227cfde8190d114939b6fa9925a27576ded7945098"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:NQ2LIUIMKS7EX34REZJGKZNBFI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Higher-order Pooling of CNN Features via Kernel Linearization for Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anoop Cherian, Piotr Koniusz, Stephen Gould","submitted_at":"2017-01-19T14:30:49Z","abstract_excerpt":"Most successful deep learning algorithms for action recognition extend models designed for image-based tasks such as object recognition to video. Such extensions are typically trained for actions on single video frames or very short clips, and then their predictions from sliding-windows over the video sequence are pooled for recognizing the action at the sequence level. Usually this pooling step uses the first-order statistics of frame-level action predictions. In this paper, we explore the advantages of using higher-order correlations; specifically, we introduce Higher-order Kernel (HOK) desc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.05432","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":"2026-05-18T00:52:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ml3TQbUPK/K/aHRid3HnOcDwQsjE0ABscFFNaHxWQIJK1EUFUJ5RyWsZkBlH2e0gyZfl7Wuw/8eFOEO3rzBDCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T09:32:42.898478Z"},"content_sha256":"2e0141a76e5db85bca811d081ad9b2ca31adb8dfd9aaa24f5d08349be504b28a","schema_version":"1.0","event_id":"sha256:2e0141a76e5db85bca811d081ad9b2ca31adb8dfd9aaa24f5d08349be504b28a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NQ2LIUIMKS7EX34REZJGKZNBFI/bundle.json","state_url":"https://pith.science/pith/NQ2LIUIMKS7EX34REZJGKZNBFI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NQ2LIUIMKS7EX34REZJGKZNBFI/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":"2026-06-01T09:32:42Z","links":{"resolver":"https://pith.science/pith/NQ2LIUIMKS7EX34REZJGKZNBFI","bundle":"https://pith.science/pith/NQ2LIUIMKS7EX34REZJGKZNBFI/bundle.json","state":"https://pith.science/pith/NQ2LIUIMKS7EX34REZJGKZNBFI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NQ2LIUIMKS7EX34REZJGKZNBFI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:NQ2LIUIMKS7EX34REZJGKZNBFI","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":"763771fb2fb6e4bb6f8bae6b0a1830e00e78097466b3b47cffd102e1c4efcb08","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-19T14:30:49Z","title_canon_sha256":"b649cbac7fb54429f87da9ef88a7c5f5f1118bc721ea1e7361ad3d4e0ec88670"},"schema_version":"1.0","source":{"id":"1701.05432","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.05432","created_at":"2026-05-18T00:52:29Z"},{"alias_kind":"arxiv_version","alias_value":"1701.05432v1","created_at":"2026-05-18T00:52:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.05432","created_at":"2026-05-18T00:52:29Z"},{"alias_kind":"pith_short_12","alias_value":"NQ2LIUIMKS7E","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"NQ2LIUIMKS7EX34R","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"NQ2LIUIM","created_at":"2026-05-18T12:31:34Z"}],"graph_snapshots":[{"event_id":"sha256:2e0141a76e5db85bca811d081ad9b2ca31adb8dfd9aaa24f5d08349be504b28a","target":"graph","created_at":"2026-05-18T00:52:29Z","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":"Most successful deep learning algorithms for action recognition extend models designed for image-based tasks such as object recognition to video. Such extensions are typically trained for actions on single video frames or very short clips, and then their predictions from sliding-windows over the video sequence are pooled for recognizing the action at the sequence level. Usually this pooling step uses the first-order statistics of frame-level action predictions. In this paper, we explore the advantages of using higher-order correlations; specifically, we introduce Higher-order Kernel (HOK) desc","authors_text":"Anoop Cherian, Piotr Koniusz, Stephen Gould","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-19T14:30:49Z","title":"Higher-order Pooling of CNN Features via Kernel Linearization for Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.05432","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":"sha256:6b0e0c090836a655d74396227cfde8190d114939b6fa9925a27576ded7945098","target":"record","created_at":"2026-05-18T00:52:29Z","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":"763771fb2fb6e4bb6f8bae6b0a1830e00e78097466b3b47cffd102e1c4efcb08","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-19T14:30:49Z","title_canon_sha256":"b649cbac7fb54429f87da9ef88a7c5f5f1118bc721ea1e7361ad3d4e0ec88670"},"schema_version":"1.0","source":{"id":"1701.05432","kind":"arxiv","version":1}},"canonical_sha256":"6c34b4510c54be4bef9126526565a12a0046876f12f953d1bf504251f971b42b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c34b4510c54be4bef9126526565a12a0046876f12f953d1bf504251f971b42b","first_computed_at":"2026-05-18T00:52:29.940027Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:52:29.940027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MGG8z1EbJxJ3GqlrBLxzm9KFGSgIMV5uzyaEPX/FnzvDzEUbqQtSZayQ42zerlc4Uor4Xbffyx4AOYCDua3qDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:52:29.940523Z","signed_message":"canonical_sha256_bytes"},"source_id":"1701.05432","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b0e0c090836a655d74396227cfde8190d114939b6fa9925a27576ded7945098","sha256:2e0141a76e5db85bca811d081ad9b2ca31adb8dfd9aaa24f5d08349be504b28a"],"state_sha256":"cfb47e056eb1bc8c4ec4024ff48906515e69e12acae377ca01dcf10fc2cca9ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XcGP8m5H3rXFaxfbrbs3hGNkVF77g1ywoEb5Dz05h1N9xtL6WzS1DA1oCssMVB3UpRen4Z98Qp1TvXAZruhzBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T09:32:42.900322Z","bundle_sha256":"d24ea2be6e39c738f3577852195a55295f9b73c6f2845363194591960014d76d"}}