{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:QT2SDEY3SK7I3XBXOLP3DB3FYB","short_pith_number":"pith:QT2SDEY3","canonical_record":{"source":{"id":"1609.03056","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-09-10T14:24:38Z","cross_cats_sorted":[],"title_canon_sha256":"4f937eb30a8a51887e833188e173e1283a8ad9156359f5475db29b29aa8b2af8","abstract_canon_sha256":"02f6952b7c68c923a3e18a163fae37956527ae831e5d26f56a818003430c4663"},"schema_version":"1.0"},"canonical_sha256":"84f521931b92be8ddc3772dfb18765c0540e212017283c7e407a36f1fad6da29","source":{"kind":"arxiv","id":"1609.03056","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.03056","created_at":"2026-05-18T00:51:01Z"},{"alias_kind":"arxiv_version","alias_value":"1609.03056v2","created_at":"2026-05-18T00:51:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.03056","created_at":"2026-05-18T00:51:01Z"},{"alias_kind":"pith_short_12","alias_value":"QT2SDEY3SK7I","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"QT2SDEY3SK7I3XBX","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"QT2SDEY3","created_at":"2026-05-18T12:30:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:QT2SDEY3SK7I3XBXOLP3DB3FYB","target":"record","payload":{"canonical_record":{"source":{"id":"1609.03056","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-09-10T14:24:38Z","cross_cats_sorted":[],"title_canon_sha256":"4f937eb30a8a51887e833188e173e1283a8ad9156359f5475db29b29aa8b2af8","abstract_canon_sha256":"02f6952b7c68c923a3e18a163fae37956527ae831e5d26f56a818003430c4663"},"schema_version":"1.0"},"canonical_sha256":"84f521931b92be8ddc3772dfb18765c0540e212017283c7e407a36f1fad6da29","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:01.153578Z","signature_b64":"L0v5MtPvkVebvt587PPljduwtExNvOUcGQQYfK8BZupsfc6OozqPvukHXKswvN642HSJ3gHTtmc2mnbY5ADUBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84f521931b92be8ddc3772dfb18765c0540e212017283c7e407a36f1fad6da29","last_reissued_at":"2026-05-18T00:51:01.153191Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:01.153191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.03056","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":"2026-05-18T00:51:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BmRTrUNyB2qyDRJvved+bX2Ff5lKXhNQEpajJnoEC/C/2s74br/NCK+OmCtA/9YWpkONSn0TiZuzVzEw7qerCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T20:41:18.676581Z"},"content_sha256":"a79bc78391f806c7771ace530c06daa7d69d06e22638fafeaae4488edc7ffcbd","schema_version":"1.0","event_id":"sha256:a79bc78391f806c7771ace530c06daa7d69d06e22638fafeaae4488edc7ffcbd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:QT2SDEY3SK7I3XBXOLP3DB3FYB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sequential Deep Trajectory Descriptor for Action Recognition with Three-stream CNN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Tiejun Huang, Yaowei Wang, Yemin Shi, Yonghong Tian","submitted_at":"2016-09-10T14:24:38Z","abstract_excerpt":"Learning the spatial-temporal representation of motion information is crucial to human action recognition. Nevertheless, most of the existing features or descriptors cannot capture motion information effectively, especially for long-term motion. To address this problem, this paper proposes a long-term motion descriptor called sequential Deep Trajectory Descriptor (sDTD). Specifically, we project dense trajectories into two-dimensional planes, and subsequently a CNN-RNN network is employed to learn an effective representation for long-term motion. Unlike the popular two-stream ConvNets, the sDT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.03056","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":"2026-05-18T00:51:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Aixfm8pwu+XPWzMo+5kU0XUneXbFNH7CtJdUxVDGE1NrOotp5DkCBh0og0idyjIGV6KstrSeZOpEYm5VCkKDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T20:41:18.676921Z"},"content_sha256":"be5caf732adc4b6175d603cd03f28f07549242f9b9990326498aa3df7b0b8bae","schema_version":"1.0","event_id":"sha256:be5caf732adc4b6175d603cd03f28f07549242f9b9990326498aa3df7b0b8bae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QT2SDEY3SK7I3XBXOLP3DB3FYB/bundle.json","state_url":"https://pith.science/pith/QT2SDEY3SK7I3XBXOLP3DB3FYB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QT2SDEY3SK7I3XBXOLP3DB3FYB/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":"2026-06-03T20:41:18Z","links":{"resolver":"https://pith.science/pith/QT2SDEY3SK7I3XBXOLP3DB3FYB","bundle":"https://pith.science/pith/QT2SDEY3SK7I3XBXOLP3DB3FYB/bundle.json","state":"https://pith.science/pith/QT2SDEY3SK7I3XBXOLP3DB3FYB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QT2SDEY3SK7I3XBXOLP3DB3FYB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:QT2SDEY3SK7I3XBXOLP3DB3FYB","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":"02f6952b7c68c923a3e18a163fae37956527ae831e5d26f56a818003430c4663","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-09-10T14:24:38Z","title_canon_sha256":"4f937eb30a8a51887e833188e173e1283a8ad9156359f5475db29b29aa8b2af8"},"schema_version":"1.0","source":{"id":"1609.03056","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.03056","created_at":"2026-05-18T00:51:01Z"},{"alias_kind":"arxiv_version","alias_value":"1609.03056v2","created_at":"2026-05-18T00:51:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.03056","created_at":"2026-05-18T00:51:01Z"},{"alias_kind":"pith_short_12","alias_value":"QT2SDEY3SK7I","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"QT2SDEY3SK7I3XBX","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"QT2SDEY3","created_at":"2026-05-18T12:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:be5caf732adc4b6175d603cd03f28f07549242f9b9990326498aa3df7b0b8bae","target":"graph","created_at":"2026-05-18T00:51:01Z","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":"Learning the spatial-temporal representation of motion information is crucial to human action recognition. Nevertheless, most of the existing features or descriptors cannot capture motion information effectively, especially for long-term motion. To address this problem, this paper proposes a long-term motion descriptor called sequential Deep Trajectory Descriptor (sDTD). Specifically, we project dense trajectories into two-dimensional planes, and subsequently a CNN-RNN network is employed to learn an effective representation for long-term motion. Unlike the popular two-stream ConvNets, the sDT","authors_text":"Tiejun Huang, Yaowei Wang, Yemin Shi, Yonghong Tian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-09-10T14:24:38Z","title":"Sequential Deep Trajectory Descriptor for Action Recognition with Three-stream CNN"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.03056","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:a79bc78391f806c7771ace530c06daa7d69d06e22638fafeaae4488edc7ffcbd","target":"record","created_at":"2026-05-18T00:51:01Z","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":"02f6952b7c68c923a3e18a163fae37956527ae831e5d26f56a818003430c4663","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-09-10T14:24:38Z","title_canon_sha256":"4f937eb30a8a51887e833188e173e1283a8ad9156359f5475db29b29aa8b2af8"},"schema_version":"1.0","source":{"id":"1609.03056","kind":"arxiv","version":2}},"canonical_sha256":"84f521931b92be8ddc3772dfb18765c0540e212017283c7e407a36f1fad6da29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84f521931b92be8ddc3772dfb18765c0540e212017283c7e407a36f1fad6da29","first_computed_at":"2026-05-18T00:51:01.153191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:51:01.153191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L0v5MtPvkVebvt587PPljduwtExNvOUcGQQYfK8BZupsfc6OozqPvukHXKswvN642HSJ3gHTtmc2mnbY5ADUBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:51:01.153578Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.03056","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a79bc78391f806c7771ace530c06daa7d69d06e22638fafeaae4488edc7ffcbd","sha256:be5caf732adc4b6175d603cd03f28f07549242f9b9990326498aa3df7b0b8bae"],"state_sha256":"fdcab0b963a84d19b79830a2d18d9c10241f20306507911ce951358774f1ebf1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lLuiY+fNjXctDTw6d1INI0NywzPjisIeZekC6CVeWvDmM+kcMJdob7/9ZXWQwmYEhqUhVizHLCqY/hPsdJKHDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T20:41:18.678852Z","bundle_sha256":"eb7432248d380d6aefad75c3ec0e95cce8b24062101a19bcdfff20165a243e31"}}