{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:FGVW5KRRP6WTBDTZTO52GSWG6Y","short_pith_number":"pith:FGVW5KRR","canonical_record":{"source":{"id":"1902.07370","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-20T01:58:42Z","cross_cats_sorted":[],"title_canon_sha256":"d7ffb37007d72ee102f9b46830959bddda138bebe9fe954b749a156e66d6663e","abstract_canon_sha256":"9130f2c60dfb964d760700a7af24f0669a5c8f8b04a0455f8e7b8e787c1e3bf5"},"schema_version":"1.0"},"canonical_sha256":"29ab6eaa317fad308e799bbba34ac6f63221a6fecbd80c9e1ab8b6a8fbd658cf","source":{"kind":"arxiv","id":"1902.07370","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.07370","created_at":"2026-05-17T23:53:08Z"},{"alias_kind":"arxiv_version","alias_value":"1902.07370v1","created_at":"2026-05-17T23:53:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.07370","created_at":"2026-05-17T23:53:08Z"},{"alias_kind":"pith_short_12","alias_value":"FGVW5KRRP6WT","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"FGVW5KRRP6WTBDTZ","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"FGVW5KRR","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:FGVW5KRRP6WTBDTZTO52GSWG6Y","target":"record","payload":{"canonical_record":{"source":{"id":"1902.07370","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-20T01:58:42Z","cross_cats_sorted":[],"title_canon_sha256":"d7ffb37007d72ee102f9b46830959bddda138bebe9fe954b749a156e66d6663e","abstract_canon_sha256":"9130f2c60dfb964d760700a7af24f0669a5c8f8b04a0455f8e7b8e787c1e3bf5"},"schema_version":"1.0"},"canonical_sha256":"29ab6eaa317fad308e799bbba34ac6f63221a6fecbd80c9e1ab8b6a8fbd658cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:08.183263Z","signature_b64":"L+zOT1uvvnplJFd6aAw6rJ9C+L1+RaF6FIgEOnvBaIa3dkeWv4H7hrJ03r/yUkS9oPe0m1RTW9Go/GRl879DBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29ab6eaa317fad308e799bbba34ac6f63221a6fecbd80c9e1ab8b6a8fbd658cf","last_reissued_at":"2026-05-17T23:53:08.182716Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:08.182716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.07370","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":"2026-05-17T23:53:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TjyX3ixmSoudC6z8usJ5U7pLuqh15Uooy6HCGXkqN0CT54CelyjmQEfncMj6AgL/pDUkJJhHc1tKOxVGBsyNAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T15:28:00.971618Z"},"content_sha256":"372ec5694f724678eb1269144bf8a0060b85a506780d414043dba0320b1370bb","schema_version":"1.0","event_id":"sha256:372ec5694f724678eb1269144bf8a0060b85a506780d414043dba0320b1370bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:FGVW5KRRP6WTBDTZTO52GSWG6Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Transferable Self-attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Li, Haichao Shi, Kai Zheng, Lixin Duan, Xiaobin Zhu, Xiao-Yu Zhang","submitted_at":"2019-02-20T01:58:42Z","abstract_excerpt":"Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume videos are trimmed as short sequences and require ground-truth annotations of each video frame/sequence, which is quite costly and time-consuming. In this paper, given only video-level annotations, we propose a novel weakly supervised framework to simultaneously locate action frames as well as recognize actions in untrimmed videos. Our proposed framework consists of two major components. First, for action frame localization, we take advantage of the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.07370","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":"2026-05-17T23:53:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n4yRpoFXiOc7zTxHA23jMdpIW0+A8UBxV6BoH8q5i1hvEcnRHUFTNd07msrVRLHu6NiV0HZGqQ1Q4TrHTV4IBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T15:28:00.972251Z"},"content_sha256":"8e1eec5d9ecbc8aac5a25cab09cad73df9d78090db7338ba3711860377097eba","schema_version":"1.0","event_id":"sha256:8e1eec5d9ecbc8aac5a25cab09cad73df9d78090db7338ba3711860377097eba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FGVW5KRRP6WTBDTZTO52GSWG6Y/bundle.json","state_url":"https://pith.science/pith/FGVW5KRRP6WTBDTZTO52GSWG6Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FGVW5KRRP6WTBDTZTO52GSWG6Y/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":"2026-05-28T15:28:00Z","links":{"resolver":"https://pith.science/pith/FGVW5KRRP6WTBDTZTO52GSWG6Y","bundle":"https://pith.science/pith/FGVW5KRRP6WTBDTZTO52GSWG6Y/bundle.json","state":"https://pith.science/pith/FGVW5KRRP6WTBDTZTO52GSWG6Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FGVW5KRRP6WTBDTZTO52GSWG6Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:FGVW5KRRP6WTBDTZTO52GSWG6Y","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":"9130f2c60dfb964d760700a7af24f0669a5c8f8b04a0455f8e7b8e787c1e3bf5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-20T01:58:42Z","title_canon_sha256":"d7ffb37007d72ee102f9b46830959bddda138bebe9fe954b749a156e66d6663e"},"schema_version":"1.0","source":{"id":"1902.07370","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.07370","created_at":"2026-05-17T23:53:08Z"},{"alias_kind":"arxiv_version","alias_value":"1902.07370v1","created_at":"2026-05-17T23:53:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.07370","created_at":"2026-05-17T23:53:08Z"},{"alias_kind":"pith_short_12","alias_value":"FGVW5KRRP6WT","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"FGVW5KRRP6WTBDTZ","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"FGVW5KRR","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:8e1eec5d9ecbc8aac5a25cab09cad73df9d78090db7338ba3711860377097eba","target":"graph","created_at":"2026-05-17T23:53:08Z","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":"Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume videos are trimmed as short sequences and require ground-truth annotations of each video frame/sequence, which is quite costly and time-consuming. In this paper, given only video-level annotations, we propose a novel weakly supervised framework to simultaneously locate action frames as well as recognize actions in untrimmed videos. Our proposed framework consists of two major components. First, for action frame localization, we take advantage of the","authors_text":"Changsheng Li, Haichao Shi, Kai Zheng, Lixin Duan, Xiaobin Zhu, Xiao-Yu Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-20T01:58:42Z","title":"Learning Transferable Self-attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.07370","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":"sha256:372ec5694f724678eb1269144bf8a0060b85a506780d414043dba0320b1370bb","target":"record","created_at":"2026-05-17T23:53:08Z","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":"9130f2c60dfb964d760700a7af24f0669a5c8f8b04a0455f8e7b8e787c1e3bf5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-20T01:58:42Z","title_canon_sha256":"d7ffb37007d72ee102f9b46830959bddda138bebe9fe954b749a156e66d6663e"},"schema_version":"1.0","source":{"id":"1902.07370","kind":"arxiv","version":1}},"canonical_sha256":"29ab6eaa317fad308e799bbba34ac6f63221a6fecbd80c9e1ab8b6a8fbd658cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29ab6eaa317fad308e799bbba34ac6f63221a6fecbd80c9e1ab8b6a8fbd658cf","first_computed_at":"2026-05-17T23:53:08.182716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:53:08.182716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L+zOT1uvvnplJFd6aAw6rJ9C+L1+RaF6FIgEOnvBaIa3dkeWv4H7hrJ03r/yUkS9oPe0m1RTW9Go/GRl879DBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:53:08.183263Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.07370","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:372ec5694f724678eb1269144bf8a0060b85a506780d414043dba0320b1370bb","sha256:8e1eec5d9ecbc8aac5a25cab09cad73df9d78090db7338ba3711860377097eba"],"state_sha256":"52cee9ad38c04d466cb07a1608c726bbd863cecee99c14603470d647c00149c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qAmC2JzG0XsPuaAwa9qm0T3Bf+fk2kAZroaTBQ12h9ddKgkE17hZkcuO3HfaDkvUBBZjGU9ZcziYsW3rVU3VDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T15:28:00.975526Z","bundle_sha256":"1a7635597aba12e915677083343bd00243488c9ffa7e9646837f5fe541eabda6"}}