{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:PC7P4OC5G3BEPWQT3WWVI4BVUX","short_pith_number":"pith:PC7P4OC5","canonical_record":{"source":{"id":"2106.10634","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-20T06:35:40Z","cross_cats_sorted":[],"title_canon_sha256":"b8c9a418ca19e391be0f13fe7bb6e442a031527076fc5f97c56da3d37abddb22","abstract_canon_sha256":"fb2fe39cf8ddd1a61bc511742f2a4a533d00346247f9ce0e4b77317f970d7b37"},"schema_version":"1.0"},"canonical_sha256":"78befe385d36c247da13ddad547035a5f7c636be576e5695944f5d934c310c05","source":{"kind":"arxiv","id":"2106.10634","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.10634","created_at":"2026-07-05T04:20:28Z"},{"alias_kind":"arxiv_version","alias_value":"2106.10634v2","created_at":"2026-07-05T04:20:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.10634","created_at":"2026-07-05T04:20:28Z"},{"alias_kind":"pith_short_12","alias_value":"PC7P4OC5G3BE","created_at":"2026-07-05T04:20:28Z"},{"alias_kind":"pith_short_16","alias_value":"PC7P4OC5G3BEPWQT","created_at":"2026-07-05T04:20:28Z"},{"alias_kind":"pith_short_8","alias_value":"PC7P4OC5","created_at":"2026-07-05T04:20:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:PC7P4OC5G3BEPWQT3WWVI4BVUX","target":"record","payload":{"canonical_record":{"source":{"id":"2106.10634","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-20T06:35:40Z","cross_cats_sorted":[],"title_canon_sha256":"b8c9a418ca19e391be0f13fe7bb6e442a031527076fc5f97c56da3d37abddb22","abstract_canon_sha256":"fb2fe39cf8ddd1a61bc511742f2a4a533d00346247f9ce0e4b77317f970d7b37"},"schema_version":"1.0"},"canonical_sha256":"78befe385d36c247da13ddad547035a5f7c636be576e5695944f5d934c310c05","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:28.566073Z","signature_b64":"0RWnXlFnZbxFwNYkPXw3x85u/+ky6AwBeLMcGJh2mCxSX8WbguFN9WPVJJ4IirHfLyq1aaFdkFUd+gikEVh/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78befe385d36c247da13ddad547035a5f7c636be576e5695944f5d934c310c05","last_reissued_at":"2026-07-05T04:20:28.565610Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:28.565610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.10634","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":"2026-07-05T04:20:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vajmSwy2Pu8C1OWiqgw6zpaR58CbwK/Jomatty4iai44g8pQGxV3/swhMITelvDLGo49rq3k+CZSOEMXtKnYAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:00:39.101343Z"},"content_sha256":"0f0d6580e0c32ba3a548e7d24f97533955028826e5344eb25d075abc84410000","schema_version":"1.0","event_id":"sha256:0f0d6580e0c32ba3a548e7d24f97533955028826e5344eb25d075abc84410000"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:PC7P4OC5G3BEPWQT3WWVI4BVUX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Augmented 2D-TAN: A Two-stage Approach for Human-centric Spatio-Temporal Video Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaolei Tan, Jian-Fang Hu, Wei-Shi Zheng, Xiang Li, Zihang Lin","submitted_at":"2021-06-20T06:35:40Z","abstract_excerpt":"We propose an effective two-stage approach to tackle the problem of language-based Human-centric Spatio-Temporal Video Grounding (HC-STVG) task. In the first stage, we propose an Augmented 2D Temporal Adjacent Network (Augmented 2D-TAN) to temporally ground the target moment corresponding to the given description. Primarily, we improve the original 2D-TAN from two aspects: First, a temporal context-aware Bi-LSTM Aggregation Module is developed to aggregate clip-level representations, replacing the original max-pooling. Second, we propose to employ Random Concatenation Augmentation (RCA) mechan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.10634","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.10634/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T04:20:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q82OUQXzqcabPgkM4751yXojr9mT4MouD2MztHsC0kUvke6Q4SJXH5iLi8C4+M2T6gSxrXrua/JO6uK0ONjuCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:00:39.101878Z"},"content_sha256":"1621df73e5c1ed3327659ffc2a6a5cdf0d5dee8cc24a6e93262f2b2bea7e1189","schema_version":"1.0","event_id":"sha256:1621df73e5c1ed3327659ffc2a6a5cdf0d5dee8cc24a6e93262f2b2bea7e1189"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PC7P4OC5G3BEPWQT3WWVI4BVUX/bundle.json","state_url":"https://pith.science/pith/PC7P4OC5G3BEPWQT3WWVI4BVUX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PC7P4OC5G3BEPWQT3WWVI4BVUX/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":"2026-08-05T08:00:39Z","links":{"resolver":"https://pith.science/pith/PC7P4OC5G3BEPWQT3WWVI4BVUX","bundle":"https://pith.science/pith/PC7P4OC5G3BEPWQT3WWVI4BVUX/bundle.json","state":"https://pith.science/pith/PC7P4OC5G3BEPWQT3WWVI4BVUX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PC7P4OC5G3BEPWQT3WWVI4BVUX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PC7P4OC5G3BEPWQT3WWVI4BVUX","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":"fb2fe39cf8ddd1a61bc511742f2a4a533d00346247f9ce0e4b77317f970d7b37","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-20T06:35:40Z","title_canon_sha256":"b8c9a418ca19e391be0f13fe7bb6e442a031527076fc5f97c56da3d37abddb22"},"schema_version":"1.0","source":{"id":"2106.10634","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.10634","created_at":"2026-07-05T04:20:28Z"},{"alias_kind":"arxiv_version","alias_value":"2106.10634v2","created_at":"2026-07-05T04:20:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.10634","created_at":"2026-07-05T04:20:28Z"},{"alias_kind":"pith_short_12","alias_value":"PC7P4OC5G3BE","created_at":"2026-07-05T04:20:28Z"},{"alias_kind":"pith_short_16","alias_value":"PC7P4OC5G3BEPWQT","created_at":"2026-07-05T04:20:28Z"},{"alias_kind":"pith_short_8","alias_value":"PC7P4OC5","created_at":"2026-07-05T04:20:28Z"}],"graph_snapshots":[{"event_id":"sha256:1621df73e5c1ed3327659ffc2a6a5cdf0d5dee8cc24a6e93262f2b2bea7e1189","target":"graph","created_at":"2026-07-05T04:20:28Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.10634/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose an effective two-stage approach to tackle the problem of language-based Human-centric Spatio-Temporal Video Grounding (HC-STVG) task. In the first stage, we propose an Augmented 2D Temporal Adjacent Network (Augmented 2D-TAN) to temporally ground the target moment corresponding to the given description. Primarily, we improve the original 2D-TAN from two aspects: First, a temporal context-aware Bi-LSTM Aggregation Module is developed to aggregate clip-level representations, replacing the original max-pooling. Second, we propose to employ Random Concatenation Augmentation (RCA) mechan","authors_text":"Chaolei Tan, Jian-Fang Hu, Wei-Shi Zheng, Xiang Li, Zihang Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-20T06:35:40Z","title":"Augmented 2D-TAN: A Two-stage Approach for Human-centric Spatio-Temporal Video Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.10634","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":"sha256:0f0d6580e0c32ba3a548e7d24f97533955028826e5344eb25d075abc84410000","target":"record","created_at":"2026-07-05T04:20:28Z","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":"fb2fe39cf8ddd1a61bc511742f2a4a533d00346247f9ce0e4b77317f970d7b37","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-20T06:35:40Z","title_canon_sha256":"b8c9a418ca19e391be0f13fe7bb6e442a031527076fc5f97c56da3d37abddb22"},"schema_version":"1.0","source":{"id":"2106.10634","kind":"arxiv","version":2}},"canonical_sha256":"78befe385d36c247da13ddad547035a5f7c636be576e5695944f5d934c310c05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78befe385d36c247da13ddad547035a5f7c636be576e5695944f5d934c310c05","first_computed_at":"2026-07-05T04:20:28.565610Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:20:28.565610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0RWnXlFnZbxFwNYkPXw3x85u/+ky6AwBeLMcGJh2mCxSX8WbguFN9WPVJJ4IirHfLyq1aaFdkFUd+gikEVh/AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:20:28.566073Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.10634","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f0d6580e0c32ba3a548e7d24f97533955028826e5344eb25d075abc84410000","sha256:1621df73e5c1ed3327659ffc2a6a5cdf0d5dee8cc24a6e93262f2b2bea7e1189"],"state_sha256":"7ffb02d60b4b6eed6a7181e1a128c411a0232962b6a8663634785916f394a3eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DiTol8ZinQ1tsUsfhYI3gu/OCkP6fc2BqdbJrVSTGORpR5EI2y2on22a1QQJhE7RLjnc8g3ucWuTh0r4zrytDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:00:39.107107Z","bundle_sha256":"8fc8b804443c2f7fa6cce509181b5ece9253b379f78ae06b050798f6db015773"}}