{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PC7P4OC5G3BEPWQT3WWVI4BVUX","short_pith_number":"pith:PC7P4OC5","schema_version":"1.0","canonical_sha256":"78befe385d36c247da13ddad547035a5f7c636be576e5695944f5d934c310c05","source":{"kind":"arxiv","id":"2106.10634","version":2},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2106.10634","created_at":"2026-07-05T04:20:28.565674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.10634v2","created_at":"2026-07-05T04:20:28.565674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.10634","created_at":"2026-07-05T04:20:28.565674+00:00"},{"alias_kind":"pith_short_12","alias_value":"PC7P4OC5G3BE","created_at":"2026-07-05T04:20:28.565674+00:00"},{"alias_kind":"pith_short_16","alias_value":"PC7P4OC5G3BEPWQT","created_at":"2026-07-05T04:20:28.565674+00:00"},{"alias_kind":"pith_short_8","alias_value":"PC7P4OC5","created_at":"2026-07-05T04:20:28.565674+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12346","citing_title":"Unlocking the Potential of Grounding DINO in Videos: Parameter-Efficient Adaptation for Limited-Data Spatial-Temporal Localization","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PC7P4OC5G3BEPWQT3WWVI4BVUX","json":"https://pith.science/pith/PC7P4OC5G3BEPWQT3WWVI4BVUX.json","graph_json":"https://pith.science/api/pith-number/PC7P4OC5G3BEPWQT3WWVI4BVUX/graph.json","events_json":"https://pith.science/api/pith-number/PC7P4OC5G3BEPWQT3WWVI4BVUX/events.json","paper":"https://pith.science/paper/PC7P4OC5"},"agent_actions":{"view_html":"https://pith.science/pith/PC7P4OC5G3BEPWQT3WWVI4BVUX","download_json":"https://pith.science/pith/PC7P4OC5G3BEPWQT3WWVI4BVUX.json","view_paper":"https://pith.science/paper/PC7P4OC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.10634&json=true","fetch_graph":"https://pith.science/api/pith-number/PC7P4OC5G3BEPWQT3WWVI4BVUX/graph.json","fetch_events":"https://pith.science/api/pith-number/PC7P4OC5G3BEPWQT3WWVI4BVUX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PC7P4OC5G3BEPWQT3WWVI4BVUX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PC7P4OC5G3BEPWQT3WWVI4BVUX/action/storage_attestation","attest_author":"https://pith.science/pith/PC7P4OC5G3BEPWQT3WWVI4BVUX/action/author_attestation","sign_citation":"https://pith.science/pith/PC7P4OC5G3BEPWQT3WWVI4BVUX/action/citation_signature","submit_replication":"https://pith.science/pith/PC7P4OC5G3BEPWQT3WWVI4BVUX/action/replication_record"}},"created_at":"2026-07-05T04:20:28.565674+00:00","updated_at":"2026-07-05T04:20:28.565674+00:00"}