{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:T2SQWCTINEQ7XRLMXIJ33QRNBM","short_pith_number":"pith:T2SQWCTI","schema_version":"1.0","canonical_sha256":"9ea50b0a686921fbc56cba13bdc22d0b3d15954e645a1b76d82f217f5e44fe54","source":{"kind":"arxiv","id":"2108.08121","version":1},"attestation_state":"computed","paper":{"title":"Target Adaptive Context Aggregation for Video Scene Graph Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gangshan Wu, Limin Wang, Yao Teng, ZhiFeng Li","submitted_at":"2021-08-18T12:46:28Z","abstract_excerpt":"This paper deals with a challenging task of video scene graph generation (VidSGG), which could serve as a structured video representation for high-level understanding tasks. We present a new {\\em detect-to-track} paradigm for this task by decoupling the context modeling for relation prediction from the complicated low-level entity tracking. Specifically, we design an efficient method for frame-level VidSGG, termed as {\\em Target Adaptive Context Aggregation Network} (TRACE), with a focus on capturing spatio-temporal context information for relation recognition. Our TRACE framework streamlines "},"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":"2108.08121","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-18T12:46:28Z","cross_cats_sorted":[],"title_canon_sha256":"d33fc9a4cfa7718a195ac5ad866ad2deea9d834356d56318c11605a7ea6c6adb","abstract_canon_sha256":"2c19de9a635c9def628e181ce2af272d8e34f8d5fedb32588ad1bb6c8643d1ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:59.767058Z","signature_b64":"xlVEV4RFzAagYTB9jnLWmUzyYMGsWWKlq/NcPZDqn2X5Q1zhfH1nnyDfJ4rsrKcfWFyCw6QbP7SCmFy7XgwdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ea50b0a686921fbc56cba13bdc22d0b3d15954e645a1b76d82f217f5e44fe54","last_reissued_at":"2026-07-05T03:06:59.766699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:59.766699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Target Adaptive Context Aggregation for Video Scene Graph Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gangshan Wu, Limin Wang, Yao Teng, ZhiFeng Li","submitted_at":"2021-08-18T12:46:28Z","abstract_excerpt":"This paper deals with a challenging task of video scene graph generation (VidSGG), which could serve as a structured video representation for high-level understanding tasks. We present a new {\\em detect-to-track} paradigm for this task by decoupling the context modeling for relation prediction from the complicated low-level entity tracking. Specifically, we design an efficient method for frame-level VidSGG, termed as {\\em Target Adaptive Context Aggregation Network} (TRACE), with a focus on capturing spatio-temporal context information for relation recognition. Our TRACE framework streamlines "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.08121","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2108.08121/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":"2108.08121","created_at":"2026-07-05T03:06:59.766754+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.08121v1","created_at":"2026-07-05T03:06:59.766754+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.08121","created_at":"2026-07-05T03:06:59.766754+00:00"},{"alias_kind":"pith_short_12","alias_value":"T2SQWCTINEQ7","created_at":"2026-07-05T03:06:59.766754+00:00"},{"alias_kind":"pith_short_16","alias_value":"T2SQWCTINEQ7XRLM","created_at":"2026-07-05T03:06:59.766754+00:00"},{"alias_kind":"pith_short_8","alias_value":"T2SQWCTI","created_at":"2026-07-05T03:06:59.766754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T2SQWCTINEQ7XRLMXIJ33QRNBM","json":"https://pith.science/pith/T2SQWCTINEQ7XRLMXIJ33QRNBM.json","graph_json":"https://pith.science/api/pith-number/T2SQWCTINEQ7XRLMXIJ33QRNBM/graph.json","events_json":"https://pith.science/api/pith-number/T2SQWCTINEQ7XRLMXIJ33QRNBM/events.json","paper":"https://pith.science/paper/T2SQWCTI"},"agent_actions":{"view_html":"https://pith.science/pith/T2SQWCTINEQ7XRLMXIJ33QRNBM","download_json":"https://pith.science/pith/T2SQWCTINEQ7XRLMXIJ33QRNBM.json","view_paper":"https://pith.science/paper/T2SQWCTI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.08121&json=true","fetch_graph":"https://pith.science/api/pith-number/T2SQWCTINEQ7XRLMXIJ33QRNBM/graph.json","fetch_events":"https://pith.science/api/pith-number/T2SQWCTINEQ7XRLMXIJ33QRNBM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T2SQWCTINEQ7XRLMXIJ33QRNBM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T2SQWCTINEQ7XRLMXIJ33QRNBM/action/storage_attestation","attest_author":"https://pith.science/pith/T2SQWCTINEQ7XRLMXIJ33QRNBM/action/author_attestation","sign_citation":"https://pith.science/pith/T2SQWCTINEQ7XRLMXIJ33QRNBM/action/citation_signature","submit_replication":"https://pith.science/pith/T2SQWCTINEQ7XRLMXIJ33QRNBM/action/replication_record"}},"created_at":"2026-07-05T03:06:59.766754+00:00","updated_at":"2026-07-05T03:06:59.766754+00:00"}