{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6QW76A5H7OLEJMUY3I7ULCODD7","short_pith_number":"pith:6QW76A5H","schema_version":"1.0","canonical_sha256":"f42dff03a7fb9644b298da3f4589c31fe98452b04998da767ef46ddfff50e9d9","source":{"kind":"arxiv","id":"2207.02756","version":1},"attestation_state":"computed","paper":{"title":"STVGFormer: Spatio-Temporal Video Grounding with Static-Dynamic Cross-Modal Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaolei Tan, Jian-Fang Hu, Tiancai Ye, Wei-Shi Zheng, Zhi Jin, Zihang Lin","submitted_at":"2022-07-06T15:48:58Z","abstract_excerpt":"In this technical report, we introduce our solution to human-centric spatio-temporal video grounding task. We propose a concise and effective framework named STVGFormer, which models spatiotemporal visual-linguistic dependencies with a static branch and a dynamic branch. The static branch performs cross-modal understanding in a single frame and learns to localize the target object spatially according to intra-frame visual cues like object appearances. The dynamic branch performs cross-modal understanding across multiple frames. It learns to predict the starting and ending time of the target mo"},"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":"2207.02756","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-06T15:48:58Z","cross_cats_sorted":[],"title_canon_sha256":"e55c3f09d2f04cf8d6dd00e05d2f31eab53bc525bd9c0f1d677500c0ac5d9b7c","abstract_canon_sha256":"294439a5d910715e5c90fa049688e737ad956357cbd41f2f792b8a15fa91ce4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:07.516151Z","signature_b64":"TqQK34hqx7bF+sF9SdjwGTJ5Esz9iCKA9EWFsaPj1amjyO0xNJvDzVhJKVxrLVmD5RlrnNuAI0SNKdR1KoW2Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f42dff03a7fb9644b298da3f4589c31fe98452b04998da767ef46ddfff50e9d9","last_reissued_at":"2026-07-05T04:38:07.515761Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:07.515761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STVGFormer: Spatio-Temporal Video Grounding with Static-Dynamic Cross-Modal Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaolei Tan, Jian-Fang Hu, Tiancai Ye, Wei-Shi Zheng, Zhi Jin, Zihang Lin","submitted_at":"2022-07-06T15:48:58Z","abstract_excerpt":"In this technical report, we introduce our solution to human-centric spatio-temporal video grounding task. We propose a concise and effective framework named STVGFormer, which models spatiotemporal visual-linguistic dependencies with a static branch and a dynamic branch. The static branch performs cross-modal understanding in a single frame and learns to localize the target object spatially according to intra-frame visual cues like object appearances. The dynamic branch performs cross-modal understanding across multiple frames. It learns to predict the starting and ending time of the target mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.02756","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/2207.02756/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":"2207.02756","created_at":"2026-07-05T04:38:07.515813+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.02756v1","created_at":"2026-07-05T04:38:07.515813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.02756","created_at":"2026-07-05T04:38:07.515813+00:00"},{"alias_kind":"pith_short_12","alias_value":"6QW76A5H7OLE","created_at":"2026-07-05T04:38:07.515813+00:00"},{"alias_kind":"pith_short_16","alias_value":"6QW76A5H7OLEJMUY","created_at":"2026-07-05T04:38:07.515813+00:00"},{"alias_kind":"pith_short_8","alias_value":"6QW76A5H","created_at":"2026-07-05T04:38:07.515813+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/6QW76A5H7OLEJMUY3I7ULCODD7","json":"https://pith.science/pith/6QW76A5H7OLEJMUY3I7ULCODD7.json","graph_json":"https://pith.science/api/pith-number/6QW76A5H7OLEJMUY3I7ULCODD7/graph.json","events_json":"https://pith.science/api/pith-number/6QW76A5H7OLEJMUY3I7ULCODD7/events.json","paper":"https://pith.science/paper/6QW76A5H"},"agent_actions":{"view_html":"https://pith.science/pith/6QW76A5H7OLEJMUY3I7ULCODD7","download_json":"https://pith.science/pith/6QW76A5H7OLEJMUY3I7ULCODD7.json","view_paper":"https://pith.science/paper/6QW76A5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.02756&json=true","fetch_graph":"https://pith.science/api/pith-number/6QW76A5H7OLEJMUY3I7ULCODD7/graph.json","fetch_events":"https://pith.science/api/pith-number/6QW76A5H7OLEJMUY3I7ULCODD7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6QW76A5H7OLEJMUY3I7ULCODD7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6QW76A5H7OLEJMUY3I7ULCODD7/action/storage_attestation","attest_author":"https://pith.science/pith/6QW76A5H7OLEJMUY3I7ULCODD7/action/author_attestation","sign_citation":"https://pith.science/pith/6QW76A5H7OLEJMUY3I7ULCODD7/action/citation_signature","submit_replication":"https://pith.science/pith/6QW76A5H7OLEJMUY3I7ULCODD7/action/replication_record"}},"created_at":"2026-07-05T04:38:07.515813+00:00","updated_at":"2026-07-05T04:38:07.515813+00:00"}