{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6QW76A5H7OLEJMUY3I7ULCODD7","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":"294439a5d910715e5c90fa049688e737ad956357cbd41f2f792b8a15fa91ce4e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-06T15:48:58Z","title_canon_sha256":"e55c3f09d2f04cf8d6dd00e05d2f31eab53bc525bd9c0f1d677500c0ac5d9b7c"},"schema_version":"1.0","source":{"id":"2207.02756","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.02756","created_at":"2026-07-05T04:38:07Z"},{"alias_kind":"arxiv_version","alias_value":"2207.02756v1","created_at":"2026-07-05T04:38:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.02756","created_at":"2026-07-05T04:38:07Z"},{"alias_kind":"pith_short_12","alias_value":"6QW76A5H7OLE","created_at":"2026-07-05T04:38:07Z"},{"alias_kind":"pith_short_16","alias_value":"6QW76A5H7OLEJMUY","created_at":"2026-07-05T04:38:07Z"},{"alias_kind":"pith_short_8","alias_value":"6QW76A5H","created_at":"2026-07-05T04:38:07Z"}],"graph_snapshots":[{"event_id":"sha256:26e342a4c3cda5321d03611b2eb3f3043e830f048a1daa1ef49a2eb8d9811ec5","target":"graph","created_at":"2026-07-05T04:38:07Z","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/2207.02756/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chaolei Tan, Jian-Fang Hu, Tiancai Ye, Wei-Shi Zheng, Zhi Jin, Zihang Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-06T15:48:58Z","title":"STVGFormer: Spatio-Temporal Video Grounding with Static-Dynamic Cross-Modal Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.02756","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:aa39194f3b9c5e9b3821136390620d9842b9a8d74d86effff90fd4f06b33a3e0","target":"record","created_at":"2026-07-05T04:38:07Z","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":"294439a5d910715e5c90fa049688e737ad956357cbd41f2f792b8a15fa91ce4e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-06T15:48:58Z","title_canon_sha256":"e55c3f09d2f04cf8d6dd00e05d2f31eab53bc525bd9c0f1d677500c0ac5d9b7c"},"schema_version":"1.0","source":{"id":"2207.02756","kind":"arxiv","version":1}},"canonical_sha256":"f42dff03a7fb9644b298da3f4589c31fe98452b04998da767ef46ddfff50e9d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f42dff03a7fb9644b298da3f4589c31fe98452b04998da767ef46ddfff50e9d9","first_computed_at":"2026-07-05T04:38:07.515761Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:38:07.515761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TqQK34hqx7bF+sF9SdjwGTJ5Esz9iCKA9EWFsaPj1amjyO0xNJvDzVhJKVxrLVmD5RlrnNuAI0SNKdR1KoW2Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:38:07.516151Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.02756","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa39194f3b9c5e9b3821136390620d9842b9a8d74d86effff90fd4f06b33a3e0","sha256:26e342a4c3cda5321d03611b2eb3f3043e830f048a1daa1ef49a2eb8d9811ec5"],"state_sha256":"4a1f9c6aa76f203beee20753d2f6ef3726f1f6fcaef9925a35d73e6579ca011a"}