{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QHNKA4ASCPSC4KZSWYRFAKCSXW","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":"39318773f41c0f3d630db50902a9fd674a9c33c0a165efe64a34e2aa63196740","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-10T11:23:38Z","title_canon_sha256":"1b04623c89d303e364d937d31fec359a3adae6fb1bc85dbefc24953c4c5306c3"},"schema_version":"1.0","source":{"id":"2011.05049","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.05049","created_at":"2026-07-05T02:45:34Z"},{"alias_kind":"arxiv_version","alias_value":"2011.05049v2","created_at":"2026-07-05T02:45:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.05049","created_at":"2026-07-05T02:45:34Z"},{"alias_kind":"pith_short_12","alias_value":"QHNKA4ASCPSC","created_at":"2026-07-05T02:45:34Z"},{"alias_kind":"pith_short_16","alias_value":"QHNKA4ASCPSC4KZS","created_at":"2026-07-05T02:45:34Z"},{"alias_kind":"pith_short_8","alias_value":"QHNKA4AS","created_at":"2026-07-05T02:45:34Z"}],"graph_snapshots":[{"event_id":"sha256:37d89e0e8ba346977096e5aa27e08885c7cdff943c01d9ea0c23bc3616589c88","target":"graph","created_at":"2026-07-05T02:45:34Z","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/2011.05049/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we introduce a novel task - Humancentric Spatio-Temporal Video Grounding (HC-STVG). Unlike the existing referring expression tasks in images or videos, by focusing on humans, HC-STVG aims to localize a spatiotemporal tube of the target person from an untrimmed video based on a given textural description. This task is useful, especially for healthcare and security-related applications, where the surveillance videos can be extremely long but only a specific person during a specific period of time is concerned. HC-STVG is a video grounding task that requires both spatial (where) and","authors_text":"Dong Xu, Guanbin Li, Hongxu Jiang, Qian Yu, Si Liu, Xiaojie Jin, Yue Liao, Zongheng Tang","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-10T11:23:38Z","title":"Human-centric Spatio-Temporal Video Grounding With Visual Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.05049","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:ae2a24ecca9c541dbd8f271c2397fd253476a2996fa64aa1791038bd42e06f29","target":"record","created_at":"2026-07-05T02:45:34Z","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":"39318773f41c0f3d630db50902a9fd674a9c33c0a165efe64a34e2aa63196740","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-10T11:23:38Z","title_canon_sha256":"1b04623c89d303e364d937d31fec359a3adae6fb1bc85dbefc24953c4c5306c3"},"schema_version":"1.0","source":{"id":"2011.05049","kind":"arxiv","version":2}},"canonical_sha256":"81daa0701213e42e2b32b622502852bd972877d95fe7bae7f7207e6c0effc1a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81daa0701213e42e2b32b622502852bd972877d95fe7bae7f7207e6c0effc1a0","first_computed_at":"2026-07-05T02:45:34.217573Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:45:34.217573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p9seWjhUiGP9MGrw0yz0JkZcBWBkzQxys5SlooDgnJfZc8E1wLiTqZTHWwYViYfKZFbU9KWw0Jx0rGBgZpfEDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:45:34.218049Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.05049","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae2a24ecca9c541dbd8f271c2397fd253476a2996fa64aa1791038bd42e06f29","sha256:37d89e0e8ba346977096e5aa27e08885c7cdff943c01d9ea0c23bc3616589c88"],"state_sha256":"446a6ea501a127572b3c716a3a20a053d1c0f8ec12202aee62f7bb1e32b822d1"}