{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3BMAGVGLX2ODPAP7LXEEMEPQUM","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":"9f4610437c444c8bee5d98901b0df669234074ecaa5f639e680747cbc288ee34","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-13T16:17:34Z","title_canon_sha256":"30180020fd83126e24289acd816158f2ff799fe9572d66c2786baa35f22f9aef"},"schema_version":"1.0","source":{"id":"2201.05047","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.05047","created_at":"2026-07-05T05:18:01Z"},{"alias_kind":"arxiv_version","alias_value":"2201.05047v4","created_at":"2026-07-05T05:18:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05047","created_at":"2026-07-05T05:18:01Z"},{"alias_kind":"pith_short_12","alias_value":"3BMAGVGLX2OD","created_at":"2026-07-05T05:18:01Z"},{"alias_kind":"pith_short_16","alias_value":"3BMAGVGLX2ODPAP7","created_at":"2026-07-05T05:18:01Z"},{"alias_kind":"pith_short_8","alias_value":"3BMAGVGL","created_at":"2026-07-05T05:18:01Z"}],"graph_snapshots":[{"event_id":"sha256:d50bc886cb239ab923ad091b0caad69ca1cae6c3840840755f348414c1a5c2bc","target":"graph","created_at":"2026-07-05T05:18:01Z","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/2201.05047/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Detection Transformer (DETR) and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors. However, their performance on Video Object Detection (VOD) has not been well explored. In this paper, we present TransVOD, the first end-to-end video object detection system based on spatial-temporal Transformer architectures. The first goal of this paper is to streamline the pipeline of VOD, effectively removing the need for many hand-crafted components for feature aggreg","authors_text":"Dacheng Tao, Guangliang Cheng, Lizhuang Ma, Lu He, Qianyu Zhou, Xiangtai Li, Yibo Yang, Yunhai Tong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-13T16:17:34Z","title":"TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05047","kind":"arxiv","version":4},"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:f0e5bef325f17ae41d07517272164fa0dc665c722d2197e5d612a2f186d9cee9","target":"record","created_at":"2026-07-05T05:18:01Z","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":"9f4610437c444c8bee5d98901b0df669234074ecaa5f639e680747cbc288ee34","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-13T16:17:34Z","title_canon_sha256":"30180020fd83126e24289acd816158f2ff799fe9572d66c2786baa35f22f9aef"},"schema_version":"1.0","source":{"id":"2201.05047","kind":"arxiv","version":4}},"canonical_sha256":"d8580354cbbe9c3781ff5dc84611f0a33a1eb38510d86870651c06f08754f563","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8580354cbbe9c3781ff5dc84611f0a33a1eb38510d86870651c06f08754f563","first_computed_at":"2026-07-05T05:18:01.211959Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:18:01.211959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uHMiuneIKDLP1/u3YyKgk2PHH+zvNaLJiO7WNnH4tne8NjqSysMXM5HFi4drRoq8sN/wYkDVDISjjxjRsza5Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:18:01.212359Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.05047","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0e5bef325f17ae41d07517272164fa0dc665c722d2197e5d612a2f186d9cee9","sha256:d50bc886cb239ab923ad091b0caad69ca1cae6c3840840755f348414c1a5c2bc"],"state_sha256":"4e8ad0b7eead8f901ce70e1daceeae1c1a40d87fb19f98ab7f1f5b492761c24f"}