{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3BMAGVGLX2ODPAP7LXEEMEPQUM","short_pith_number":"pith:3BMAGVGL","schema_version":"1.0","canonical_sha256":"d8580354cbbe9c3781ff5dc84611f0a33a1eb38510d86870651c06f08754f563","source":{"kind":"arxiv","id":"2201.05047","version":4},"attestation_state":"computed","paper":{"title":"TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Guangliang Cheng, Lizhuang Ma, Lu He, Qianyu Zhou, Xiangtai Li, Yibo Yang, Yunhai Tong","submitted_at":"2022-01-13T16:17:34Z","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"},"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":"2201.05047","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-13T16:17:34Z","cross_cats_sorted":[],"title_canon_sha256":"30180020fd83126e24289acd816158f2ff799fe9572d66c2786baa35f22f9aef","abstract_canon_sha256":"9f4610437c444c8bee5d98901b0df669234074ecaa5f639e680747cbc288ee34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:01.212359Z","signature_b64":"uHMiuneIKDLP1/u3YyKgk2PHH+zvNaLJiO7WNnH4tne8NjqSysMXM5HFi4drRoq8sN/wYkDVDISjjxjRsza5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8580354cbbe9c3781ff5dc84611f0a33a1eb38510d86870651c06f08754f563","last_reissued_at":"2026-07-05T05:18:01.211959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:01.211959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Guangliang Cheng, Lizhuang Ma, Lu He, Qianyu Zhou, Xiangtai Li, Yibo Yang, Yunhai Tong","submitted_at":"2022-01-13T16:17:34Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05047","kind":"arxiv","version":4},"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/2201.05047/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":"2201.05047","created_at":"2026-07-05T05:18:01.212015+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.05047v4","created_at":"2026-07-05T05:18:01.212015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05047","created_at":"2026-07-05T05:18:01.212015+00:00"},{"alias_kind":"pith_short_12","alias_value":"3BMAGVGLX2OD","created_at":"2026-07-05T05:18:01.212015+00:00"},{"alias_kind":"pith_short_16","alias_value":"3BMAGVGLX2ODPAP7","created_at":"2026-07-05T05:18:01.212015+00:00"},{"alias_kind":"pith_short_8","alias_value":"3BMAGVGL","created_at":"2026-07-05T05:18:01.212015+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/3BMAGVGLX2ODPAP7LXEEMEPQUM","json":"https://pith.science/pith/3BMAGVGLX2ODPAP7LXEEMEPQUM.json","graph_json":"https://pith.science/api/pith-number/3BMAGVGLX2ODPAP7LXEEMEPQUM/graph.json","events_json":"https://pith.science/api/pith-number/3BMAGVGLX2ODPAP7LXEEMEPQUM/events.json","paper":"https://pith.science/paper/3BMAGVGL"},"agent_actions":{"view_html":"https://pith.science/pith/3BMAGVGLX2ODPAP7LXEEMEPQUM","download_json":"https://pith.science/pith/3BMAGVGLX2ODPAP7LXEEMEPQUM.json","view_paper":"https://pith.science/paper/3BMAGVGL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.05047&json=true","fetch_graph":"https://pith.science/api/pith-number/3BMAGVGLX2ODPAP7LXEEMEPQUM/graph.json","fetch_events":"https://pith.science/api/pith-number/3BMAGVGLX2ODPAP7LXEEMEPQUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3BMAGVGLX2ODPAP7LXEEMEPQUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3BMAGVGLX2ODPAP7LXEEMEPQUM/action/storage_attestation","attest_author":"https://pith.science/pith/3BMAGVGLX2ODPAP7LXEEMEPQUM/action/author_attestation","sign_citation":"https://pith.science/pith/3BMAGVGLX2ODPAP7LXEEMEPQUM/action/citation_signature","submit_replication":"https://pith.science/pith/3BMAGVGLX2ODPAP7LXEEMEPQUM/action/replication_record"}},"created_at":"2026-07-05T05:18:01.212015+00:00","updated_at":"2026-07-05T05:18:01.212015+00:00"}