{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:E3VFWJHEIOFXY5I7QEMYUPBZKI","short_pith_number":"pith:E3VFWJHE","schema_version":"1.0","canonical_sha256":"26ea5b24e4438b7c751f81198a3c3952387fce5a850334b4cc9bda3aeb2ec932","source":{"kind":"arxiv","id":"2110.03921","version":2},"attestation_state":"computed","paper":{"title":"ViDT: An Efficient and Effective Fully Transformer-based Object Detector","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Byeongho Heo, Deqing Sun, Dongyoon Han, Hwanjun Song, Ming-Hsuan Yang, Sanghyuk Chun, Varun Jampani, Wonjae Kim","submitted_at":"2021-10-08T06:32:05Z","abstract_excerpt":"Transformers are transforming the landscape of computer vision, especially for recognition tasks. Detection transformers are the first fully end-to-end learning systems for object detection, while vision transformers are the first fully transformer-based architecture for image classification. In this paper, we integrate Vision and Detection Transformers (ViDT) to build an effective and efficient object detector. ViDT introduces a reconfigured attention module to extend the recent Swin Transformer to be a standalone object detector, followed by a computationally efficient transformer decoder th"},"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":"2110.03921","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-08T06:32:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0c81584429d2130e39f60b94a5bde484b7f958a51360bbfd6e6508cb4c5cb5bb","abstract_canon_sha256":"984da16ad9509f8ab019ca600a5a3a9f0ef0c0ec7e37841da79efbf644066fe3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:50.943952Z","signature_b64":"9BXwXLmyLEu/DzQCAag1gqc9gtYeRdFbe4VRQ8J5IDaaDoQRpn/qTEvJLhcvMWRxrnKyfGmV8EV7KWzG9UDYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26ea5b24e4438b7c751f81198a3c3952387fce5a850334b4cc9bda3aeb2ec932","last_reissued_at":"2026-07-05T03:35:50.943466Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:50.943466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViDT: An Efficient and Effective Fully Transformer-based Object Detector","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Byeongho Heo, Deqing Sun, Dongyoon Han, Hwanjun Song, Ming-Hsuan Yang, Sanghyuk Chun, Varun Jampani, Wonjae Kim","submitted_at":"2021-10-08T06:32:05Z","abstract_excerpt":"Transformers are transforming the landscape of computer vision, especially for recognition tasks. Detection transformers are the first fully end-to-end learning systems for object detection, while vision transformers are the first fully transformer-based architecture for image classification. In this paper, we integrate Vision and Detection Transformers (ViDT) to build an effective and efficient object detector. ViDT introduces a reconfigured attention module to extend the recent Swin Transformer to be a standalone object detector, followed by a computationally efficient transformer decoder th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03921","kind":"arxiv","version":2},"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/2110.03921/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":"2110.03921","created_at":"2026-07-05T03:35:50.943527+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.03921v2","created_at":"2026-07-05T03:35:50.943527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03921","created_at":"2026-07-05T03:35:50.943527+00:00"},{"alias_kind":"pith_short_12","alias_value":"E3VFWJHEIOFX","created_at":"2026-07-05T03:35:50.943527+00:00"},{"alias_kind":"pith_short_16","alias_value":"E3VFWJHEIOFXY5I7","created_at":"2026-07-05T03:35:50.943527+00:00"},{"alias_kind":"pith_short_8","alias_value":"E3VFWJHE","created_at":"2026-07-05T03:35:50.943527+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24020","citing_title":"Machine Intelligence that Understands Visual and Linguistic Information and Interacts with Humans and Environments","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2412.06341","citing_title":"Visual Accommodation: Rethinking Image Scale as a Learnable Variable for Object Detection","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E3VFWJHEIOFXY5I7QEMYUPBZKI","json":"https://pith.science/pith/E3VFWJHEIOFXY5I7QEMYUPBZKI.json","graph_json":"https://pith.science/api/pith-number/E3VFWJHEIOFXY5I7QEMYUPBZKI/graph.json","events_json":"https://pith.science/api/pith-number/E3VFWJHEIOFXY5I7QEMYUPBZKI/events.json","paper":"https://pith.science/paper/E3VFWJHE"},"agent_actions":{"view_html":"https://pith.science/pith/E3VFWJHEIOFXY5I7QEMYUPBZKI","download_json":"https://pith.science/pith/E3VFWJHEIOFXY5I7QEMYUPBZKI.json","view_paper":"https://pith.science/paper/E3VFWJHE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.03921&json=true","fetch_graph":"https://pith.science/api/pith-number/E3VFWJHEIOFXY5I7QEMYUPBZKI/graph.json","fetch_events":"https://pith.science/api/pith-number/E3VFWJHEIOFXY5I7QEMYUPBZKI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E3VFWJHEIOFXY5I7QEMYUPBZKI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E3VFWJHEIOFXY5I7QEMYUPBZKI/action/storage_attestation","attest_author":"https://pith.science/pith/E3VFWJHEIOFXY5I7QEMYUPBZKI/action/author_attestation","sign_citation":"https://pith.science/pith/E3VFWJHEIOFXY5I7QEMYUPBZKI/action/citation_signature","submit_replication":"https://pith.science/pith/E3VFWJHEIOFXY5I7QEMYUPBZKI/action/replication_record"}},"created_at":"2026-07-05T03:35:50.943527+00:00","updated_at":"2026-07-05T03:35:50.943527+00:00"}