{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ANCXLY72XAZ45FLS57WAYOTKJ7","short_pith_number":"pith:ANCXLY72","schema_version":"1.0","canonical_sha256":"034575e3fab833ce9572efec0c3a6a4fd957fd19d5f5a9d2a8928db0cd4993dd","source":{"kind":"arxiv","id":"2012.12556","version":6},"attestation_state":"computed","paper":{"title":"A Survey on Visual Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"An Xiao, Chunjing Xu, Dacheng Tao, Hanting Chen, Jianyuan Guo, Kai Han, Xinghao Chen, Yehui Tang, Yiman Zhang, Yixing Xu, Yunhe Wang, Zhaohui Yang, Zhenhua Liu","submitted_at":"2020-12-23T09:37:54Z","abstract_excerpt":"Transformer, first applied to the field of natural language processing, is a type of deep neural network mainly based on the self-attention mechanism. Thanks to its strong representation capabilities, researchers are looking at ways to apply transformer to computer vision tasks. In a variety of visual benchmarks, transformer-based models perform similar to or better than other types of networks such as convolutional and recurrent neural networks. Given its high performance and less need for vision-specific inductive bias, transformer is receiving more and more attention from the computer visio"},"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":"2012.12556","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-23T09:37:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d9e99683e83d96ec7762e3c13db9c15ab85fe14d32327709891c2afd9efc4b6f","abstract_canon_sha256":"6c8beb915d94ef1676340e6adeb4d8fd7d27b684e54e3b0b5f71322ba90831f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:50.428691Z","signature_b64":"q6PLi7m57gS3R1+VA4bJ4q92zQKeI39HMjyhQTEfqFLsj7llFgS0QfeGMn08WlkVpR8uUdUgBAewycB0CLYwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"034575e3fab833ce9572efec0c3a6a4fd957fd19d5f5a9d2a8928db0cd4993dd","last_reissued_at":"2026-07-05T06:28:50.428282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:50.428282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Visual Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"An Xiao, Chunjing Xu, Dacheng Tao, Hanting Chen, Jianyuan Guo, Kai Han, Xinghao Chen, Yehui Tang, Yiman Zhang, Yixing Xu, Yunhe Wang, Zhaohui Yang, Zhenhua Liu","submitted_at":"2020-12-23T09:37:54Z","abstract_excerpt":"Transformer, first applied to the field of natural language processing, is a type of deep neural network mainly based on the self-attention mechanism. Thanks to its strong representation capabilities, researchers are looking at ways to apply transformer to computer vision tasks. In a variety of visual benchmarks, transformer-based models perform similar to or better than other types of networks such as convolutional and recurrent neural networks. Given its high performance and less need for vision-specific inductive bias, transformer is receiving more and more attention from the computer visio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.12556","kind":"arxiv","version":6},"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/2012.12556/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":"2012.12556","created_at":"2026-07-05T06:28:50.428340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.12556v6","created_at":"2026-07-05T06:28:50.428340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.12556","created_at":"2026-07-05T06:28:50.428340+00:00"},{"alias_kind":"pith_short_12","alias_value":"ANCXLY72XAZ4","created_at":"2026-07-05T06:28:50.428340+00:00"},{"alias_kind":"pith_short_16","alias_value":"ANCXLY72XAZ45FLS","created_at":"2026-07-05T06:28:50.428340+00:00"},{"alias_kind":"pith_short_8","alias_value":"ANCXLY72","created_at":"2026-07-05T06:28:50.428340+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18401","citing_title":"Recent Deep Learning in Crowd Behaviour Analysis: A Brief Review","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ANCXLY72XAZ45FLS57WAYOTKJ7","json":"https://pith.science/pith/ANCXLY72XAZ45FLS57WAYOTKJ7.json","graph_json":"https://pith.science/api/pith-number/ANCXLY72XAZ45FLS57WAYOTKJ7/graph.json","events_json":"https://pith.science/api/pith-number/ANCXLY72XAZ45FLS57WAYOTKJ7/events.json","paper":"https://pith.science/paper/ANCXLY72"},"agent_actions":{"view_html":"https://pith.science/pith/ANCXLY72XAZ45FLS57WAYOTKJ7","download_json":"https://pith.science/pith/ANCXLY72XAZ45FLS57WAYOTKJ7.json","view_paper":"https://pith.science/paper/ANCXLY72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.12556&json=true","fetch_graph":"https://pith.science/api/pith-number/ANCXLY72XAZ45FLS57WAYOTKJ7/graph.json","fetch_events":"https://pith.science/api/pith-number/ANCXLY72XAZ45FLS57WAYOTKJ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ANCXLY72XAZ45FLS57WAYOTKJ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ANCXLY72XAZ45FLS57WAYOTKJ7/action/storage_attestation","attest_author":"https://pith.science/pith/ANCXLY72XAZ45FLS57WAYOTKJ7/action/author_attestation","sign_citation":"https://pith.science/pith/ANCXLY72XAZ45FLS57WAYOTKJ7/action/citation_signature","submit_replication":"https://pith.science/pith/ANCXLY72XAZ45FLS57WAYOTKJ7/action/replication_record"}},"created_at":"2026-07-05T06:28:50.428340+00:00","updated_at":"2026-07-05T06:28:50.428340+00:00"}