{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NM2WLTGA5T4X2LXFW3F4NAQOW7","short_pith_number":"pith:NM2WLTGA","schema_version":"1.0","canonical_sha256":"6b3565ccc0ecf97d2ee5b6cbc6820eb7d5af297a1298b6851f70def71ed26a19","source":{"kind":"arxiv","id":"2107.12292","version":1},"attestation_state":"computed","paper":{"title":"Contextual Transformer Networks for Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Tao Mei, Ting Yao, Yehao Li, Yingwei Pan","submitted_at":"2021-07-26T16:00:21Z","abstract_excerpt":"Transformer with self-attention has led to the revolutionizing of natural language processing field, and recently inspires the emergence of Transformer-style architecture design with competitive results in numerous computer vision tasks. Nevertheless, most of existing designs directly employ self-attention over a 2D feature map to obtain the attention matrix based on pairs of isolated queries and keys at each spatial location, but leave the rich contexts among neighbor keys under-exploited. In this work, we design a novel Transformer-style module, i.e., Contextual Transformer (CoT) block, for "},"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":"2107.12292","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-26T16:00:21Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"824dc9e4af24f40fee4eca9baea0d9c886a0bcc7452ca39f4b7fab0698254cd2","abstract_canon_sha256":"44565285a3d104a5f79ecae452fcc9b3214f25b90672fdda1fd3070bb519cce0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:42.281043Z","signature_b64":"sQrZLyAJh4T1YP6K4CGF0WFffvLZOZgoG17MUonhQ4pW9mGG7eUKP1/3CXN7K9fYuBeUfooXv10o8cfAM6+JAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b3565ccc0ecf97d2ee5b6cbc6820eb7d5af297a1298b6851f70def71ed26a19","last_reissued_at":"2026-07-05T03:00:42.280610Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:42.280610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contextual Transformer Networks for Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Tao Mei, Ting Yao, Yehao Li, Yingwei Pan","submitted_at":"2021-07-26T16:00:21Z","abstract_excerpt":"Transformer with self-attention has led to the revolutionizing of natural language processing field, and recently inspires the emergence of Transformer-style architecture design with competitive results in numerous computer vision tasks. Nevertheless, most of existing designs directly employ self-attention over a 2D feature map to obtain the attention matrix based on pairs of isolated queries and keys at each spatial location, but leave the rich contexts among neighbor keys under-exploited. In this work, we design a novel Transformer-style module, i.e., Contextual Transformer (CoT) block, for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.12292","kind":"arxiv","version":1},"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/2107.12292/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":"2107.12292","created_at":"2026-07-05T03:00:42.280675+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.12292v1","created_at":"2026-07-05T03:00:42.280675+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.12292","created_at":"2026-07-05T03:00:42.280675+00:00"},{"alias_kind":"pith_short_12","alias_value":"NM2WLTGA5T4X","created_at":"2026-07-05T03:00:42.280675+00:00"},{"alias_kind":"pith_short_16","alias_value":"NM2WLTGA5T4X2LXF","created_at":"2026-07-05T03:00:42.280675+00:00"},{"alias_kind":"pith_short_8","alias_value":"NM2WLTGA","created_at":"2026-07-05T03:00:42.280675+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/NM2WLTGA5T4X2LXFW3F4NAQOW7","json":"https://pith.science/pith/NM2WLTGA5T4X2LXFW3F4NAQOW7.json","graph_json":"https://pith.science/api/pith-number/NM2WLTGA5T4X2LXFW3F4NAQOW7/graph.json","events_json":"https://pith.science/api/pith-number/NM2WLTGA5T4X2LXFW3F4NAQOW7/events.json","paper":"https://pith.science/paper/NM2WLTGA"},"agent_actions":{"view_html":"https://pith.science/pith/NM2WLTGA5T4X2LXFW3F4NAQOW7","download_json":"https://pith.science/pith/NM2WLTGA5T4X2LXFW3F4NAQOW7.json","view_paper":"https://pith.science/paper/NM2WLTGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.12292&json=true","fetch_graph":"https://pith.science/api/pith-number/NM2WLTGA5T4X2LXFW3F4NAQOW7/graph.json","fetch_events":"https://pith.science/api/pith-number/NM2WLTGA5T4X2LXFW3F4NAQOW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NM2WLTGA5T4X2LXFW3F4NAQOW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NM2WLTGA5T4X2LXFW3F4NAQOW7/action/storage_attestation","attest_author":"https://pith.science/pith/NM2WLTGA5T4X2LXFW3F4NAQOW7/action/author_attestation","sign_citation":"https://pith.science/pith/NM2WLTGA5T4X2LXFW3F4NAQOW7/action/citation_signature","submit_replication":"https://pith.science/pith/NM2WLTGA5T4X2LXFW3F4NAQOW7/action/replication_record"}},"created_at":"2026-07-05T03:00:42.280675+00:00","updated_at":"2026-07-05T03:00:42.280675+00:00"}