{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EE5HIXTF5UA3AZAUZEOFJBEIGZ","short_pith_number":"pith:EE5HIXTF","schema_version":"1.0","canonical_sha256":"213a745e65ed01b06414c91c5484883644e53a4510ff38976978d00e713748bd","source":{"kind":"arxiv","id":"2304.09854","version":4},"attestation_state":"computed","paper":{"title":"Transformer-Based Visual Segmentation: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Guangliang Cheng, Haobo Yuan, Henghui Ding, Jiangmiao Pang, Kai Chen, Wenwei Zhang, Xiangtai Li, Ziwei Liu","submitted_at":"2023-04-19T17:59:02Z","abstract_excerpt":"Visual segmentation seeks to partition images, video frames, or point clouds into multiple segments or groups. This technique has numerous real-world applications, such as autonomous driving, image editing, robot sensing, and medical analysis. Over the past decade, deep learning-based methods have made remarkable strides in this area. Recently, transformers, a type of neural network based on self-attention originally designed for natural language processing, have considerably surpassed previous convolutional or recurrent approaches in various vision processing tasks. Specifically, vision trans"},"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":"2304.09854","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-19T17:59:02Z","cross_cats_sorted":[],"title_canon_sha256":"a895a199454647f53e94f5d1a9b0bc12d447f04629bf42f61ffbcf951d5aa002","abstract_canon_sha256":"40e761c15e68b2a7d6e5650ec63feb5fcc249154220d3c49900a7e3d53caf621"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:41.484054Z","signature_b64":"vfZPVrDKWpDgKu38z6FtaQCDqWwOa4gDBUwIm6BC7Y3qrRdmacVGe2XlKJiK5QD59OA6sP/nYjPnS9f87RiCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"213a745e65ed01b06414c91c5484883644e53a4510ff38976978d00e713748bd","last_reissued_at":"2026-07-05T08:51:41.483586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:41.483586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformer-Based Visual Segmentation: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Guangliang Cheng, Haobo Yuan, Henghui Ding, Jiangmiao Pang, Kai Chen, Wenwei Zhang, Xiangtai Li, Ziwei Liu","submitted_at":"2023-04-19T17:59:02Z","abstract_excerpt":"Visual segmentation seeks to partition images, video frames, or point clouds into multiple segments or groups. This technique has numerous real-world applications, such as autonomous driving, image editing, robot sensing, and medical analysis. Over the past decade, deep learning-based methods have made remarkable strides in this area. Recently, transformers, a type of neural network based on self-attention originally designed for natural language processing, have considerably surpassed previous convolutional or recurrent approaches in various vision processing tasks. Specifically, vision trans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.09854","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/2304.09854/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":"2304.09854","created_at":"2026-07-05T08:51:41.483645+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.09854v4","created_at":"2026-07-05T08:51:41.483645+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.09854","created_at":"2026-07-05T08:51:41.483645+00:00"},{"alias_kind":"pith_short_12","alias_value":"EE5HIXTF5UA3","created_at":"2026-07-05T08:51:41.483645+00:00"},{"alias_kind":"pith_short_16","alias_value":"EE5HIXTF5UA3AZAU","created_at":"2026-07-05T08:51:41.483645+00:00"},{"alias_kind":"pith_short_8","alias_value":"EE5HIXTF","created_at":"2026-07-05T08:51:41.483645+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.02286","citing_title":"Attention-Mamba: A Mamba-Enhanced Multi-Scale Parallel Inference Network for Medical Image Segmentation","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2412.07160","citing_title":"Motion-aware Contrastive Learning for Temporal Panoptic Scene Graph Generation","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EE5HIXTF5UA3AZAUZEOFJBEIGZ","json":"https://pith.science/pith/EE5HIXTF5UA3AZAUZEOFJBEIGZ.json","graph_json":"https://pith.science/api/pith-number/EE5HIXTF5UA3AZAUZEOFJBEIGZ/graph.json","events_json":"https://pith.science/api/pith-number/EE5HIXTF5UA3AZAUZEOFJBEIGZ/events.json","paper":"https://pith.science/paper/EE5HIXTF"},"agent_actions":{"view_html":"https://pith.science/pith/EE5HIXTF5UA3AZAUZEOFJBEIGZ","download_json":"https://pith.science/pith/EE5HIXTF5UA3AZAUZEOFJBEIGZ.json","view_paper":"https://pith.science/paper/EE5HIXTF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.09854&json=true","fetch_graph":"https://pith.science/api/pith-number/EE5HIXTF5UA3AZAUZEOFJBEIGZ/graph.json","fetch_events":"https://pith.science/api/pith-number/EE5HIXTF5UA3AZAUZEOFJBEIGZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EE5HIXTF5UA3AZAUZEOFJBEIGZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EE5HIXTF5UA3AZAUZEOFJBEIGZ/action/storage_attestation","attest_author":"https://pith.science/pith/EE5HIXTF5UA3AZAUZEOFJBEIGZ/action/author_attestation","sign_citation":"https://pith.science/pith/EE5HIXTF5UA3AZAUZEOFJBEIGZ/action/citation_signature","submit_replication":"https://pith.science/pith/EE5HIXTF5UA3AZAUZEOFJBEIGZ/action/replication_record"}},"created_at":"2026-07-05T08:51:41.483645+00:00","updated_at":"2026-07-05T08:51:41.483645+00:00"}