{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LOU46R7P5BFOINES6XGDJYY4NV","short_pith_number":"pith:LOU46R7P","schema_version":"1.0","canonical_sha256":"5ba9cf47efe84ae43492f5cc34e31c6d6b184f87e63fe10472ccec72acd48c11","source":{"kind":"arxiv","id":"2204.02574","version":2},"attestation_state":"computed","paper":{"title":"FocalClick: Towards Practical Interactive Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donglian Qi, Hengshuang Zhao, Manni Duan, Xi Chen, Yilei Zhang, Zhiyan Zhao","submitted_at":"2022-04-06T04:32:01Z","abstract_excerpt":"Interactive segmentation allows users to extract target masks by making positive/negative clicks. Although explored by many previous works, there is still a gap between academic approaches and industrial needs: first, existing models are not efficient enough to work on low power devices; second, they perform poorly when used to refine preexisting masks as they could not avoid destroying the correct part. FocalClick solves both issues at once by predicting and updating the mask in localized areas. For higher efficiency, we decompose the slow prediction on the entire image into two fast inferenc"},"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":"2204.02574","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-06T04:32:01Z","cross_cats_sorted":[],"title_canon_sha256":"25ae4c11f07f9c1406d9b74d17813ffff9c527ad5b2f38b5a9b7c90a0b901cc3","abstract_canon_sha256":"8f0762ee1d6e7e56fe5500b03a3431b45a3011fd10abd485454f16329b380796"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:15:15.386257Z","signature_b64":"o4/hJYG3zvPD/mui4Of96mWqfkNLi1hLx+pvPew//EENoHbiD7TfSD/UpvbJa9nAusjLjdV776rhHuYZtxHgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ba9cf47efe84ae43492f5cc34e31c6d6b184f87e63fe10472ccec72acd48c11","last_reissued_at":"2026-07-05T04:15:15.385735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:15:15.385735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FocalClick: Towards Practical Interactive Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donglian Qi, Hengshuang Zhao, Manni Duan, Xi Chen, Yilei Zhang, Zhiyan Zhao","submitted_at":"2022-04-06T04:32:01Z","abstract_excerpt":"Interactive segmentation allows users to extract target masks by making positive/negative clicks. Although explored by many previous works, there is still a gap between academic approaches and industrial needs: first, existing models are not efficient enough to work on low power devices; second, they perform poorly when used to refine preexisting masks as they could not avoid destroying the correct part. FocalClick solves both issues at once by predicting and updating the mask in localized areas. For higher efficiency, we decompose the slow prediction on the entire image into two fast inferenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02574","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/2204.02574/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":"2204.02574","created_at":"2026-07-05T04:15:15.385800+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.02574v2","created_at":"2026-07-05T04:15:15.385800+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02574","created_at":"2026-07-05T04:15:15.385800+00:00"},{"alias_kind":"pith_short_12","alias_value":"LOU46R7P5BFO","created_at":"2026-07-05T04:15:15.385800+00:00"},{"alias_kind":"pith_short_16","alias_value":"LOU46R7P5BFOINES","created_at":"2026-07-05T04:15:15.385800+00:00"},{"alias_kind":"pith_short_8","alias_value":"LOU46R7P","created_at":"2026-07-05T04:15:15.385800+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15513","citing_title":"SPA: Efficient User-Preference Alignment against Uncertainty in Medical Image Segmentation","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LOU46R7P5BFOINES6XGDJYY4NV","json":"https://pith.science/pith/LOU46R7P5BFOINES6XGDJYY4NV.json","graph_json":"https://pith.science/api/pith-number/LOU46R7P5BFOINES6XGDJYY4NV/graph.json","events_json":"https://pith.science/api/pith-number/LOU46R7P5BFOINES6XGDJYY4NV/events.json","paper":"https://pith.science/paper/LOU46R7P"},"agent_actions":{"view_html":"https://pith.science/pith/LOU46R7P5BFOINES6XGDJYY4NV","download_json":"https://pith.science/pith/LOU46R7P5BFOINES6XGDJYY4NV.json","view_paper":"https://pith.science/paper/LOU46R7P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.02574&json=true","fetch_graph":"https://pith.science/api/pith-number/LOU46R7P5BFOINES6XGDJYY4NV/graph.json","fetch_events":"https://pith.science/api/pith-number/LOU46R7P5BFOINES6XGDJYY4NV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LOU46R7P5BFOINES6XGDJYY4NV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LOU46R7P5BFOINES6XGDJYY4NV/action/storage_attestation","attest_author":"https://pith.science/pith/LOU46R7P5BFOINES6XGDJYY4NV/action/author_attestation","sign_citation":"https://pith.science/pith/LOU46R7P5BFOINES6XGDJYY4NV/action/citation_signature","submit_replication":"https://pith.science/pith/LOU46R7P5BFOINES6XGDJYY4NV/action/replication_record"}},"created_at":"2026-07-05T04:15:15.385800+00:00","updated_at":"2026-07-05T04:15:15.385800+00:00"}