{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JNFGWTUSLC5JSIS3GVXBHX7JVW","short_pith_number":"pith:JNFGWTUS","schema_version":"1.0","canonical_sha256":"4b4a6b4e9258ba99225b356e13dfe9ada7d07e691b27c22e44c16126d7604d0a","source":{"kind":"arxiv","id":"2405.04009","version":1},"attestation_state":"computed","paper":{"title":"Structured Click Control in Transformer-based Interactive Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Feng Wu, Long Xu, Rui Huang, Shiwu Lai, Yongquan Chen","submitted_at":"2024-05-07T04:57:25Z","abstract_excerpt":"Click-point-based interactive segmentation has received widespread attention due to its efficiency. However, it's hard for existing algorithms to obtain precise and robust responses after multiple clicks. In this case, the segmentation results tend to have little change or are even worse than before. To improve the robustness of the response, we propose a structured click intent model based on graph neural networks, which adaptively obtains graph nodes via the global similarity of user-clicked Transformer tokens. Then the graph nodes will be aggregated to obtain structured interaction features"},"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":"2405.04009","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-07T04:57:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"988aa4325ca06939197c2c24d9f4dc80efbbb46235e58b1d55ebb7de11b6c078","abstract_canon_sha256":"78a1ce35d9494875714fd9cf51760c9e26d144cce7b7a793ad9bbc12113e6c45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:30.447023Z","signature_b64":"PGIf0dPj0uiGXnUykeH/k7kSVealXP4BzeUkaXAVI51/jodBL7QqKqvN4u5jVRY7XPHEIZFyQRdXz5o4YH3UDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b4a6b4e9258ba99225b356e13dfe9ada7d07e691b27c22e44c16126d7604d0a","last_reissued_at":"2026-07-05T08:16:30.446535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:30.446535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured Click Control in Transformer-based Interactive Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Feng Wu, Long Xu, Rui Huang, Shiwu Lai, Yongquan Chen","submitted_at":"2024-05-07T04:57:25Z","abstract_excerpt":"Click-point-based interactive segmentation has received widespread attention due to its efficiency. However, it's hard for existing algorithms to obtain precise and robust responses after multiple clicks. In this case, the segmentation results tend to have little change or are even worse than before. To improve the robustness of the response, we propose a structured click intent model based on graph neural networks, which adaptively obtains graph nodes via the global similarity of user-clicked Transformer tokens. Then the graph nodes will be aggregated to obtain structured interaction features"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04009","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/2405.04009/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":"2405.04009","created_at":"2026-07-05T08:16:30.446606+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.04009v1","created_at":"2026-07-05T08:16:30.446606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04009","created_at":"2026-07-05T08:16:30.446606+00:00"},{"alias_kind":"pith_short_12","alias_value":"JNFGWTUSLC5J","created_at":"2026-07-05T08:16:30.446606+00:00"},{"alias_kind":"pith_short_16","alias_value":"JNFGWTUSLC5JSIS3","created_at":"2026-07-05T08:16:30.446606+00:00"},{"alias_kind":"pith_short_8","alias_value":"JNFGWTUS","created_at":"2026-07-05T08:16:30.446606+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09612","citing_title":"Inter2Former: Dynamic Hybrid Attention for Efficient High-Precision Interactive","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JNFGWTUSLC5JSIS3GVXBHX7JVW","json":"https://pith.science/pith/JNFGWTUSLC5JSIS3GVXBHX7JVW.json","graph_json":"https://pith.science/api/pith-number/JNFGWTUSLC5JSIS3GVXBHX7JVW/graph.json","events_json":"https://pith.science/api/pith-number/JNFGWTUSLC5JSIS3GVXBHX7JVW/events.json","paper":"https://pith.science/paper/JNFGWTUS"},"agent_actions":{"view_html":"https://pith.science/pith/JNFGWTUSLC5JSIS3GVXBHX7JVW","download_json":"https://pith.science/pith/JNFGWTUSLC5JSIS3GVXBHX7JVW.json","view_paper":"https://pith.science/paper/JNFGWTUS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.04009&json=true","fetch_graph":"https://pith.science/api/pith-number/JNFGWTUSLC5JSIS3GVXBHX7JVW/graph.json","fetch_events":"https://pith.science/api/pith-number/JNFGWTUSLC5JSIS3GVXBHX7JVW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JNFGWTUSLC5JSIS3GVXBHX7JVW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JNFGWTUSLC5JSIS3GVXBHX7JVW/action/storage_attestation","attest_author":"https://pith.science/pith/JNFGWTUSLC5JSIS3GVXBHX7JVW/action/author_attestation","sign_citation":"https://pith.science/pith/JNFGWTUSLC5JSIS3GVXBHX7JVW/action/citation_signature","submit_replication":"https://pith.science/pith/JNFGWTUSLC5JSIS3GVXBHX7JVW/action/replication_record"}},"created_at":"2026-07-05T08:16:30.446606+00:00","updated_at":"2026-07-05T08:16:30.446606+00:00"}