{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:PMZIHG55VUU46TTLRC67NKSIEV","short_pith_number":"pith:PMZIHG55","schema_version":"1.0","canonical_sha256":"7b32839bbdad29cf4e6b88bdf6aa482552a4049165f6d00694f239656e3af26e","source":{"kind":"arxiv","id":"1707.00243","version":2},"attestation_state":"computed","paper":{"title":"Deep GrabCut for Object Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brian Price, Jimei Yang, Ning Xu, Scott Cohen, Thomas Huang","submitted_at":"2017-07-02T05:53:49Z","abstract_excerpt":"Most previous bounding-box-based segmentation methods assume the bounding box tightly covers the object of interest. However it is common that a rectangle input could be too large or too small. In this paper, we propose a novel segmentation approach that uses a rectangle as a soft constraint by transforming it into an Euclidean distance map. A convolutional encoder-decoder network is trained end-to-end by concatenating images with these distance maps as inputs and predicting the object masks as outputs. Our approach gets accurate segmentation results given sloppy rectangles while being general"},"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":"1707.00243","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-02T05:53:49Z","cross_cats_sorted":[],"title_canon_sha256":"c29da47c7053aadd6012442e6eec3a8ce352bd1459f9a23ac869262ceeec3db2","abstract_canon_sha256":"cdda905bb63b815ce84d48ad2da8d38a3e3777fcf50521f72a921ccb271d4c4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:17.259437Z","signature_b64":"BcPZjIqim+TVelEUneNmQd6RR/Hv5iEd927zQGeEUsfgEOX4yZY7I2zSe6NxPm21pm+ONtROWxj3tZv/VM3kCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b32839bbdad29cf4e6b88bdf6aa482552a4049165f6d00694f239656e3af26e","last_reissued_at":"2026-05-18T00:40:17.258675Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:17.258675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep GrabCut for Object Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brian Price, Jimei Yang, Ning Xu, Scott Cohen, Thomas Huang","submitted_at":"2017-07-02T05:53:49Z","abstract_excerpt":"Most previous bounding-box-based segmentation methods assume the bounding box tightly covers the object of interest. However it is common that a rectangle input could be too large or too small. In this paper, we propose a novel segmentation approach that uses a rectangle as a soft constraint by transforming it into an Euclidean distance map. A convolutional encoder-decoder network is trained end-to-end by concatenating images with these distance maps as inputs and predicting the object masks as outputs. Our approach gets accurate segmentation results given sloppy rectangles while being general"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.00243","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":""},"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":"1707.00243","created_at":"2026-05-18T00:40:17.258786+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.00243v2","created_at":"2026-05-18T00:40:17.258786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.00243","created_at":"2026-05-18T00:40:17.258786+00:00"},{"alias_kind":"pith_short_12","alias_value":"PMZIHG55VUU4","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"PMZIHG55VUU46TTL","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"PMZIHG55","created_at":"2026-05-18T12:31:37.085036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2409.06490","citing_title":"UAVDB: Point-Guided Masks for UAV Detection and Segmentation","ref_index":76,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PMZIHG55VUU46TTLRC67NKSIEV","json":"https://pith.science/pith/PMZIHG55VUU46TTLRC67NKSIEV.json","graph_json":"https://pith.science/api/pith-number/PMZIHG55VUU46TTLRC67NKSIEV/graph.json","events_json":"https://pith.science/api/pith-number/PMZIHG55VUU46TTLRC67NKSIEV/events.json","paper":"https://pith.science/paper/PMZIHG55"},"agent_actions":{"view_html":"https://pith.science/pith/PMZIHG55VUU46TTLRC67NKSIEV","download_json":"https://pith.science/pith/PMZIHG55VUU46TTLRC67NKSIEV.json","view_paper":"https://pith.science/paper/PMZIHG55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.00243&json=true","fetch_graph":"https://pith.science/api/pith-number/PMZIHG55VUU46TTLRC67NKSIEV/graph.json","fetch_events":"https://pith.science/api/pith-number/PMZIHG55VUU46TTLRC67NKSIEV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PMZIHG55VUU46TTLRC67NKSIEV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PMZIHG55VUU46TTLRC67NKSIEV/action/storage_attestation","attest_author":"https://pith.science/pith/PMZIHG55VUU46TTLRC67NKSIEV/action/author_attestation","sign_citation":"https://pith.science/pith/PMZIHG55VUU46TTLRC67NKSIEV/action/citation_signature","submit_replication":"https://pith.science/pith/PMZIHG55VUU46TTLRC67NKSIEV/action/replication_record"}},"created_at":"2026-05-18T00:40:17.258786+00:00","updated_at":"2026-05-18T00:40:17.258786+00:00"}