{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:NMIMVWUX3JF7FEPBPMNJWG4UNU","short_pith_number":"pith:NMIMVWUX","schema_version":"1.0","canonical_sha256":"6b10cada97da4bf291e17b1a9b1b946d0bb14e066b8430c9dcb6101c4728e024","source":{"kind":"arxiv","id":"1707.08364","version":1},"attestation_state":"computed","paper":{"title":"Deep Interactive Region Segmentation and Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Sharifi Boroujerdi, Maryam Khanian, Michael Breuss","submitted_at":"2017-07-26T10:40:33Z","abstract_excerpt":"With recent innovations in dense image captioning, it is now possible to describe every object of the scene with a caption while objects are determined by bounding boxes. However, interpretation of such an output is not trivial due to the existence of many overlapping bounding boxes. Furthermore, in current captioning frameworks, the user is not able to involve personal preferences to exclude out of interest areas. In this paper, we propose a novel hybrid deep learning architecture for interactive region segmentation and captioning where the user is able to specify an arbitrary region of the i"},"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":"1707.08364","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-26T10:40:33Z","cross_cats_sorted":[],"title_canon_sha256":"90ba29ea97f5f31edf0c6db095160db12e1594c04207b67460d7489987f93e20","abstract_canon_sha256":"ac897ffde16ec5ee3b5785c27c1ff9c1c5a54d622f8e7c5c69adf5529f84a7de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:24.420281Z","signature_b64":"4WDafMOXPWFW02yL2VQvtgo5ey34sf/Tb44gfZOk+HWEWtM4QhxEAN6ZhSYnneGbwCFpOggLhH2B5KPg6Y6oBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b10cada97da4bf291e17b1a9b1b946d0bb14e066b8430c9dcb6101c4728e024","last_reissued_at":"2026-05-18T00:39:24.419568Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:24.419568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Interactive Region Segmentation and Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Sharifi Boroujerdi, Maryam Khanian, Michael Breuss","submitted_at":"2017-07-26T10:40:33Z","abstract_excerpt":"With recent innovations in dense image captioning, it is now possible to describe every object of the scene with a caption while objects are determined by bounding boxes. However, interpretation of such an output is not trivial due to the existence of many overlapping bounding boxes. Furthermore, in current captioning frameworks, the user is not able to involve personal preferences to exclude out of interest areas. In this paper, we propose a novel hybrid deep learning architecture for interactive region segmentation and captioning where the user is able to specify an arbitrary region of the i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.08364","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":""},"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":"1707.08364","created_at":"2026-05-18T00:39:24.419681+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.08364v1","created_at":"2026-05-18T00:39:24.419681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.08364","created_at":"2026-05-18T00:39:24.419681+00:00"},{"alias_kind":"pith_short_12","alias_value":"NMIMVWUX3JF7","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"NMIMVWUX3JF7FEPB","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"NMIMVWUX","created_at":"2026-05-18T12:31:34.259226+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/NMIMVWUX3JF7FEPBPMNJWG4UNU","json":"https://pith.science/pith/NMIMVWUX3JF7FEPBPMNJWG4UNU.json","graph_json":"https://pith.science/api/pith-number/NMIMVWUX3JF7FEPBPMNJWG4UNU/graph.json","events_json":"https://pith.science/api/pith-number/NMIMVWUX3JF7FEPBPMNJWG4UNU/events.json","paper":"https://pith.science/paper/NMIMVWUX"},"agent_actions":{"view_html":"https://pith.science/pith/NMIMVWUX3JF7FEPBPMNJWG4UNU","download_json":"https://pith.science/pith/NMIMVWUX3JF7FEPBPMNJWG4UNU.json","view_paper":"https://pith.science/paper/NMIMVWUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.08364&json=true","fetch_graph":"https://pith.science/api/pith-number/NMIMVWUX3JF7FEPBPMNJWG4UNU/graph.json","fetch_events":"https://pith.science/api/pith-number/NMIMVWUX3JF7FEPBPMNJWG4UNU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NMIMVWUX3JF7FEPBPMNJWG4UNU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NMIMVWUX3JF7FEPBPMNJWG4UNU/action/storage_attestation","attest_author":"https://pith.science/pith/NMIMVWUX3JF7FEPBPMNJWG4UNU/action/author_attestation","sign_citation":"https://pith.science/pith/NMIMVWUX3JF7FEPBPMNJWG4UNU/action/citation_signature","submit_replication":"https://pith.science/pith/NMIMVWUX3JF7FEPBPMNJWG4UNU/action/replication_record"}},"created_at":"2026-05-18T00:39:24.419681+00:00","updated_at":"2026-05-18T00:39:24.419681+00:00"}