{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IU7NUOZVM6HTQYGOZADTW4HVCP","short_pith_number":"pith:IU7NUOZV","schema_version":"1.0","canonical_sha256":"453eda3b35678f3860cec8073b70f513d4eaa3d21dddbe145a24eb04afb19c7d","source":{"kind":"arxiv","id":"1807.02257","version":2},"attestation_state":"computed","paper":{"title":"Dynamic Multimodal Instance Segmentation guided by natural language queries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Edgar Margffoy-Tuay, Emilio Botero, Juan C. P\\'erez, Pablo Arbel\\'aez","submitted_at":"2018-07-06T05:21:06Z","abstract_excerpt":"We address the problem of segmenting an object given a natural language expression that describes it. Current techniques tackle this task by either (\\textit{i}) directly or recursively merging linguistic and visual information in the channel dimension and then performing convolutions; or by (\\textit{ii}) mapping the expression to a space in which it can be thought of as a filter, whose response is directly related to the presence of the object at a given spatial coordinate in the image, so that a convolution can be applied to look for the object. We propose a novel method that integrates these"},"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":"1807.02257","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-07-06T05:21:06Z","cross_cats_sorted":[],"title_canon_sha256":"f3b0101971abe2216d5eb66a2df9bb8c1b3163a22cf5dacf0457446afe8aaf46","abstract_canon_sha256":"6d7f636191b30a8fc1142fd4a7c4164ff997a4afe522e5726fef84d5812c7bc5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:09.862144Z","signature_b64":"9u4YSVvohVw2RO2hrZL/g2XpeXzFJgKJVubbJ/BV/yLrxD8/tMgGPpbIAk0x2OOiNpKHH8k5eJpji6BJtR8FAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"453eda3b35678f3860cec8073b70f513d4eaa3d21dddbe145a24eb04afb19c7d","last_reissued_at":"2026-05-18T00:10:09.861647Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:09.861647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Multimodal Instance Segmentation guided by natural language queries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Edgar Margffoy-Tuay, Emilio Botero, Juan C. P\\'erez, Pablo Arbel\\'aez","submitted_at":"2018-07-06T05:21:06Z","abstract_excerpt":"We address the problem of segmenting an object given a natural language expression that describes it. Current techniques tackle this task by either (\\textit{i}) directly or recursively merging linguistic and visual information in the channel dimension and then performing convolutions; or by (\\textit{ii}) mapping the expression to a space in which it can be thought of as a filter, whose response is directly related to the presence of the object at a given spatial coordinate in the image, so that a convolution can be applied to look for the object. We propose a novel method that integrates these"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.02257","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":"1807.02257","created_at":"2026-05-18T00:10:09.861724+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.02257v2","created_at":"2026-05-18T00:10:09.861724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.02257","created_at":"2026-05-18T00:10:09.861724+00:00"},{"alias_kind":"pith_short_12","alias_value":"IU7NUOZVM6HT","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"IU7NUOZVM6HTQYGO","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"IU7NUOZV","created_at":"2026-05-18T12:32:31.084164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.02982","citing_title":"Multimodal Human-Intent Modeling for Contextual Robot-to-Human Handovers of Arbitrary Objects","ref_index":91,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IU7NUOZVM6HTQYGOZADTW4HVCP","json":"https://pith.science/pith/IU7NUOZVM6HTQYGOZADTW4HVCP.json","graph_json":"https://pith.science/api/pith-number/IU7NUOZVM6HTQYGOZADTW4HVCP/graph.json","events_json":"https://pith.science/api/pith-number/IU7NUOZVM6HTQYGOZADTW4HVCP/events.json","paper":"https://pith.science/paper/IU7NUOZV"},"agent_actions":{"view_html":"https://pith.science/pith/IU7NUOZVM6HTQYGOZADTW4HVCP","download_json":"https://pith.science/pith/IU7NUOZVM6HTQYGOZADTW4HVCP.json","view_paper":"https://pith.science/paper/IU7NUOZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.02257&json=true","fetch_graph":"https://pith.science/api/pith-number/IU7NUOZVM6HTQYGOZADTW4HVCP/graph.json","fetch_events":"https://pith.science/api/pith-number/IU7NUOZVM6HTQYGOZADTW4HVCP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IU7NUOZVM6HTQYGOZADTW4HVCP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IU7NUOZVM6HTQYGOZADTW4HVCP/action/storage_attestation","attest_author":"https://pith.science/pith/IU7NUOZVM6HTQYGOZADTW4HVCP/action/author_attestation","sign_citation":"https://pith.science/pith/IU7NUOZVM6HTQYGOZADTW4HVCP/action/citation_signature","submit_replication":"https://pith.science/pith/IU7NUOZVM6HTQYGOZADTW4HVCP/action/replication_record"}},"created_at":"2026-05-18T00:10:09.861724+00:00","updated_at":"2026-05-18T00:10:09.861724+00:00"}