{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:R45EVLB3NOMKA6VAEPCQIGSLIP","short_pith_number":"pith:R45EVLB3","schema_version":"1.0","canonical_sha256":"8f3a4aac3b6b98a07aa023c5041a4b43ed9946a5db95f9040928f0d12982afd5","source":{"kind":"arxiv","id":"2006.03776","version":1},"attestation_state":"computed","paper":{"title":"MAGNet: Multi-Region Attention-Assisted Grounding of Natural Language Queries at Phrase Level","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Amar Shrestha, Haowen Fang, Krittaphat Pugdeethosapol, Qinru Qiu","submitted_at":"2020-06-06T04:14:15Z","abstract_excerpt":"Grounding free-form textual queries necessitates an understanding of these textual phrases and its relation to the visual cues to reliably reason about the described locations. Spatial attention networks are known to learn this relationship and focus its gaze on salient objects in the image. Thus, we propose to utilize spatial attention networks for image-level visual-textual fusion preserving local (word) and global (phrase) information to refine region proposals with an in-network Region Proposal Network (RPN) and detect single or multiple regions for a phrase query. We focus only on the phr"},"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":"2006.03776","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-06T04:14:15Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"065e2d35bea3a32711ef95c1afe38627e898e7c9cbfc02836381b20b0de8c7c5","abstract_canon_sha256":"12a93f9430a99a08c48a433d45406f82af5719999362991280b457f552f8c8bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:08:32.962759Z","signature_b64":"Qf/1WyvKNyh3dQCroc3XFQpYZZXein9LhYA4z1y7LR+tXh7AtDY8Z+HMf109yqsXtffn4wmE6zyyat//9ILgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f3a4aac3b6b98a07aa023c5041a4b43ed9946a5db95f9040928f0d12982afd5","last_reissued_at":"2026-07-05T01:08:32.962385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:08:32.962385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAGNet: Multi-Region Attention-Assisted Grounding of Natural Language Queries at Phrase Level","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Amar Shrestha, Haowen Fang, Krittaphat Pugdeethosapol, Qinru Qiu","submitted_at":"2020-06-06T04:14:15Z","abstract_excerpt":"Grounding free-form textual queries necessitates an understanding of these textual phrases and its relation to the visual cues to reliably reason about the described locations. Spatial attention networks are known to learn this relationship and focus its gaze on salient objects in the image. Thus, we propose to utilize spatial attention networks for image-level visual-textual fusion preserving local (word) and global (phrase) information to refine region proposals with an in-network Region Proposal Network (RPN) and detect single or multiple regions for a phrase query. We focus only on the phr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.03776","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/2006.03776/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":"2006.03776","created_at":"2026-07-05T01:08:32.962445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.03776v1","created_at":"2026-07-05T01:08:32.962445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.03776","created_at":"2026-07-05T01:08:32.962445+00:00"},{"alias_kind":"pith_short_12","alias_value":"R45EVLB3NOMK","created_at":"2026-07-05T01:08:32.962445+00:00"},{"alias_kind":"pith_short_16","alias_value":"R45EVLB3NOMKA6VA","created_at":"2026-07-05T01:08:32.962445+00:00"},{"alias_kind":"pith_short_8","alias_value":"R45EVLB3","created_at":"2026-07-05T01:08:32.962445+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/R45EVLB3NOMKA6VAEPCQIGSLIP","json":"https://pith.science/pith/R45EVLB3NOMKA6VAEPCQIGSLIP.json","graph_json":"https://pith.science/api/pith-number/R45EVLB3NOMKA6VAEPCQIGSLIP/graph.json","events_json":"https://pith.science/api/pith-number/R45EVLB3NOMKA6VAEPCQIGSLIP/events.json","paper":"https://pith.science/paper/R45EVLB3"},"agent_actions":{"view_html":"https://pith.science/pith/R45EVLB3NOMKA6VAEPCQIGSLIP","download_json":"https://pith.science/pith/R45EVLB3NOMKA6VAEPCQIGSLIP.json","view_paper":"https://pith.science/paper/R45EVLB3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.03776&json=true","fetch_graph":"https://pith.science/api/pith-number/R45EVLB3NOMKA6VAEPCQIGSLIP/graph.json","fetch_events":"https://pith.science/api/pith-number/R45EVLB3NOMKA6VAEPCQIGSLIP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R45EVLB3NOMKA6VAEPCQIGSLIP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R45EVLB3NOMKA6VAEPCQIGSLIP/action/storage_attestation","attest_author":"https://pith.science/pith/R45EVLB3NOMKA6VAEPCQIGSLIP/action/author_attestation","sign_citation":"https://pith.science/pith/R45EVLB3NOMKA6VAEPCQIGSLIP/action/citation_signature","submit_replication":"https://pith.science/pith/R45EVLB3NOMKA6VAEPCQIGSLIP/action/replication_record"}},"created_at":"2026-07-05T01:08:32.962445+00:00","updated_at":"2026-07-05T01:08:32.962445+00:00"}