{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VPTUXC2KCJTM3JZOVXDPYUDY2H","short_pith_number":"pith:VPTUXC2K","schema_version":"1.0","canonical_sha256":"abe74b8b4a1266cda72eadc6fc5078d1ec78ec2b09da363c6219ba56913b041c","source":{"kind":"arxiv","id":"2501.10692","version":1},"attestation_state":"computed","paper":{"title":"Multi-modal Fusion and Query Refinement Network for Video Moment Retrieval and Highlight Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benxiang Zhai, Sidan Du, Yifang Xu, Youyao Jia, Yunzhuo Sun, Zien Xie","submitted_at":"2025-01-18T08:09:44Z","abstract_excerpt":"Given a video and a linguistic query, video moment retrieval and highlight detection (MR&HD) aim to locate all the relevant spans while simultaneously predicting saliency scores. Most existing methods utilize RGB images as input, overlooking the inherent multi-modal visual signals like optical flow and depth. In this paper, we propose a Multi-modal Fusion and Query Refinement Network (MRNet) to learn complementary information from multi-modal cues. Specifically, we design a multi-modal fusion module to dynamically combine RGB, optical flow, and depth map. Furthermore, to simulate human underst"},"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":"2501.10692","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-18T08:09:44Z","cross_cats_sorted":[],"title_canon_sha256":"f0341ca98335a8c71d3867e9cb093a416616b485090492d5aa59c22839c2e0d6","abstract_canon_sha256":"a2737d27d7f3fbeb37efc1abf6390023f78d4f1e47e5b6364e80b05621c77b54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:32.011225Z","signature_b64":"1YZlFUayKfHGhBvnOwWYcphldq3pLNArWnjDH5CLoo09slHtneT8WIc74RbiVt5MZDwJW/ubUWZHC/Z5An4vCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abe74b8b4a1266cda72eadc6fc5078d1ec78ec2b09da363c6219ba56913b041c","last_reissued_at":"2026-07-05T10:02:32.010656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:32.010656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-modal Fusion and Query Refinement Network for Video Moment Retrieval and Highlight Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benxiang Zhai, Sidan Du, Yifang Xu, Youyao Jia, Yunzhuo Sun, Zien Xie","submitted_at":"2025-01-18T08:09:44Z","abstract_excerpt":"Given a video and a linguistic query, video moment retrieval and highlight detection (MR&HD) aim to locate all the relevant spans while simultaneously predicting saliency scores. Most existing methods utilize RGB images as input, overlooking the inherent multi-modal visual signals like optical flow and depth. In this paper, we propose a Multi-modal Fusion and Query Refinement Network (MRNet) to learn complementary information from multi-modal cues. Specifically, we design a multi-modal fusion module to dynamically combine RGB, optical flow, and depth map. Furthermore, to simulate human underst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10692","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/2501.10692/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":"2501.10692","created_at":"2026-07-05T10:02:32.010727+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.10692v1","created_at":"2026-07-05T10:02:32.010727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10692","created_at":"2026-07-05T10:02:32.010727+00:00"},{"alias_kind":"pith_short_12","alias_value":"VPTUXC2KCJTM","created_at":"2026-07-05T10:02:32.010727+00:00"},{"alias_kind":"pith_short_16","alias_value":"VPTUXC2KCJTM3JZO","created_at":"2026-07-05T10:02:32.010727+00:00"},{"alias_kind":"pith_short_8","alias_value":"VPTUXC2K","created_at":"2026-07-05T10:02:32.010727+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/VPTUXC2KCJTM3JZOVXDPYUDY2H","json":"https://pith.science/pith/VPTUXC2KCJTM3JZOVXDPYUDY2H.json","graph_json":"https://pith.science/api/pith-number/VPTUXC2KCJTM3JZOVXDPYUDY2H/graph.json","events_json":"https://pith.science/api/pith-number/VPTUXC2KCJTM3JZOVXDPYUDY2H/events.json","paper":"https://pith.science/paper/VPTUXC2K"},"agent_actions":{"view_html":"https://pith.science/pith/VPTUXC2KCJTM3JZOVXDPYUDY2H","download_json":"https://pith.science/pith/VPTUXC2KCJTM3JZOVXDPYUDY2H.json","view_paper":"https://pith.science/paper/VPTUXC2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.10692&json=true","fetch_graph":"https://pith.science/api/pith-number/VPTUXC2KCJTM3JZOVXDPYUDY2H/graph.json","fetch_events":"https://pith.science/api/pith-number/VPTUXC2KCJTM3JZOVXDPYUDY2H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VPTUXC2KCJTM3JZOVXDPYUDY2H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VPTUXC2KCJTM3JZOVXDPYUDY2H/action/storage_attestation","attest_author":"https://pith.science/pith/VPTUXC2KCJTM3JZOVXDPYUDY2H/action/author_attestation","sign_citation":"https://pith.science/pith/VPTUXC2KCJTM3JZOVXDPYUDY2H/action/citation_signature","submit_replication":"https://pith.science/pith/VPTUXC2KCJTM3JZOVXDPYUDY2H/action/replication_record"}},"created_at":"2026-07-05T10:02:32.010727+00:00","updated_at":"2026-07-05T10:02:32.010727+00:00"}