{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VPTUXC2KCJTM3JZOVXDPYUDY2H","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a2737d27d7f3fbeb37efc1abf6390023f78d4f1e47e5b6364e80b05621c77b54","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-18T08:09:44Z","title_canon_sha256":"f0341ca98335a8c71d3867e9cb093a416616b485090492d5aa59c22839c2e0d6"},"schema_version":"1.0","source":{"id":"2501.10692","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.10692","created_at":"2026-07-05T10:02:32Z"},{"alias_kind":"arxiv_version","alias_value":"2501.10692v1","created_at":"2026-07-05T10:02:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10692","created_at":"2026-07-05T10:02:32Z"},{"alias_kind":"pith_short_12","alias_value":"VPTUXC2KCJTM","created_at":"2026-07-05T10:02:32Z"},{"alias_kind":"pith_short_16","alias_value":"VPTUXC2KCJTM3JZO","created_at":"2026-07-05T10:02:32Z"},{"alias_kind":"pith_short_8","alias_value":"VPTUXC2K","created_at":"2026-07-05T10:02:32Z"}],"graph_snapshots":[{"event_id":"sha256:19e5a5b940a76da67866bbfd9681ce8738491c5bdd8be7f0810663a20985c646","target":"graph","created_at":"2026-07-05T10:02:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.10692/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Benxiang Zhai, Sidan Du, Yifang Xu, Youyao Jia, Yunzhuo Sun, Zien Xie","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-18T08:09:44Z","title":"Multi-modal Fusion and Query Refinement Network for Video Moment Retrieval and Highlight Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10692","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:16ce76e1f3a9021cc9bc846d6d4b3a6b431a0eda543d43144b59202bc5cba4e0","target":"record","created_at":"2026-07-05T10:02:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a2737d27d7f3fbeb37efc1abf6390023f78d4f1e47e5b6364e80b05621c77b54","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-18T08:09:44Z","title_canon_sha256":"f0341ca98335a8c71d3867e9cb093a416616b485090492d5aa59c22839c2e0d6"},"schema_version":"1.0","source":{"id":"2501.10692","kind":"arxiv","version":1}},"canonical_sha256":"abe74b8b4a1266cda72eadc6fc5078d1ec78ec2b09da363c6219ba56913b041c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abe74b8b4a1266cda72eadc6fc5078d1ec78ec2b09da363c6219ba56913b041c","first_computed_at":"2026-07-05T10:02:32.010656Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:32.010656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1YZlFUayKfHGhBvnOwWYcphldq3pLNArWnjDH5CLoo09slHtneT8WIc74RbiVt5MZDwJW/ubUWZHC/Z5An4vCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:32.011225Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.10692","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16ce76e1f3a9021cc9bc846d6d4b3a6b431a0eda543d43144b59202bc5cba4e0","sha256:19e5a5b940a76da67866bbfd9681ce8738491c5bdd8be7f0810663a20985c646"],"state_sha256":"49ef8ea83786ada93c980bd407bcefe976cf7e50e518093ac01f1dd3b9276af4"}