{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NOOSQ2W34GVBXYG7NYZW2EHRAZ","short_pith_number":"pith:NOOSQ2W3","schema_version":"1.0","canonical_sha256":"6b9d286adbe1aa1be0df6e336d10f1065a539bc12bddc60ce9f9c7ad24ba615e","source":{"kind":"arxiv","id":"2302.09328","version":1},"attestation_state":"computed","paper":{"title":"SSVMR: Saliency-based Self-training for Video-Music Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Hongxiang Li, Xuxin Cheng, Yaowei Li, Yuexian Zou, Zhihong Zhu","submitted_at":"2023-02-18T13:30:56Z","abstract_excerpt":"With the rise of short videos, the demand for selecting appropriate background music (BGM) for a video has increased significantly, video-music retrieval (VMR) task gradually draws much attention by research community. As other cross-modal learning tasks, existing VMR approaches usually attempt to measure the similarity between the video and music in the feature space. However, they (1) neglect the inevitable label noise; (2) neglect to enhance the ability to capture critical video clips. In this paper, we propose a novel saliency-based self-training framework, which is termed SSVMR. Specifica"},"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":"2302.09328","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2023-02-18T13:30:56Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"73cd3e5c9a5191c460181807733c72a66f41a2b005c5a1e1c1e4631176eb2672","abstract_canon_sha256":"92b031f8b3ffe76c7f947be65b461570a3dc9e8c1057847296ad840c5846f812"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:24.243266Z","signature_b64":"FaRgb/1tPXPQ9/5OL8ds554YnmetOn3EJoduX59eeUyNUnmg0qHR0msYrnEQYCqPjy2VEx+6Q/knd8j2FA1WBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b9d286adbe1aa1be0df6e336d10f1065a539bc12bddc60ce9f9c7ad24ba615e","last_reissued_at":"2026-07-05T05:43:24.242830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:24.242830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SSVMR: Saliency-based Self-training for Video-Music Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Hongxiang Li, Xuxin Cheng, Yaowei Li, Yuexian Zou, Zhihong Zhu","submitted_at":"2023-02-18T13:30:56Z","abstract_excerpt":"With the rise of short videos, the demand for selecting appropriate background music (BGM) for a video has increased significantly, video-music retrieval (VMR) task gradually draws much attention by research community. As other cross-modal learning tasks, existing VMR approaches usually attempt to measure the similarity between the video and music in the feature space. However, they (1) neglect the inevitable label noise; (2) neglect to enhance the ability to capture critical video clips. In this paper, we propose a novel saliency-based self-training framework, which is termed SSVMR. Specifica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.09328","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/2302.09328/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":"2302.09328","created_at":"2026-07-05T05:43:24.242891+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.09328v1","created_at":"2026-07-05T05:43:24.242891+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.09328","created_at":"2026-07-05T05:43:24.242891+00:00"},{"alias_kind":"pith_short_12","alias_value":"NOOSQ2W34GVB","created_at":"2026-07-05T05:43:24.242891+00:00"},{"alias_kind":"pith_short_16","alias_value":"NOOSQ2W34GVBXYG7","created_at":"2026-07-05T05:43:24.242891+00:00"},{"alias_kind":"pith_short_8","alias_value":"NOOSQ2W3","created_at":"2026-07-05T05:43:24.242891+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/NOOSQ2W34GVBXYG7NYZW2EHRAZ","json":"https://pith.science/pith/NOOSQ2W34GVBXYG7NYZW2EHRAZ.json","graph_json":"https://pith.science/api/pith-number/NOOSQ2W34GVBXYG7NYZW2EHRAZ/graph.json","events_json":"https://pith.science/api/pith-number/NOOSQ2W34GVBXYG7NYZW2EHRAZ/events.json","paper":"https://pith.science/paper/NOOSQ2W3"},"agent_actions":{"view_html":"https://pith.science/pith/NOOSQ2W34GVBXYG7NYZW2EHRAZ","download_json":"https://pith.science/pith/NOOSQ2W34GVBXYG7NYZW2EHRAZ.json","view_paper":"https://pith.science/paper/NOOSQ2W3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.09328&json=true","fetch_graph":"https://pith.science/api/pith-number/NOOSQ2W34GVBXYG7NYZW2EHRAZ/graph.json","fetch_events":"https://pith.science/api/pith-number/NOOSQ2W34GVBXYG7NYZW2EHRAZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NOOSQ2W34GVBXYG7NYZW2EHRAZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NOOSQ2W34GVBXYG7NYZW2EHRAZ/action/storage_attestation","attest_author":"https://pith.science/pith/NOOSQ2W34GVBXYG7NYZW2EHRAZ/action/author_attestation","sign_citation":"https://pith.science/pith/NOOSQ2W34GVBXYG7NYZW2EHRAZ/action/citation_signature","submit_replication":"https://pith.science/pith/NOOSQ2W34GVBXYG7NYZW2EHRAZ/action/replication_record"}},"created_at":"2026-07-05T05:43:24.242891+00:00","updated_at":"2026-07-05T05:43:24.242891+00:00"}