{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CQAAOG6JBXPZWLMJG37ZIERAGC","short_pith_number":"pith:CQAAOG6J","schema_version":"1.0","canonical_sha256":"1400071bc90ddf9b2d8936ff941220309acd8459e0e3a3949887e379ff42b656","source":{"kind":"arxiv","id":"2311.05190","version":1},"attestation_state":"computed","paper":{"title":"Audio-visual Saliency for Omnidirectional Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangtao Zhai, Huiyu Duan, Jie Li, Kaiwei Zhang, Li Chen, Xilei Zhu, Xiongkuo Min, Yucheng Zhu, Yuxin Zhu","submitted_at":"2023-11-09T08:03:40Z","abstract_excerpt":"Visual saliency prediction for omnidirectional videos (ODVs) has shown great significance and necessity for omnidirectional videos to help ODV coding, ODV transmission, ODV rendering, etc.. However, most studies only consider visual information for ODV saliency prediction while audio is rarely considered despite its significant influence on the viewing behavior of ODV. This is mainly due to the lack of large-scale audio-visual ODV datasets and corresponding analysis. Thus, in this paper, we first establish the largest audio-visual saliency dataset for omnidirectional videos (AVS-ODV), which co"},"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":"2311.05190","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-09T08:03:40Z","cross_cats_sorted":[],"title_canon_sha256":"355761f65e650611406519abee00213c7c3e9f9dc026458d80726b97284e525c","abstract_canon_sha256":"7397b0c7747b2651db77a864c773e312c7f7856317a8737a571043ef52bed04f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:55.859868Z","signature_b64":"3jM9uu82d3Ux1Sf46tskTAKFAdclDhjusoxpsv99Rc8Qg2r3H7+UHcYP411tGC19FJfvSHySqCY7eo98clScCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1400071bc90ddf9b2d8936ff941220309acd8459e0e3a3949887e379ff42b656","last_reissued_at":"2026-07-05T07:10:55.859440Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:55.859440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-visual Saliency for Omnidirectional Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangtao Zhai, Huiyu Duan, Jie Li, Kaiwei Zhang, Li Chen, Xilei Zhu, Xiongkuo Min, Yucheng Zhu, Yuxin Zhu","submitted_at":"2023-11-09T08:03:40Z","abstract_excerpt":"Visual saliency prediction for omnidirectional videos (ODVs) has shown great significance and necessity for omnidirectional videos to help ODV coding, ODV transmission, ODV rendering, etc.. However, most studies only consider visual information for ODV saliency prediction while audio is rarely considered despite its significant influence on the viewing behavior of ODV. This is mainly due to the lack of large-scale audio-visual ODV datasets and corresponding analysis. Thus, in this paper, we first establish the largest audio-visual saliency dataset for omnidirectional videos (AVS-ODV), which co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05190","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/2311.05190/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":"2311.05190","created_at":"2026-07-05T07:10:55.859520+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.05190v1","created_at":"2026-07-05T07:10:55.859520+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05190","created_at":"2026-07-05T07:10:55.859520+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQAAOG6JBXPZ","created_at":"2026-07-05T07:10:55.859520+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQAAOG6JBXPZWLMJ","created_at":"2026-07-05T07:10:55.859520+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQAAOG6J","created_at":"2026-07-05T07:10:55.859520+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21925","citing_title":"Quality Assessment and Distortion-aware Saliency Prediction for AI-Generated Omnidirectional Images","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQAAOG6JBXPZWLMJG37ZIERAGC","json":"https://pith.science/pith/CQAAOG6JBXPZWLMJG37ZIERAGC.json","graph_json":"https://pith.science/api/pith-number/CQAAOG6JBXPZWLMJG37ZIERAGC/graph.json","events_json":"https://pith.science/api/pith-number/CQAAOG6JBXPZWLMJG37ZIERAGC/events.json","paper":"https://pith.science/paper/CQAAOG6J"},"agent_actions":{"view_html":"https://pith.science/pith/CQAAOG6JBXPZWLMJG37ZIERAGC","download_json":"https://pith.science/pith/CQAAOG6JBXPZWLMJG37ZIERAGC.json","view_paper":"https://pith.science/paper/CQAAOG6J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.05190&json=true","fetch_graph":"https://pith.science/api/pith-number/CQAAOG6JBXPZWLMJG37ZIERAGC/graph.json","fetch_events":"https://pith.science/api/pith-number/CQAAOG6JBXPZWLMJG37ZIERAGC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQAAOG6JBXPZWLMJG37ZIERAGC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQAAOG6JBXPZWLMJG37ZIERAGC/action/storage_attestation","attest_author":"https://pith.science/pith/CQAAOG6JBXPZWLMJG37ZIERAGC/action/author_attestation","sign_citation":"https://pith.science/pith/CQAAOG6JBXPZWLMJG37ZIERAGC/action/citation_signature","submit_replication":"https://pith.science/pith/CQAAOG6JBXPZWLMJG37ZIERAGC/action/replication_record"}},"created_at":"2026-07-05T07:10:55.859520+00:00","updated_at":"2026-07-05T07:10:55.859520+00:00"}