{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CEBBRWMYHS5PULU2WWHIL2IG3Y","short_pith_number":"pith:CEBBRWMY","schema_version":"1.0","canonical_sha256":"110218d9983cbafa2e9ab58e85e906de3f2a22a0bd0c9f76431ebc222da1e5a4","source":{"kind":"arxiv","id":"2412.10749","version":1},"attestation_state":"computed","paper":{"title":"Patch-level Sounding Object Tracking for Audio-Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.MM","authors_text":"Dan Guo, Jing Zhang, Jinxing Zhou, Kun Li, Shengeng Tang, Zhangbin Li","submitted_at":"2024-12-14T08:34:44Z","abstract_excerpt":"Answering questions related to audio-visual scenes, i.e., the AVQA task, is becoming increasingly popular. A critical challenge is accurately identifying and tracking sounding objects related to the question along the timeline. In this paper, we present a new Patch-level Sounding Object Tracking (PSOT) method. It begins with a Motion-driven Key Patch Tracking (M-KPT) module, which relies on visual motion information to identify salient visual patches with significant movements that are more likely to relate to sounding objects and questions. We measure the patch-wise motion intensity map betwe"},"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":"2412.10749","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-12-14T08:34:44Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"452347e89e15bda0057418f548afafdd2b9631086f953aa950e539eaaa1f8a0f","abstract_canon_sha256":"1427e4985bb7270468be0814c091ecb08d272ee2745710d247ef07def6f683d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:20.882861Z","signature_b64":"zJ+BKq4K2Wn5SRBmU6scH7UH9o3lU0kqHLFK8ej+ZuIWBpPf1XYlI1pTWUreKptjx31uv1Tx7HH5qABD/SiUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"110218d9983cbafa2e9ab58e85e906de3f2a22a0bd0c9f76431ebc222da1e5a4","last_reissued_at":"2026-07-05T09:49:20.882401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:20.882401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Patch-level Sounding Object Tracking for Audio-Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.MM","authors_text":"Dan Guo, Jing Zhang, Jinxing Zhou, Kun Li, Shengeng Tang, Zhangbin Li","submitted_at":"2024-12-14T08:34:44Z","abstract_excerpt":"Answering questions related to audio-visual scenes, i.e., the AVQA task, is becoming increasingly popular. A critical challenge is accurately identifying and tracking sounding objects related to the question along the timeline. In this paper, we present a new Patch-level Sounding Object Tracking (PSOT) method. It begins with a Motion-driven Key Patch Tracking (M-KPT) module, which relies on visual motion information to identify salient visual patches with significant movements that are more likely to relate to sounding objects and questions. We measure the patch-wise motion intensity map betwe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10749","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/2412.10749/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":"2412.10749","created_at":"2026-07-05T09:49:20.882462+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10749v1","created_at":"2026-07-05T09:49:20.882462+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10749","created_at":"2026-07-05T09:49:20.882462+00:00"},{"alias_kind":"pith_short_12","alias_value":"CEBBRWMYHS5P","created_at":"2026-07-05T09:49:20.882462+00:00"},{"alias_kind":"pith_short_16","alias_value":"CEBBRWMYHS5PULU2","created_at":"2026-07-05T09:49:20.882462+00:00"},{"alias_kind":"pith_short_8","alias_value":"CEBBRWMY","created_at":"2026-07-05T09:49:20.882462+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/CEBBRWMYHS5PULU2WWHIL2IG3Y","json":"https://pith.science/pith/CEBBRWMYHS5PULU2WWHIL2IG3Y.json","graph_json":"https://pith.science/api/pith-number/CEBBRWMYHS5PULU2WWHIL2IG3Y/graph.json","events_json":"https://pith.science/api/pith-number/CEBBRWMYHS5PULU2WWHIL2IG3Y/events.json","paper":"https://pith.science/paper/CEBBRWMY"},"agent_actions":{"view_html":"https://pith.science/pith/CEBBRWMYHS5PULU2WWHIL2IG3Y","download_json":"https://pith.science/pith/CEBBRWMYHS5PULU2WWHIL2IG3Y.json","view_paper":"https://pith.science/paper/CEBBRWMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10749&json=true","fetch_graph":"https://pith.science/api/pith-number/CEBBRWMYHS5PULU2WWHIL2IG3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/CEBBRWMYHS5PULU2WWHIL2IG3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CEBBRWMYHS5PULU2WWHIL2IG3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CEBBRWMYHS5PULU2WWHIL2IG3Y/action/storage_attestation","attest_author":"https://pith.science/pith/CEBBRWMYHS5PULU2WWHIL2IG3Y/action/author_attestation","sign_citation":"https://pith.science/pith/CEBBRWMYHS5PULU2WWHIL2IG3Y/action/citation_signature","submit_replication":"https://pith.science/pith/CEBBRWMYHS5PULU2WWHIL2IG3Y/action/replication_record"}},"created_at":"2026-07-05T09:49:20.882462+00:00","updated_at":"2026-07-05T09:49:20.882462+00:00"}