{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GFOYPZZ7ZVODWWHAA4KNQE3Q2H","short_pith_number":"pith:GFOYPZZ7","schema_version":"1.0","canonical_sha256":"315d87e73fcd5c3b58e00714d81370d1f2281880acda710100a9c46d3f59f15c","source":{"kind":"arxiv","id":"2310.18709","version":4},"attestation_state":"computed","paper":{"title":"Audio-Visual Instance Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Bowei Xing, Buwen Liang, Dantong Niu, Guangyao Li, Jinxing Zhou, Ji Shi, Liao Qu, Peiliang Zhang, Qixun Wang, Ruohao Guo, Wenzhen Yue, Xianghua Ying, Yanyu Qi, Yaru Chen","submitted_at":"2023-10-28T13:37:52Z","abstract_excerpt":"In this paper, we propose a new multi-modal task, termed audio-visual instance segmentation (AVIS), which aims to simultaneously identify, segment and track individual sounding object instances in audible videos. To facilitate this research, we introduce a high-quality benchmark named AVISeg, containing over 90K instance masks from 26 semantic categories in 926 long videos. Additionally, we propose a strong baseline model for this task. Our model first localizes sound source within each frame, and condenses object-specific contexts into concise tokens. Then it builds long-range audio-visual de"},"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":"2310.18709","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-28T13:37:52Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"e809b201627c2f3d376ec6ba8d0b14443f1cca813983ddc7679d53f7673da825","abstract_canon_sha256":"a98bb8f8f358c0f064b01a7c3f555eeb34303be085e7f37fb2f4febc6b15bd74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:56.480533Z","signature_b64":"x83KgbMZTAV9BSqK1SYLkXNUeP61mz3APsTuDruYVwqYm4sSOOXRJ0dbSxzbwPzwf6cqUK3/ZCDhUK6sYVYiCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"315d87e73fcd5c3b58e00714d81370d1f2281880acda710100a9c46d3f59f15c","last_reissued_at":"2026-07-05T10:21:56.480097Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:56.480097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-Visual Instance Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Bowei Xing, Buwen Liang, Dantong Niu, Guangyao Li, Jinxing Zhou, Ji Shi, Liao Qu, Peiliang Zhang, Qixun Wang, Ruohao Guo, Wenzhen Yue, Xianghua Ying, Yanyu Qi, Yaru Chen","submitted_at":"2023-10-28T13:37:52Z","abstract_excerpt":"In this paper, we propose a new multi-modal task, termed audio-visual instance segmentation (AVIS), which aims to simultaneously identify, segment and track individual sounding object instances in audible videos. To facilitate this research, we introduce a high-quality benchmark named AVISeg, containing over 90K instance masks from 26 semantic categories in 926 long videos. Additionally, we propose a strong baseline model for this task. Our model first localizes sound source within each frame, and condenses object-specific contexts into concise tokens. Then it builds long-range audio-visual de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18709","kind":"arxiv","version":4},"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/2310.18709/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":"2310.18709","created_at":"2026-07-05T10:21:56.480163+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18709v4","created_at":"2026-07-05T10:21:56.480163+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18709","created_at":"2026-07-05T10:21:56.480163+00:00"},{"alias_kind":"pith_short_12","alias_value":"GFOYPZZ7ZVOD","created_at":"2026-07-05T10:21:56.480163+00:00"},{"alias_kind":"pith_short_16","alias_value":"GFOYPZZ7ZVODWWHA","created_at":"2026-07-05T10:21:56.480163+00:00"},{"alias_kind":"pith_short_8","alias_value":"GFOYPZZ7","created_at":"2026-07-05T10:21:56.480163+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.04566","citing_title":"CLASP: Cross-modal Salient Anchor-based Semantic Propagation for Weakly-supervised Dense Audio-Visual Event Localization","ref_index":2020,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GFOYPZZ7ZVODWWHAA4KNQE3Q2H","json":"https://pith.science/pith/GFOYPZZ7ZVODWWHAA4KNQE3Q2H.json","graph_json":"https://pith.science/api/pith-number/GFOYPZZ7ZVODWWHAA4KNQE3Q2H/graph.json","events_json":"https://pith.science/api/pith-number/GFOYPZZ7ZVODWWHAA4KNQE3Q2H/events.json","paper":"https://pith.science/paper/GFOYPZZ7"},"agent_actions":{"view_html":"https://pith.science/pith/GFOYPZZ7ZVODWWHAA4KNQE3Q2H","download_json":"https://pith.science/pith/GFOYPZZ7ZVODWWHAA4KNQE3Q2H.json","view_paper":"https://pith.science/paper/GFOYPZZ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18709&json=true","fetch_graph":"https://pith.science/api/pith-number/GFOYPZZ7ZVODWWHAA4KNQE3Q2H/graph.json","fetch_events":"https://pith.science/api/pith-number/GFOYPZZ7ZVODWWHAA4KNQE3Q2H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GFOYPZZ7ZVODWWHAA4KNQE3Q2H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GFOYPZZ7ZVODWWHAA4KNQE3Q2H/action/storage_attestation","attest_author":"https://pith.science/pith/GFOYPZZ7ZVODWWHAA4KNQE3Q2H/action/author_attestation","sign_citation":"https://pith.science/pith/GFOYPZZ7ZVODWWHAA4KNQE3Q2H/action/citation_signature","submit_replication":"https://pith.science/pith/GFOYPZZ7ZVODWWHAA4KNQE3Q2H/action/replication_record"}},"created_at":"2026-07-05T10:21:56.480163+00:00","updated_at":"2026-07-05T10:21:56.480163+00:00"}