{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WQUI5UL6U2ZPCZ4FRD5JOR55TJ","short_pith_number":"pith:WQUI5UL6","schema_version":"1.0","canonical_sha256":"b4288ed17ea6b2f1678588fa9747bd9a422a60bcad61f4c9861d860e8dd99e3b","source":{"kind":"arxiv","id":"2501.07810","version":1},"attestation_state":"computed","paper":{"title":"AVS-Mamba: Exploring Temporal and Multi-modal Mamba for Audio-Visual Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huchuan Lu, Lijun Wang, Lu Zhang, Pingping Zhang, Sitong Gong, Yifan Wang, Yunzhi Zhuge","submitted_at":"2025-01-14T03:20:20Z","abstract_excerpt":"The essence of audio-visual segmentation (AVS) lies in locating and delineating sound-emitting objects within a video stream. While Transformer-based methods have shown promise, their handling of long-range dependencies struggles due to quadratic computational costs, presenting a bottleneck in complex scenarios. To overcome this limitation and facilitate complex multi-modal comprehension with linear complexity, we introduce AVS-Mamba, a selective state space model to address the AVS task. Our framework incorporates two key components for video understanding and cross-modal learning: Temporal M"},"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":"2501.07810","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T03:20:20Z","cross_cats_sorted":[],"title_canon_sha256":"ed8fa7a7f4a94ee0adc612c479ed3a59d5896125451ec96d1a6d6a2fc7dcee08","abstract_canon_sha256":"d362edc9ad11976f05b1f549f57eb3bd8168c80335e96f9a14680e72868de9cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:50.494014Z","signature_b64":"Svdy0AifZUhile/nAOwhHDxRLtHE3UQaegv48aoUNcJF8ee4gkKfJPdE4MoUkbK3bY2RVhgPS7AyJ9hVLL7gDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4288ed17ea6b2f1678588fa9747bd9a422a60bcad61f4c9861d860e8dd99e3b","last_reissued_at":"2026-07-05T10:00:50.493521Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:50.493521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AVS-Mamba: Exploring Temporal and Multi-modal Mamba for Audio-Visual Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huchuan Lu, Lijun Wang, Lu Zhang, Pingping Zhang, Sitong Gong, Yifan Wang, Yunzhi Zhuge","submitted_at":"2025-01-14T03:20:20Z","abstract_excerpt":"The essence of audio-visual segmentation (AVS) lies in locating and delineating sound-emitting objects within a video stream. While Transformer-based methods have shown promise, their handling of long-range dependencies struggles due to quadratic computational costs, presenting a bottleneck in complex scenarios. To overcome this limitation and facilitate complex multi-modal comprehension with linear complexity, we introduce AVS-Mamba, a selective state space model to address the AVS task. Our framework incorporates two key components for video understanding and cross-modal learning: Temporal M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07810","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/2501.07810/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":"2501.07810","created_at":"2026-07-05T10:00:50.493582+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.07810v1","created_at":"2026-07-05T10:00:50.493582+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07810","created_at":"2026-07-05T10:00:50.493582+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQUI5UL6U2ZP","created_at":"2026-07-05T10:00:50.493582+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQUI5UL6U2ZPCZ4F","created_at":"2026-07-05T10:00:50.493582+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQUI5UL6","created_at":"2026-07-05T10:00:50.493582+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01384","citing_title":"MUG: Pseudo Labeling Augmented Audio-Visual Mamba Network for Audio-Visual Video Parsing","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WQUI5UL6U2ZPCZ4FRD5JOR55TJ","json":"https://pith.science/pith/WQUI5UL6U2ZPCZ4FRD5JOR55TJ.json","graph_json":"https://pith.science/api/pith-number/WQUI5UL6U2ZPCZ4FRD5JOR55TJ/graph.json","events_json":"https://pith.science/api/pith-number/WQUI5UL6U2ZPCZ4FRD5JOR55TJ/events.json","paper":"https://pith.science/paper/WQUI5UL6"},"agent_actions":{"view_html":"https://pith.science/pith/WQUI5UL6U2ZPCZ4FRD5JOR55TJ","download_json":"https://pith.science/pith/WQUI5UL6U2ZPCZ4FRD5JOR55TJ.json","view_paper":"https://pith.science/paper/WQUI5UL6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.07810&json=true","fetch_graph":"https://pith.science/api/pith-number/WQUI5UL6U2ZPCZ4FRD5JOR55TJ/graph.json","fetch_events":"https://pith.science/api/pith-number/WQUI5UL6U2ZPCZ4FRD5JOR55TJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQUI5UL6U2ZPCZ4FRD5JOR55TJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQUI5UL6U2ZPCZ4FRD5JOR55TJ/action/storage_attestation","attest_author":"https://pith.science/pith/WQUI5UL6U2ZPCZ4FRD5JOR55TJ/action/author_attestation","sign_citation":"https://pith.science/pith/WQUI5UL6U2ZPCZ4FRD5JOR55TJ/action/citation_signature","submit_replication":"https://pith.science/pith/WQUI5UL6U2ZPCZ4FRD5JOR55TJ/action/replication_record"}},"created_at":"2026-07-05T10:00:50.493582+00:00","updated_at":"2026-07-05T10:00:50.493582+00:00"}