{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DCFHMLG6JYOM5Q45BK7R6WKWPJ","short_pith_number":"pith:DCFHMLG6","schema_version":"1.0","canonical_sha256":"188a762cde4e1ccec39d0abf1f59567a57b8d666f383800ff3c48f0709d31dc1","source":{"kind":"arxiv","id":"2402.02327","version":2},"attestation_state":"computed","paper":{"title":"Bootstrapping Audio-Visual Segmentation by Strengthening Audio Cues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Bin Liu, Jieping Ye, Le Lu, Nenghai Yu, Qi Chu, Tao Gong, Tianxiang Chen, Yue Wu, Zhentao Tan","submitted_at":"2024-02-04T03:02:35Z","abstract_excerpt":"How to effectively interact audio with vision has garnered considerable interest within the multi-modality research field. Recently, a novel audio-visual segmentation (AVS) task has been proposed, aiming to segment the sounding objects in video frames under the guidance of audio cues. However, most existing AVS methods are hindered by a modality imbalance where the visual features tend to dominate those of the audio modality, due to a unidirectional and insufficient integration of audio cues. This imbalance skews the feature representation towards the visual aspect, impeding the learning of jo"},"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":"2402.02327","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-04T03:02:35Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"8a4408cf3f018e2a74115d06082b31135f0bdab55c171ea3268cd29f120b1423","abstract_canon_sha256":"10c8b1b7b52b1471fb4409a0c813ce236e7f3829d0f508de786c67368545c690"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:48.546346Z","signature_b64":"a3V7YxlRvLu2I5XgSRNU7oInQ9t5U9MpERsPN+mW/wd2fUtgySSKpEhSk47vDwfvUj8p4ksw0fJ9X2werXznDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"188a762cde4e1ccec39d0abf1f59567a57b8d666f383800ff3c48f0709d31dc1","last_reissued_at":"2026-07-05T07:41:48.545934Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:48.545934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bootstrapping Audio-Visual Segmentation by Strengthening Audio Cues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Bin Liu, Jieping Ye, Le Lu, Nenghai Yu, Qi Chu, Tao Gong, Tianxiang Chen, Yue Wu, Zhentao Tan","submitted_at":"2024-02-04T03:02:35Z","abstract_excerpt":"How to effectively interact audio with vision has garnered considerable interest within the multi-modality research field. Recently, a novel audio-visual segmentation (AVS) task has been proposed, aiming to segment the sounding objects in video frames under the guidance of audio cues. However, most existing AVS methods are hindered by a modality imbalance where the visual features tend to dominate those of the audio modality, due to a unidirectional and insufficient integration of audio cues. This imbalance skews the feature representation towards the visual aspect, impeding the learning of jo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02327","kind":"arxiv","version":2},"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/2402.02327/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":"2402.02327","created_at":"2026-07-05T07:41:48.545992+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02327v2","created_at":"2026-07-05T07:41:48.545992+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02327","created_at":"2026-07-05T07:41:48.545992+00:00"},{"alias_kind":"pith_short_12","alias_value":"DCFHMLG6JYOM","created_at":"2026-07-05T07:41:48.545992+00:00"},{"alias_kind":"pith_short_16","alias_value":"DCFHMLG6JYOM5Q45","created_at":"2026-07-05T07:41:48.545992+00:00"},{"alias_kind":"pith_short_8","alias_value":"DCFHMLG6","created_at":"2026-07-05T07:41:48.545992+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.20740","citing_title":"Implicit Counterfactual Learning for Audio-Visual Segmentation","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DCFHMLG6JYOM5Q45BK7R6WKWPJ","json":"https://pith.science/pith/DCFHMLG6JYOM5Q45BK7R6WKWPJ.json","graph_json":"https://pith.science/api/pith-number/DCFHMLG6JYOM5Q45BK7R6WKWPJ/graph.json","events_json":"https://pith.science/api/pith-number/DCFHMLG6JYOM5Q45BK7R6WKWPJ/events.json","paper":"https://pith.science/paper/DCFHMLG6"},"agent_actions":{"view_html":"https://pith.science/pith/DCFHMLG6JYOM5Q45BK7R6WKWPJ","download_json":"https://pith.science/pith/DCFHMLG6JYOM5Q45BK7R6WKWPJ.json","view_paper":"https://pith.science/paper/DCFHMLG6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02327&json=true","fetch_graph":"https://pith.science/api/pith-number/DCFHMLG6JYOM5Q45BK7R6WKWPJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DCFHMLG6JYOM5Q45BK7R6WKWPJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DCFHMLG6JYOM5Q45BK7R6WKWPJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DCFHMLG6JYOM5Q45BK7R6WKWPJ/action/storage_attestation","attest_author":"https://pith.science/pith/DCFHMLG6JYOM5Q45BK7R6WKWPJ/action/author_attestation","sign_citation":"https://pith.science/pith/DCFHMLG6JYOM5Q45BK7R6WKWPJ/action/citation_signature","submit_replication":"https://pith.science/pith/DCFHMLG6JYOM5Q45BK7R6WKWPJ/action/replication_record"}},"created_at":"2026-07-05T07:41:48.545992+00:00","updated_at":"2026-07-05T07:41:48.545992+00:00"}