{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NFL6YJM4IHCIWHBT4B2CPZFXPG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"937f9d18e537d8179121511bbc45809e31bb03b5cb7f1dd9bc56b2fca9e7e70f","cross_cats_sorted":["cs.CV","cs.LG","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-25T03:59:04Z","title_canon_sha256":"fac611864fb70cb13edb745b07385fefef7674759ce39028a0bbd2f41aa54254"},"schema_version":"1.0","source":{"id":"2307.13236","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.13236","created_at":"2026-07-05T06:34:11Z"},{"alias_kind":"arxiv_version","alias_value":"2307.13236v1","created_at":"2026-07-05T06:34:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.13236","created_at":"2026-07-05T06:34:11Z"},{"alias_kind":"pith_short_12","alias_value":"NFL6YJM4IHCI","created_at":"2026-07-05T06:34:11Z"},{"alias_kind":"pith_short_16","alias_value":"NFL6YJM4IHCIWHBT","created_at":"2026-07-05T06:34:11Z"},{"alias_kind":"pith_short_8","alias_value":"NFL6YJM4","created_at":"2026-07-05T06:34:11Z"}],"graph_snapshots":[{"event_id":"sha256:5b7e7f2dc8f2bc729f45ac9f3fb1136e225374d7c326fd12e33832667a3f8447","target":"graph","created_at":"2026-07-05T06:34:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2307.13236/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of the audio-visual segmentation (AVS) task is to segment the sounding objects in the video frames using audio cues. However, current fusion-based methods have the performance limitations due to the small receptive field of convolution and inadequate fusion of audio-visual features. To overcome these issues, we propose a novel \\textbf{Au}dio-aware query-enhanced \\textbf{TR}ansformer (AuTR) to tackle the task. Unlike existing methods, our approach introduces a multimodal transformer architecture that enables deep fusion and aggregation of audio-visual features. Furthermore, we devise a","authors_text":"Chaofan Ma, Chen Ju, Jinxiang Liu, Yanfeng Wang, Ya Zhang, Yu Wang","cross_cats":["cs.CV","cs.LG","cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-25T03:59:04Z","title":"Audio-aware Query-enhanced Transformer for Audio-Visual Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.13236","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ae287e06769b4357ca8ae8cc6e4ed535e0cb9cb975455ba7be792e0355cfdd07","target":"record","created_at":"2026-07-05T06:34:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"937f9d18e537d8179121511bbc45809e31bb03b5cb7f1dd9bc56b2fca9e7e70f","cross_cats_sorted":["cs.CV","cs.LG","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-25T03:59:04Z","title_canon_sha256":"fac611864fb70cb13edb745b07385fefef7674759ce39028a0bbd2f41aa54254"},"schema_version":"1.0","source":{"id":"2307.13236","kind":"arxiv","version":1}},"canonical_sha256":"6957ec259c41c48b1c33e07427e4b77982cf030b74afa34929f9574381773bcf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6957ec259c41c48b1c33e07427e4b77982cf030b74afa34929f9574381773bcf","first_computed_at":"2026-07-05T06:34:11.048873Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:34:11.048873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4CYC8WeBS6pS0654mqDHRinvnYXXC4M0iditq+IZZHxI+GjMRPsMyOQvhpwCfM6nMQ3FJCUfbjVhUK2lqxDRDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:34:11.049303Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.13236","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae287e06769b4357ca8ae8cc6e4ed535e0cb9cb975455ba7be792e0355cfdd07","sha256:5b7e7f2dc8f2bc729f45ac9f3fb1136e225374d7c326fd12e33832667a3f8447"],"state_sha256":"d8a556add654e3664fe48f4a7f66ac85b77a3f1dd0f5517cbe70a1d07dbd7e52"}