{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LXOY7CXCQWJETIAGDUZTL2IFCY","short_pith_number":"pith:LXOY7CXC","schema_version":"1.0","canonical_sha256":"5ddd8f8ae2859249a0061d3335e9051628242cebd53050febe2633f0abe863dc","source":{"kind":"arxiv","id":"2506.04214","version":1},"attestation_state":"computed","paper":{"title":"Sounding that Object: Interactive Object-Aware Image to Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Baihe Huang, Dongya Jia, Gopala Anumanchipalli, Jiawei Chen, Tingle Li, Xiaobin Zhuang, Yuping Wang, Yuxuan Wang, Zhuo Chen","submitted_at":"2025-06-04T17:57:26Z","abstract_excerpt":"Generating accurate sounds for complex audio-visual scenes is challenging, especially in the presence of multiple objects and sound sources. In this paper, we propose an {\\em interactive object-aware audio generation} model that grounds sound generation in user-selected visual objects within images. Our method integrates object-centric learning into a conditional latent diffusion model, which learns to associate image regions with their corresponding sounds through multi-modal attention. At test time, our model employs image segmentation to allow users to interactively generate sounds at the {"},"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":"2506.04214","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T17:57:26Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"000529782725b5b379c7e45867c43a05949c4d0615fac7258107ebf057ba0d82","abstract_canon_sha256":"93ce894e05c47bf3e087cdeaaaec2ad10011ce27d2fd0572d81421055261c31e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:59.015795Z","signature_b64":"K6gNfM0dqoRwsYYnAmeV4L35w8onDyUEZFAUDrcdug63V0NyssqziorbeFUvHoHmOS7v9/trG2+v3jSdwrYrBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ddd8f8ae2859249a0061d3335e9051628242cebd53050febe2633f0abe863dc","last_reissued_at":"2026-07-05T11:15:59.015238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:59.015238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sounding that Object: Interactive Object-Aware Image to Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Baihe Huang, Dongya Jia, Gopala Anumanchipalli, Jiawei Chen, Tingle Li, Xiaobin Zhuang, Yuping Wang, Yuxuan Wang, Zhuo Chen","submitted_at":"2025-06-04T17:57:26Z","abstract_excerpt":"Generating accurate sounds for complex audio-visual scenes is challenging, especially in the presence of multiple objects and sound sources. In this paper, we propose an {\\em interactive object-aware audio generation} model that grounds sound generation in user-selected visual objects within images. Our method integrates object-centric learning into a conditional latent diffusion model, which learns to associate image regions with their corresponding sounds through multi-modal attention. At test time, our model employs image segmentation to allow users to interactively generate sounds at the {"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04214","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/2506.04214/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":"2506.04214","created_at":"2026-07-05T11:15:59.015324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04214v1","created_at":"2026-07-05T11:15:59.015324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04214","created_at":"2026-07-05T11:15:59.015324+00:00"},{"alias_kind":"pith_short_12","alias_value":"LXOY7CXCQWJE","created_at":"2026-07-05T11:15:59.015324+00:00"},{"alias_kind":"pith_short_16","alias_value":"LXOY7CXCQWJETIAG","created_at":"2026-07-05T11:15:59.015324+00:00"},{"alias_kind":"pith_short_8","alias_value":"LXOY7CXC","created_at":"2026-07-05T11:15:59.015324+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/LXOY7CXCQWJETIAGDUZTL2IFCY","json":"https://pith.science/pith/LXOY7CXCQWJETIAGDUZTL2IFCY.json","graph_json":"https://pith.science/api/pith-number/LXOY7CXCQWJETIAGDUZTL2IFCY/graph.json","events_json":"https://pith.science/api/pith-number/LXOY7CXCQWJETIAGDUZTL2IFCY/events.json","paper":"https://pith.science/paper/LXOY7CXC"},"agent_actions":{"view_html":"https://pith.science/pith/LXOY7CXCQWJETIAGDUZTL2IFCY","download_json":"https://pith.science/pith/LXOY7CXCQWJETIAGDUZTL2IFCY.json","view_paper":"https://pith.science/paper/LXOY7CXC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04214&json=true","fetch_graph":"https://pith.science/api/pith-number/LXOY7CXCQWJETIAGDUZTL2IFCY/graph.json","fetch_events":"https://pith.science/api/pith-number/LXOY7CXCQWJETIAGDUZTL2IFCY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LXOY7CXCQWJETIAGDUZTL2IFCY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LXOY7CXCQWJETIAGDUZTL2IFCY/action/storage_attestation","attest_author":"https://pith.science/pith/LXOY7CXCQWJETIAGDUZTL2IFCY/action/author_attestation","sign_citation":"https://pith.science/pith/LXOY7CXCQWJETIAGDUZTL2IFCY/action/citation_signature","submit_replication":"https://pith.science/pith/LXOY7CXCQWJETIAGDUZTL2IFCY/action/replication_record"}},"created_at":"2026-07-05T11:15:59.015324+00:00","updated_at":"2026-07-05T11:15:59.015324+00:00"}