{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RYWATVXD5LYTEFJNUIHHDS2ZYV","short_pith_number":"pith:RYWATVXD","schema_version":"1.0","canonical_sha256":"8e2c09d6e3eaf132152da20e71cb59c5649b5151320c7547c7e2109ba51aa3bc","source":{"kind":"arxiv","id":"2111.05526","version":1},"attestation_state":"computed","paper":{"title":"Space-Time Memory Network for Sounding Object Localization in Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenliang Xu, Sizhe Li, Yapeng Tian","submitted_at":"2021-11-10T04:40:12Z","abstract_excerpt":"Leveraging temporal synchronization and association within sight and sound is an essential step towards robust localization of sounding objects. To this end, we propose a space-time memory network for sounding object localization in videos. It can simultaneously learn spatio-temporal attention over both uni-modal and cross-modal representations from audio and visual modalities. We show and analyze both quantitatively and qualitatively the effectiveness of incorporating spatio-temporal learning in localizing audio-visual objects. We demonstrate that our approach generalizes over various complex"},"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":"2111.05526","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-10T04:40:12Z","cross_cats_sorted":[],"title_canon_sha256":"dbdd51c1b4505b397270462c776a7308fc8876b3ec4cd5e17cae71c13f79541c","abstract_canon_sha256":"c6def5c0935c9cc80b4a7a90205eafaf912339f848994d164fe244647ac9fd3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:30:45.547086Z","signature_b64":"hwFSw7h7B3fp1mVSv8HjKk/y8MEsBCrh9K8iD6Y48/U+YYc8lno4eXV+6WBDp+gwT74mUSKrr8itDxXhlRaPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e2c09d6e3eaf132152da20e71cb59c5649b5151320c7547c7e2109ba51aa3bc","last_reissued_at":"2026-07-05T03:30:45.546623Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:30:45.546623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Space-Time Memory Network for Sounding Object Localization in Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenliang Xu, Sizhe Li, Yapeng Tian","submitted_at":"2021-11-10T04:40:12Z","abstract_excerpt":"Leveraging temporal synchronization and association within sight and sound is an essential step towards robust localization of sounding objects. To this end, we propose a space-time memory network for sounding object localization in videos. It can simultaneously learn spatio-temporal attention over both uni-modal and cross-modal representations from audio and visual modalities. We show and analyze both quantitatively and qualitatively the effectiveness of incorporating spatio-temporal learning in localizing audio-visual objects. We demonstrate that our approach generalizes over various complex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.05526","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/2111.05526/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":"2111.05526","created_at":"2026-07-05T03:30:45.546701+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.05526v1","created_at":"2026-07-05T03:30:45.546701+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.05526","created_at":"2026-07-05T03:30:45.546701+00:00"},{"alias_kind":"pith_short_12","alias_value":"RYWATVXD5LYT","created_at":"2026-07-05T03:30:45.546701+00:00"},{"alias_kind":"pith_short_16","alias_value":"RYWATVXD5LYTEFJN","created_at":"2026-07-05T03:30:45.546701+00:00"},{"alias_kind":"pith_short_8","alias_value":"RYWATVXD","created_at":"2026-07-05T03:30:45.546701+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/RYWATVXD5LYTEFJNUIHHDS2ZYV","json":"https://pith.science/pith/RYWATVXD5LYTEFJNUIHHDS2ZYV.json","graph_json":"https://pith.science/api/pith-number/RYWATVXD5LYTEFJNUIHHDS2ZYV/graph.json","events_json":"https://pith.science/api/pith-number/RYWATVXD5LYTEFJNUIHHDS2ZYV/events.json","paper":"https://pith.science/paper/RYWATVXD"},"agent_actions":{"view_html":"https://pith.science/pith/RYWATVXD5LYTEFJNUIHHDS2ZYV","download_json":"https://pith.science/pith/RYWATVXD5LYTEFJNUIHHDS2ZYV.json","view_paper":"https://pith.science/paper/RYWATVXD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.05526&json=true","fetch_graph":"https://pith.science/api/pith-number/RYWATVXD5LYTEFJNUIHHDS2ZYV/graph.json","fetch_events":"https://pith.science/api/pith-number/RYWATVXD5LYTEFJNUIHHDS2ZYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RYWATVXD5LYTEFJNUIHHDS2ZYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RYWATVXD5LYTEFJNUIHHDS2ZYV/action/storage_attestation","attest_author":"https://pith.science/pith/RYWATVXD5LYTEFJNUIHHDS2ZYV/action/author_attestation","sign_citation":"https://pith.science/pith/RYWATVXD5LYTEFJNUIHHDS2ZYV/action/citation_signature","submit_replication":"https://pith.science/pith/RYWATVXD5LYTEFJNUIHHDS2ZYV/action/replication_record"}},"created_at":"2026-07-05T03:30:45.546701+00:00","updated_at":"2026-07-05T03:30:45.546701+00:00"}