{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VQPY2WLH7RO3OPOCDDRWYW5VVA","short_pith_number":"pith:VQPY2WLH","schema_version":"1.0","canonical_sha256":"ac1f8d5967fc5db73dc218e36c5bb5a80bf4f5ead599ddf7edfadf5f0001aaa9","source":{"kind":"arxiv","id":"2007.12130","version":1},"attestation_state":"computed","paper":{"title":"Sound2Sight: Generating Visual Dynamics from Sound and Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Anoop Cherian, Moitreya Chatterjee, Narendra Ahuja","submitted_at":"2020-07-23T16:57:44Z","abstract_excerpt":"Learning associations across modalities is critical for robust multimodal reasoning, especially when a modality may be missing during inference. In this paper, we study this problem in the context of audio-conditioned visual synthesis -- a task that is important, for example, in occlusion reasoning. Specifically, our goal is to generate future video frames and their motion dynamics conditioned on audio and a few past frames. To tackle this problem, we present Sound2Sight, a deep variational framework, that is trained to learn a per frame stochastic prior conditioned on a joint embedding of aud"},"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":"2007.12130","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-23T16:57:44Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"8d3171b5b22074b46baf5e4767476591edfc7651569696535e10709c4173df29","abstract_canon_sha256":"a131cbb8dc9250cecfc2871538551412636cf225a17d836f41e0bee51b1dc838"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:21:43.688900Z","signature_b64":"+skMrUwTombfI/a1qEWm2ah1tNz1xUm2usF+j6/u4+2SuvPsrISPGODu69hgTC+qEjOkw/cAT0OximPY/aFKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac1f8d5967fc5db73dc218e36c5bb5a80bf4f5ead599ddf7edfadf5f0001aaa9","last_reissued_at":"2026-07-05T01:21:43.688522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:21:43.688522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sound2Sight: Generating Visual Dynamics from Sound and Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Anoop Cherian, Moitreya Chatterjee, Narendra Ahuja","submitted_at":"2020-07-23T16:57:44Z","abstract_excerpt":"Learning associations across modalities is critical for robust multimodal reasoning, especially when a modality may be missing during inference. In this paper, we study this problem in the context of audio-conditioned visual synthesis -- a task that is important, for example, in occlusion reasoning. Specifically, our goal is to generate future video frames and their motion dynamics conditioned on audio and a few past frames. To tackle this problem, we present Sound2Sight, a deep variational framework, that is trained to learn a per frame stochastic prior conditioned on a joint embedding of aud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.12130","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/2007.12130/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":"2007.12130","created_at":"2026-07-05T01:21:43.688581+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.12130v1","created_at":"2026-07-05T01:21:43.688581+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.12130","created_at":"2026-07-05T01:21:43.688581+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQPY2WLH7RO3","created_at":"2026-07-05T01:21:43.688581+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQPY2WLH7RO3OPOC","created_at":"2026-07-05T01:21:43.688581+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQPY2WLH","created_at":"2026-07-05T01:21:43.688581+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/VQPY2WLH7RO3OPOCDDRWYW5VVA","json":"https://pith.science/pith/VQPY2WLH7RO3OPOCDDRWYW5VVA.json","graph_json":"https://pith.science/api/pith-number/VQPY2WLH7RO3OPOCDDRWYW5VVA/graph.json","events_json":"https://pith.science/api/pith-number/VQPY2WLH7RO3OPOCDDRWYW5VVA/events.json","paper":"https://pith.science/paper/VQPY2WLH"},"agent_actions":{"view_html":"https://pith.science/pith/VQPY2WLH7RO3OPOCDDRWYW5VVA","download_json":"https://pith.science/pith/VQPY2WLH7RO3OPOCDDRWYW5VVA.json","view_paper":"https://pith.science/paper/VQPY2WLH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.12130&json=true","fetch_graph":"https://pith.science/api/pith-number/VQPY2WLH7RO3OPOCDDRWYW5VVA/graph.json","fetch_events":"https://pith.science/api/pith-number/VQPY2WLH7RO3OPOCDDRWYW5VVA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQPY2WLH7RO3OPOCDDRWYW5VVA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQPY2WLH7RO3OPOCDDRWYW5VVA/action/storage_attestation","attest_author":"https://pith.science/pith/VQPY2WLH7RO3OPOCDDRWYW5VVA/action/author_attestation","sign_citation":"https://pith.science/pith/VQPY2WLH7RO3OPOCDDRWYW5VVA/action/citation_signature","submit_replication":"https://pith.science/pith/VQPY2WLH7RO3OPOCDDRWYW5VVA/action/replication_record"}},"created_at":"2026-07-05T01:21:43.688581+00:00","updated_at":"2026-07-05T01:21:43.688581+00:00"}