{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2CUKB5GN76GXOA4C4SLCOA7K27","short_pith_number":"pith:2CUKB5GN","schema_version":"1.0","canonical_sha256":"d0a8a0f4cdff8d770382e4962703ead7eac620c7b730221d9cfc917f9fd5c2a3","source":{"kind":"arxiv","id":"2104.11178","version":3},"attestation_state":"computed","paper":{"title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM","eess.IV"],"primary_cat":"cs.CV","authors_text":"Boqing Gong, Hassan Akbari, Liangzhe Yuan, Rui Qian, Shih-Fu Chang, Wei-Hong Chuang, Yin Cui","submitted_at":"2021-04-22T17:07:41Z","abstract_excerpt":"We present a framework for learning multimodal representations from unlabeled data using convolution-free Transformer architectures. Specifically, our Video-Audio-Text Transformer (VATT) takes raw signals as inputs and extracts multimodal representations that are rich enough to benefit a variety of downstream tasks. We train VATT end-to-end from scratch using multimodal contrastive losses and evaluate its performance by the downstream tasks of video action recognition, audio event classification, image classification, and text-to-video retrieval. Furthermore, we study a modality-agnostic, sing"},"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":"2104.11178","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-22T17:07:41Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","eess.IV"],"title_canon_sha256":"723966a6d8647792a9ce1631471f9295068c6b9a223bd066cba0d4121ca2d9c6","abstract_canon_sha256":"90e7a5930654c287e532173ba08db5e513ddacc927016c388b1536747e8e6b5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:18.201202Z","signature_b64":"XueY2Tq6gOtxgnlZcCkXPMfrJKfDUePdN/RR8x/q/Bapj6oekLZntrkzJlYTftURg3QNIJYnSyhYpVN8OF4ICA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0a8a0f4cdff8d770382e4962703ead7eac620c7b730221d9cfc917f9fd5c2a3","last_reissued_at":"2026-07-05T03:38:18.200719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:18.200719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM","eess.IV"],"primary_cat":"cs.CV","authors_text":"Boqing Gong, Hassan Akbari, Liangzhe Yuan, Rui Qian, Shih-Fu Chang, Wei-Hong Chuang, Yin Cui","submitted_at":"2021-04-22T17:07:41Z","abstract_excerpt":"We present a framework for learning multimodal representations from unlabeled data using convolution-free Transformer architectures. Specifically, our Video-Audio-Text Transformer (VATT) takes raw signals as inputs and extracts multimodal representations that are rich enough to benefit a variety of downstream tasks. We train VATT end-to-end from scratch using multimodal contrastive losses and evaluate its performance by the downstream tasks of video action recognition, audio event classification, image classification, and text-to-video retrieval. Furthermore, we study a modality-agnostic, sing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.11178","kind":"arxiv","version":3},"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/2104.11178/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":"2104.11178","created_at":"2026-07-05T03:38:18.200777+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.11178v3","created_at":"2026-07-05T03:38:18.200777+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.11178","created_at":"2026-07-05T03:38:18.200777+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CUKB5GN76GX","created_at":"2026-07-05T03:38:18.200777+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CUKB5GN76GXOA4C","created_at":"2026-07-05T03:38:18.200777+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CUKB5GN","created_at":"2026-07-05T03:38:18.200777+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12362","citing_title":"Latent World Recovery for Multimodal Learning with Missing Modalities","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21420","citing_title":"ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2CUKB5GN76GXOA4C4SLCOA7K27","json":"https://pith.science/pith/2CUKB5GN76GXOA4C4SLCOA7K27.json","graph_json":"https://pith.science/api/pith-number/2CUKB5GN76GXOA4C4SLCOA7K27/graph.json","events_json":"https://pith.science/api/pith-number/2CUKB5GN76GXOA4C4SLCOA7K27/events.json","paper":"https://pith.science/paper/2CUKB5GN"},"agent_actions":{"view_html":"https://pith.science/pith/2CUKB5GN76GXOA4C4SLCOA7K27","download_json":"https://pith.science/pith/2CUKB5GN76GXOA4C4SLCOA7K27.json","view_paper":"https://pith.science/paper/2CUKB5GN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.11178&json=true","fetch_graph":"https://pith.science/api/pith-number/2CUKB5GN76GXOA4C4SLCOA7K27/graph.json","fetch_events":"https://pith.science/api/pith-number/2CUKB5GN76GXOA4C4SLCOA7K27/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CUKB5GN76GXOA4C4SLCOA7K27/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CUKB5GN76GXOA4C4SLCOA7K27/action/storage_attestation","attest_author":"https://pith.science/pith/2CUKB5GN76GXOA4C4SLCOA7K27/action/author_attestation","sign_citation":"https://pith.science/pith/2CUKB5GN76GXOA4C4SLCOA7K27/action/citation_signature","submit_replication":"https://pith.science/pith/2CUKB5GN76GXOA4C4SLCOA7K27/action/replication_record"}},"created_at":"2026-07-05T03:38:18.200777+00:00","updated_at":"2026-07-05T03:38:18.200777+00:00"}