{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4SUUPXFFHQWRLJEYBJGNFNWLAD","short_pith_number":"pith:4SUUPXFF","schema_version":"1.0","canonical_sha256":"e4a947dca53c2d15a4980a4cd2b6cb00f8d95be9a7662aff396151bbd435a0a8","source":{"kind":"arxiv","id":"2203.12602","version":3},"attestation_state":"computed","paper":{"title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jue Wang, Limin Wang, Yibing Song, Zhan Tong","submitted_at":"2022-03-23T17:55:10Z","abstract_excerpt":"Pre-training video transformers on extra large-scale datasets is generally required to achieve premier performance on relatively small datasets. In this paper, we show that video masked autoencoders (VideoMAE) are data-efficient learners for self-supervised video pre-training (SSVP). We are inspired by the recent ImageMAE and propose customized video tube masking with an extremely high ratio. This simple design makes video reconstruction a more challenging self-supervision task, thus encouraging extracting more effective video representations during this pre-training process. We obtain three i"},"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":"2203.12602","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-23T17:55:10Z","cross_cats_sorted":[],"title_canon_sha256":"0086e8235825feeb15c607302e68bb38086f8ab58715ed81414e1e5f9ee68c9e","abstract_canon_sha256":"2dbfea5b8af6064d6a3194dac8f60dd8d5a7b36727e74c652ea5b319fbbaf17c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:40.654936Z","signature_b64":"OyXUWy0JHwD2rEJ6p8OHolA9JDI250+qtemeXlhcXPQxmb+zKWD4dFAPFFnAHDfMXhSwACxAqprJqqdzYbleAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4a947dca53c2d15a4980a4cd2b6cb00f8d95be9a7662aff396151bbd435a0a8","last_reissued_at":"2026-07-05T05:07:40.654324Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:40.654324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jue Wang, Limin Wang, Yibing Song, Zhan Tong","submitted_at":"2022-03-23T17:55:10Z","abstract_excerpt":"Pre-training video transformers on extra large-scale datasets is generally required to achieve premier performance on relatively small datasets. In this paper, we show that video masked autoencoders (VideoMAE) are data-efficient learners for self-supervised video pre-training (SSVP). We are inspired by the recent ImageMAE and propose customized video tube masking with an extremely high ratio. This simple design makes video reconstruction a more challenging self-supervision task, thus encouraging extracting more effective video representations during this pre-training process. We obtain three i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.12602","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/2203.12602/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":"2203.12602","created_at":"2026-07-05T05:07:40.654397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.12602v3","created_at":"2026-07-05T05:07:40.654397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.12602","created_at":"2026-07-05T05:07:40.654397+00:00"},{"alias_kind":"pith_short_12","alias_value":"4SUUPXFFHQWR","created_at":"2026-07-05T05:07:40.654397+00:00"},{"alias_kind":"pith_short_16","alias_value":"4SUUPXFFHQWRLJEY","created_at":"2026-07-05T05:07:40.654397+00:00"},{"alias_kind":"pith_short_8","alias_value":"4SUUPXFF","created_at":"2026-07-05T05:07:40.654397+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22494","citing_title":"Deep Learning-Based Sign Language Recognition from Videos and Cross-Lingual Translation to Indian Vernaculars","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09646","citing_title":"Do Video Foundation Models Understand Intuitive Physics? A Layerwise Probing Analysis","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05736","citing_title":"VTI-CoT: Visual-Textual Interleaved Chain of Thought for Video Reasoning","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01884","citing_title":"EVA-Net: Subject-Independent EEG Motor Decoding with Video-Derived Motor Priors","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29504","citing_title":"Empirical Evaluation of Multi-Modal Touch Detection in Over-the-Shoulder Video Surveillance","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08674","citing_title":"BioVid: Autoregressive Video Generation with Biological Behavior Semantic Comprehension","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23428","citing_title":"FAST-ME: Foundation-aware Adaptive Stopping for Motion Estimation for Efficient IoT Video Analysis","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18878","citing_title":"Prognostic Value of Lung Ultrasound Biomarkers for Readmission Risk in Congestive Heart Failure: A Pilot Data-Driven Analysis","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17311","citing_title":"SpecSem-Net: Integrating Spectral and Semantic Features for Robust AI-generated Video Detection","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2310.01852","citing_title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","ref_index":124,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19683","citing_title":"Mask World Model: Predicting What Matters for Robust Robot Policy Learning","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10333","citing_title":"Zero-shot World Models Are Developmentally Efficient Learners","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06783","citing_title":"Insights from Visual Cognition: Understanding Human Action Dynamics with Overall Glance and Refined Gaze Transformer","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15096","citing_title":"Beyond Independent Frames: Latent Attention Masked Autoencoders for Multi-View Echocardiography","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02094","citing_title":"SignMAE: Segmentation-Driven Self-Supervised Learning for Sign Language Recognition","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4SUUPXFFHQWRLJEYBJGNFNWLAD","json":"https://pith.science/pith/4SUUPXFFHQWRLJEYBJGNFNWLAD.json","graph_json":"https://pith.science/api/pith-number/4SUUPXFFHQWRLJEYBJGNFNWLAD/graph.json","events_json":"https://pith.science/api/pith-number/4SUUPXFFHQWRLJEYBJGNFNWLAD/events.json","paper":"https://pith.science/paper/4SUUPXFF"},"agent_actions":{"view_html":"https://pith.science/pith/4SUUPXFFHQWRLJEYBJGNFNWLAD","download_json":"https://pith.science/pith/4SUUPXFFHQWRLJEYBJGNFNWLAD.json","view_paper":"https://pith.science/paper/4SUUPXFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.12602&json=true","fetch_graph":"https://pith.science/api/pith-number/4SUUPXFFHQWRLJEYBJGNFNWLAD/graph.json","fetch_events":"https://pith.science/api/pith-number/4SUUPXFFHQWRLJEYBJGNFNWLAD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4SUUPXFFHQWRLJEYBJGNFNWLAD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4SUUPXFFHQWRLJEYBJGNFNWLAD/action/storage_attestation","attest_author":"https://pith.science/pith/4SUUPXFFHQWRLJEYBJGNFNWLAD/action/author_attestation","sign_citation":"https://pith.science/pith/4SUUPXFFHQWRLJEYBJGNFNWLAD/action/citation_signature","submit_replication":"https://pith.science/pith/4SUUPXFFHQWRLJEYBJGNFNWLAD/action/replication_record"}},"created_at":"2026-07-05T05:07:40.654397+00:00","updated_at":"2026-07-05T05:07:40.654397+00:00"}