{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:COUYBYX54SJXD26WBOZWY4EFNX","short_pith_number":"pith:COUYBYX5","schema_version":"1.0","canonical_sha256":"13a980e2fde49371ebd60bb36c70856de7bf41bcca7acc750442b8ea555a7a3d","source":{"kind":"arxiv","id":"2308.10794","version":1},"attestation_state":"computed","paper":{"title":"MGMAE: Motion Guided Masking for Video Masked Autoencoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bingkun Huang, Guozhen Zhang, Limin Wang, Yu Qiao, Zhiyu Zhao","submitted_at":"2023-08-21T15:39:41Z","abstract_excerpt":"Masked autoencoding has shown excellent performance on self-supervised video representation learning. Temporal redundancy has led to a high masking ratio and customized masking strategy in VideoMAE. In this paper, we aim to further improve the performance of video masked autoencoding by introducing a motion guided masking strategy. Our key insight is that motion is a general and unique prior in video, which should be taken into account during masked pre-training. Our motion guided masking explicitly incorporates motion information to build temporal consistent masking volume. Based on this mask"},"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":"2308.10794","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-21T15:39:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"59c24663f23fd0480b9839a5286c7cd1db8ba58c2b0f165745edb321a0c51296","abstract_canon_sha256":"8a9d90af187fde69943ac0b8f7fdc32a97147cb6abbb5ccc56e991921f463a97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:14.901479Z","signature_b64":"45bNlXqO2W+qHvojetZ0YtfWXuk1P1KhdqYpM4m/XBW60UjTuZXMOFZldug9PXF1yJicwp6qt6VaDiPn9IO2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13a980e2fde49371ebd60bb36c70856de7bf41bcca7acc750442b8ea555a7a3d","last_reissued_at":"2026-07-05T06:43:14.901068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:14.901068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MGMAE: Motion Guided Masking for Video Masked Autoencoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bingkun Huang, Guozhen Zhang, Limin Wang, Yu Qiao, Zhiyu Zhao","submitted_at":"2023-08-21T15:39:41Z","abstract_excerpt":"Masked autoencoding has shown excellent performance on self-supervised video representation learning. Temporal redundancy has led to a high masking ratio and customized masking strategy in VideoMAE. In this paper, we aim to further improve the performance of video masked autoencoding by introducing a motion guided masking strategy. Our key insight is that motion is a general and unique prior in video, which should be taken into account during masked pre-training. Our motion guided masking explicitly incorporates motion information to build temporal consistent masking volume. Based on this mask"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10794","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/2308.10794/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":"2308.10794","created_at":"2026-07-05T06:43:14.901124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.10794v1","created_at":"2026-07-05T06:43:14.901124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10794","created_at":"2026-07-05T06:43:14.901124+00:00"},{"alias_kind":"pith_short_12","alias_value":"COUYBYX54SJX","created_at":"2026-07-05T06:43:14.901124+00:00"},{"alias_kind":"pith_short_16","alias_value":"COUYBYX54SJXD26W","created_at":"2026-07-05T06:43:14.901124+00:00"},{"alias_kind":"pith_short_8","alias_value":"COUYBYX5","created_at":"2026-07-05T06:43:14.901124+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.11400","citing_title":"The model is the message: Lightweight convolutional autoencoders applied to noisy imaging data for planetary science and astrobiology","ref_index":2023,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/COUYBYX54SJXD26WBOZWY4EFNX","json":"https://pith.science/pith/COUYBYX54SJXD26WBOZWY4EFNX.json","graph_json":"https://pith.science/api/pith-number/COUYBYX54SJXD26WBOZWY4EFNX/graph.json","events_json":"https://pith.science/api/pith-number/COUYBYX54SJXD26WBOZWY4EFNX/events.json","paper":"https://pith.science/paper/COUYBYX5"},"agent_actions":{"view_html":"https://pith.science/pith/COUYBYX54SJXD26WBOZWY4EFNX","download_json":"https://pith.science/pith/COUYBYX54SJXD26WBOZWY4EFNX.json","view_paper":"https://pith.science/paper/COUYBYX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.10794&json=true","fetch_graph":"https://pith.science/api/pith-number/COUYBYX54SJXD26WBOZWY4EFNX/graph.json","fetch_events":"https://pith.science/api/pith-number/COUYBYX54SJXD26WBOZWY4EFNX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/COUYBYX54SJXD26WBOZWY4EFNX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/COUYBYX54SJXD26WBOZWY4EFNX/action/storage_attestation","attest_author":"https://pith.science/pith/COUYBYX54SJXD26WBOZWY4EFNX/action/author_attestation","sign_citation":"https://pith.science/pith/COUYBYX54SJXD26WBOZWY4EFNX/action/citation_signature","submit_replication":"https://pith.science/pith/COUYBYX54SJXD26WBOZWY4EFNX/action/replication_record"}},"created_at":"2026-07-05T06:43:14.901124+00:00","updated_at":"2026-07-05T06:43:14.901124+00:00"}