{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7L2AAT5XB2JP2GYMTEIHAGJUPQ","short_pith_number":"pith:7L2AAT5X","schema_version":"1.0","canonical_sha256":"faf4004fb70e92fd1b0c99107019347c28889c67c719caf2b2b1572a68b9ab15","source":{"kind":"arxiv","id":"2304.00571","version":3},"attestation_state":"computed","paper":{"title":"DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antoni B. Chan, Baoyuan Wu, Qiangqiang Wu, Tianyu Yang, Wei Lin, Ziquan Liu","submitted_at":"2023-04-02T16:40:42Z","abstract_excerpt":"This paper studies masked autoencoder (MAE) video pre-training for various temporal matching-based downstream tasks, i.e., object-level tracking tasks including video object tracking (VOT) and video object segmentation (VOS), self-supervised visual correspondence learning, dense tracking tasks including optical flow estimation and long-term point tracking, and 3D point cloud tracking. Specifically, our work explores to provide a general representation to boost the temporal matching ability in various downstream tracking tasks. To achieve this, we firstly find that a simple extension of MAE, wh"},"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":"2304.00571","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-02T16:40:42Z","cross_cats_sorted":[],"title_canon_sha256":"03b5ec785dadb22e63099636ebb7839946d27bc03d67d6e32354689f39006f47","abstract_canon_sha256":"6344c2762baec65210969304e9d2cc51f28483734cd5742334fcd1dd57f73c97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:12.258407Z","signature_b64":"diRWOOO78mxWkxbke6u0AkQ7AdeEX4iS+cGZBjLSIhb4kJrqkP1TJxWXpAR+nKXL/NuKW8C/Gygi4LbHxqjbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"faf4004fb70e92fd1b0c99107019347c28889c67c719caf2b2b1572a68b9ab15","last_reissued_at":"2026-07-05T10:44:12.257912Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:12.257912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antoni B. Chan, Baoyuan Wu, Qiangqiang Wu, Tianyu Yang, Wei Lin, Ziquan Liu","submitted_at":"2023-04-02T16:40:42Z","abstract_excerpt":"This paper studies masked autoencoder (MAE) video pre-training for various temporal matching-based downstream tasks, i.e., object-level tracking tasks including video object tracking (VOT) and video object segmentation (VOS), self-supervised visual correspondence learning, dense tracking tasks including optical flow estimation and long-term point tracking, and 3D point cloud tracking. Specifically, our work explores to provide a general representation to boost the temporal matching ability in various downstream tracking tasks. To achieve this, we firstly find that a simple extension of MAE, wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00571","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/2304.00571/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":"2304.00571","created_at":"2026-07-05T10:44:12.257970+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.00571v3","created_at":"2026-07-05T10:44:12.257970+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00571","created_at":"2026-07-05T10:44:12.257970+00:00"},{"alias_kind":"pith_short_12","alias_value":"7L2AAT5XB2JP","created_at":"2026-07-05T10:44:12.257970+00:00"},{"alias_kind":"pith_short_16","alias_value":"7L2AAT5XB2JP2GYM","created_at":"2026-07-05T10:44:12.257970+00:00"},{"alias_kind":"pith_short_8","alias_value":"7L2AAT5X","created_at":"2026-07-05T10:44:12.257970+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06092","citing_title":"Boosting Self-Supervised Tracking with Contextual Prompts and Noise Learning","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07064","citing_title":"Learning to Track Instance from Single Nature Language Description","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7L2AAT5XB2JP2GYMTEIHAGJUPQ","json":"https://pith.science/pith/7L2AAT5XB2JP2GYMTEIHAGJUPQ.json","graph_json":"https://pith.science/api/pith-number/7L2AAT5XB2JP2GYMTEIHAGJUPQ/graph.json","events_json":"https://pith.science/api/pith-number/7L2AAT5XB2JP2GYMTEIHAGJUPQ/events.json","paper":"https://pith.science/paper/7L2AAT5X"},"agent_actions":{"view_html":"https://pith.science/pith/7L2AAT5XB2JP2GYMTEIHAGJUPQ","download_json":"https://pith.science/pith/7L2AAT5XB2JP2GYMTEIHAGJUPQ.json","view_paper":"https://pith.science/paper/7L2AAT5X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.00571&json=true","fetch_graph":"https://pith.science/api/pith-number/7L2AAT5XB2JP2GYMTEIHAGJUPQ/graph.json","fetch_events":"https://pith.science/api/pith-number/7L2AAT5XB2JP2GYMTEIHAGJUPQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7L2AAT5XB2JP2GYMTEIHAGJUPQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7L2AAT5XB2JP2GYMTEIHAGJUPQ/action/storage_attestation","attest_author":"https://pith.science/pith/7L2AAT5XB2JP2GYMTEIHAGJUPQ/action/author_attestation","sign_citation":"https://pith.science/pith/7L2AAT5XB2JP2GYMTEIHAGJUPQ/action/citation_signature","submit_replication":"https://pith.science/pith/7L2AAT5XB2JP2GYMTEIHAGJUPQ/action/replication_record"}},"created_at":"2026-07-05T10:44:12.257970+00:00","updated_at":"2026-07-05T10:44:12.257970+00:00"}