{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7L2AAT5XB2JP2GYMTEIHAGJUPQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6344c2762baec65210969304e9d2cc51f28483734cd5742334fcd1dd57f73c97","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-02T16:40:42Z","title_canon_sha256":"03b5ec785dadb22e63099636ebb7839946d27bc03d67d6e32354689f39006f47"},"schema_version":"1.0","source":{"id":"2304.00571","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.00571","created_at":"2026-07-05T10:44:12Z"},{"alias_kind":"arxiv_version","alias_value":"2304.00571v3","created_at":"2026-07-05T10:44:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00571","created_at":"2026-07-05T10:44:12Z"},{"alias_kind":"pith_short_12","alias_value":"7L2AAT5XB2JP","created_at":"2026-07-05T10:44:12Z"},{"alias_kind":"pith_short_16","alias_value":"7L2AAT5XB2JP2GYM","created_at":"2026-07-05T10:44:12Z"},{"alias_kind":"pith_short_8","alias_value":"7L2AAT5X","created_at":"2026-07-05T10:44:12Z"}],"graph_snapshots":[{"event_id":"sha256:2b65b6f1e2aa569fed4e5c15afce6d2d82c7362b3ae4c5f02c6c991a6f1a57b2","target":"graph","created_at":"2026-07-05T10:44:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2304.00571/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Antoni B. Chan, Baoyuan Wu, Qiangqiang Wu, Tianyu Yang, Wei Lin, Ziquan Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-02T16:40:42Z","title":"DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00571","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:eb43b6a2ac34ca324b3411310f7b887265d10885428e7345d9e5e291f91e77d7","target":"record","created_at":"2026-07-05T10:44:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6344c2762baec65210969304e9d2cc51f28483734cd5742334fcd1dd57f73c97","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-02T16:40:42Z","title_canon_sha256":"03b5ec785dadb22e63099636ebb7839946d27bc03d67d6e32354689f39006f47"},"schema_version":"1.0","source":{"id":"2304.00571","kind":"arxiv","version":3}},"canonical_sha256":"faf4004fb70e92fd1b0c99107019347c28889c67c719caf2b2b1572a68b9ab15","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"faf4004fb70e92fd1b0c99107019347c28889c67c719caf2b2b1572a68b9ab15","first_computed_at":"2026-07-05T10:44:12.257912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:12.257912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"diRWOOO78mxWkxbke6u0AkQ7AdeEX4iS+cGZBjLSIhb4kJrqkP1TJxWXpAR+nKXL/NuKW8C/Gygi4LbHxqjbDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:12.258407Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.00571","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb43b6a2ac34ca324b3411310f7b887265d10885428e7345d9e5e291f91e77d7","sha256:2b65b6f1e2aa569fed4e5c15afce6d2d82c7362b3ae4c5f02c6c991a6f1a57b2"],"state_sha256":"aa7bc96e3b80072d80413efbd30c53603c04e438888774c612be64dfe72f6185"}