{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:324Z3HOSR2MEDSZ3YHJMFNEPBD","short_pith_number":"pith:324Z3HOS","schema_version":"1.0","canonical_sha256":"deb99d9dd28e9841cb3bc1d2c2b48f08e7630c966ed0f87d31879da240a5d792","source":{"kind":"arxiv","id":"2303.01237","version":1},"attestation_state":"computed","paper":{"title":"FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dasong Li, Hongsheng Li, Hongwei Qin, Jifeng Dai, Ka Chun Cheung, Manyuan Zhang, Simon See, Xiaoyu Shi, Zhaoyang Huang","submitted_at":"2023-03-02T13:28:07Z","abstract_excerpt":"FlowFormer introduces a transformer architecture into optical flow estimation and achieves state-of-the-art performance. The core component of FlowFormer is the transformer-based cost-volume encoder. Inspired by the recent success of masked autoencoding (MAE) pretraining in unleashing transformers' capacity of encoding visual representation, we propose Masked Cost Volume Autoencoding (MCVA) to enhance FlowFormer by pretraining the cost-volume encoder with a novel MAE scheme. Firstly, we introduce a block-sharing masking strategy to prevent masked information leakage, as the cost maps of neighb"},"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":"2303.01237","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-02T13:28:07Z","cross_cats_sorted":[],"title_canon_sha256":"c8381d174cd21c683f046f08036cd8fb128bac4a20466422038fbb62247ad19c","abstract_canon_sha256":"fef29ad9b08547dbb62187d2df30d53abc383d5ba469692c465f3927d00a74a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:28.621399Z","signature_b64":"zuK3CslKn7iH6lhG8fQzZX05hFh125bN+sABzGbj4qNtVAwL60cqWMRFxaqXhDlG5jSBkIqdl2fTb0JLf1GxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"deb99d9dd28e9841cb3bc1d2c2b48f08e7630c966ed0f87d31879da240a5d792","last_reissued_at":"2026-07-05T05:47:28.620858Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:28.620858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dasong Li, Hongsheng Li, Hongwei Qin, Jifeng Dai, Ka Chun Cheung, Manyuan Zhang, Simon See, Xiaoyu Shi, Zhaoyang Huang","submitted_at":"2023-03-02T13:28:07Z","abstract_excerpt":"FlowFormer introduces a transformer architecture into optical flow estimation and achieves state-of-the-art performance. The core component of FlowFormer is the transformer-based cost-volume encoder. Inspired by the recent success of masked autoencoding (MAE) pretraining in unleashing transformers' capacity of encoding visual representation, we propose Masked Cost Volume Autoencoding (MCVA) to enhance FlowFormer by pretraining the cost-volume encoder with a novel MAE scheme. Firstly, we introduce a block-sharing masking strategy to prevent masked information leakage, as the cost maps of neighb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.01237","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/2303.01237/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":"2303.01237","created_at":"2026-07-05T05:47:28.620920+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.01237v1","created_at":"2026-07-05T05:47:28.620920+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.01237","created_at":"2026-07-05T05:47:28.620920+00:00"},{"alias_kind":"pith_short_12","alias_value":"324Z3HOSR2ME","created_at":"2026-07-05T05:47:28.620920+00:00"},{"alias_kind":"pith_short_16","alias_value":"324Z3HOSR2MEDSZ3","created_at":"2026-07-05T05:47:28.620920+00:00"},{"alias_kind":"pith_short_8","alias_value":"324Z3HOS","created_at":"2026-07-05T05:47:28.620920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13273","citing_title":"CompactFlowNet: Efficient Real-time Optical Flow Estimation on Mobile Devices","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/324Z3HOSR2MEDSZ3YHJMFNEPBD","json":"https://pith.science/pith/324Z3HOSR2MEDSZ3YHJMFNEPBD.json","graph_json":"https://pith.science/api/pith-number/324Z3HOSR2MEDSZ3YHJMFNEPBD/graph.json","events_json":"https://pith.science/api/pith-number/324Z3HOSR2MEDSZ3YHJMFNEPBD/events.json","paper":"https://pith.science/paper/324Z3HOS"},"agent_actions":{"view_html":"https://pith.science/pith/324Z3HOSR2MEDSZ3YHJMFNEPBD","download_json":"https://pith.science/pith/324Z3HOSR2MEDSZ3YHJMFNEPBD.json","view_paper":"https://pith.science/paper/324Z3HOS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.01237&json=true","fetch_graph":"https://pith.science/api/pith-number/324Z3HOSR2MEDSZ3YHJMFNEPBD/graph.json","fetch_events":"https://pith.science/api/pith-number/324Z3HOSR2MEDSZ3YHJMFNEPBD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/324Z3HOSR2MEDSZ3YHJMFNEPBD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/324Z3HOSR2MEDSZ3YHJMFNEPBD/action/storage_attestation","attest_author":"https://pith.science/pith/324Z3HOSR2MEDSZ3YHJMFNEPBD/action/author_attestation","sign_citation":"https://pith.science/pith/324Z3HOSR2MEDSZ3YHJMFNEPBD/action/citation_signature","submit_replication":"https://pith.science/pith/324Z3HOSR2MEDSZ3YHJMFNEPBD/action/replication_record"}},"created_at":"2026-07-05T05:47:28.620920+00:00","updated_at":"2026-07-05T05:47:28.620920+00:00"}