{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OGNF6TKRRKNGC7WX4QYV3ML7J3","short_pith_number":"pith:OGNF6TKR","schema_version":"1.0","canonical_sha256":"719a5f4d518a9a617ed7e4315db17f4eca67d5773771bca674963c103fe0444b","source":{"kind":"arxiv","id":"2302.05744","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Kot, Rizhao Cai, Xin Liu, Yawen Cui, Yongjian Hu, Zitong Yu","submitted_at":"2023-02-11T17:02:34Z","abstract_excerpt":"Recently, vision transformer (ViT) based multimodal learning methods have been proposed to improve the robustness of face anti-spoofing (FAS) systems. However, there are still no works to explore the fundamental natures (\\textit{e.g.}, modality-aware inputs, suitable multimodal pre-training, and efficient finetuning) in vanilla ViT for multimodal FAS. In this paper, we investigate three key factors (i.e., inputs, pre-training, and finetuning) in ViT for multimodal FAS with RGB, Infrared (IR), and Depth. First, in terms of the ViT inputs, we find that leveraging local feature descriptors benefi"},"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":"2302.05744","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-11T17:02:34Z","cross_cats_sorted":[],"title_canon_sha256":"8a6fd035f9684a801ca98f26da17b62c0be46a96d202ed678a0ad616c7072b4b","abstract_canon_sha256":"0ae56760dc2183a30744bd42a83f9cbcd028119b5cf19fe794e13301219800db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:57.808614Z","signature_b64":"OvCY4GKF119bLXwysHTLCuTTZOu4PEz71wQPlOI9mhC4RrST6ec7f9cKzvYcJnicer1RM1EFkd/5ZwhfvIuoCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"719a5f4d518a9a617ed7e4315db17f4eca67d5773771bca674963c103fe0444b","last_reissued_at":"2026-07-05T05:40:57.808172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:57.808172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Kot, Rizhao Cai, Xin Liu, Yawen Cui, Yongjian Hu, Zitong Yu","submitted_at":"2023-02-11T17:02:34Z","abstract_excerpt":"Recently, vision transformer (ViT) based multimodal learning methods have been proposed to improve the robustness of face anti-spoofing (FAS) systems. However, there are still no works to explore the fundamental natures (\\textit{e.g.}, modality-aware inputs, suitable multimodal pre-training, and efficient finetuning) in vanilla ViT for multimodal FAS. In this paper, we investigate three key factors (i.e., inputs, pre-training, and finetuning) in ViT for multimodal FAS with RGB, Infrared (IR), and Depth. First, in terms of the ViT inputs, we find that leveraging local feature descriptors benefi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05744","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/2302.05744/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":"2302.05744","created_at":"2026-07-05T05:40:57.808226+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.05744v1","created_at":"2026-07-05T05:40:57.808226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05744","created_at":"2026-07-05T05:40:57.808226+00:00"},{"alias_kind":"pith_short_12","alias_value":"OGNF6TKRRKNG","created_at":"2026-07-05T05:40:57.808226+00:00"},{"alias_kind":"pith_short_16","alias_value":"OGNF6TKRRKNGC7WX","created_at":"2026-07-05T05:40:57.808226+00:00"},{"alias_kind":"pith_short_8","alias_value":"OGNF6TKR","created_at":"2026-07-05T05:40:57.808226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OGNF6TKRRKNGC7WX4QYV3ML7J3","json":"https://pith.science/pith/OGNF6TKRRKNGC7WX4QYV3ML7J3.json","graph_json":"https://pith.science/api/pith-number/OGNF6TKRRKNGC7WX4QYV3ML7J3/graph.json","events_json":"https://pith.science/api/pith-number/OGNF6TKRRKNGC7WX4QYV3ML7J3/events.json","paper":"https://pith.science/paper/OGNF6TKR"},"agent_actions":{"view_html":"https://pith.science/pith/OGNF6TKRRKNGC7WX4QYV3ML7J3","download_json":"https://pith.science/pith/OGNF6TKRRKNGC7WX4QYV3ML7J3.json","view_paper":"https://pith.science/paper/OGNF6TKR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.05744&json=true","fetch_graph":"https://pith.science/api/pith-number/OGNF6TKRRKNGC7WX4QYV3ML7J3/graph.json","fetch_events":"https://pith.science/api/pith-number/OGNF6TKRRKNGC7WX4QYV3ML7J3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OGNF6TKRRKNGC7WX4QYV3ML7J3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OGNF6TKRRKNGC7WX4QYV3ML7J3/action/storage_attestation","attest_author":"https://pith.science/pith/OGNF6TKRRKNGC7WX4QYV3ML7J3/action/author_attestation","sign_citation":"https://pith.science/pith/OGNF6TKRRKNGC7WX4QYV3ML7J3/action/citation_signature","submit_replication":"https://pith.science/pith/OGNF6TKRRKNGC7WX4QYV3ML7J3/action/replication_record"}},"created_at":"2026-07-05T05:40:57.808226+00:00","updated_at":"2026-07-05T05:40:57.808226+00:00"}