{"list":"other","total":51,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2103.15679","title":"Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers","created":"2021-03-29","cited_by_count":320},{"id":"2303.13283","title":"Visual-Language Prompt Tuning with Knowledge-guided Context Optimization","created":"2023-03-23","cited_by_count":308},{"id":"1606.01847","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","created":"2016-06-06","cited_by_count":243},{"id":"1803.11097","title":"Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision","created":"2018-03-29","cited_by_count":167},{"id":"2004.14043","title":"Single-Side Domain Generalization for Face Anti-Spoofing","created":"2020-04-29","cited_by_count":139},{"id":"1708.01471","title":"Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering","created":"2017-08-04","cited_by_count":117},{"id":"2007.12342","title":"CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations","created":"2020-07-24","cited_by_count":109},{"id":"2011.02062","title":"NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing","created":"2020-11-03","cited_by_count":105},{"id":"2004.01959","title":"Cross-domain Face Presentation Attack Detection via Multi-domain Disentangled Representation Learning","created":"2020-04-04","cited_by_count":93},{"id":"1911.10771","title":"Regularized Fine-grained Meta Face Anti-spoofing","created":"2019-11-25","cited_by_count":86},{"id":"1909.08848","title":"Biometric Face Presentation Attack Detection with Multi-Channel Convolutional Neural Network","created":"2019-09-19","cited_by_count":79},{"id":"2203.05340","title":"Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing","created":"2022-03-10","cited_by_count":73},{"id":"2203.14325","title":"PatchNet: A Simple Face Anti-Spoofing Framework via Fine-Grained Patch Recognition","created":"2022-03-27","cited_by_count":67},{"id":"2003.05136","title":"CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofing","created":"2020-03-11","cited_by_count":66},{"id":"2008.08250","title":"Face Anti-Spoofing Via Disentangled Representation Learning","created":"2020-08-19","cited_by_count":65},{"id":"1908.10654","title":"CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofing","created":"2019-08-28","cited_by_count":61},{"id":"2102.12129","title":"Self-Domain Adaptation for Face Anti-Spoofing","created":"2021-02-24","cited_by_count":49},{"id":"2108.02667","title":"Adaptive Normalized Representation Learning for Generalizable Face Anti-Spoofing","created":"2021-08-05","cited_by_count":49},{"id":"2303.13662","title":"Rethinking Domain Generalization for Face Anti-spoofing: Separability and Alignment","created":"2023-03-23","cited_by_count":48},{"id":"2106.16128","title":"Dual Reweighting Domain Generalization for Face Presentation Attack Detection","created":"2021-06-30","cited_by_count":47},{"id":"2105.02453","title":"Generalizable Representation Learning for Mixture Domain Face Anti-Spoofing","created":"2021-05-06","cited_by_count":46},{"id":"2309.16649","title":"FLIP: Cross-domain Face Anti-spoofing with Language Guidance","created":"2023-09-28","cited_by_count":45},{"id":"2104.06148","title":"Contrastive Context-Aware Learning for 3D High-Fidelity Mask Face Presentation Attack Detection","created":"2021-04-13","cited_by_count":43},{"id":"2304.05640","title":"Instance-Aware Domain Generalization for Face Anti-Spoofing","created":"2023-04-12","cited_by_count":42},{"id":"2103.00948","title":"Cross Modal Focal Loss for RGBD Face Anti-Spoofing","created":"2021-03-01","cited_by_count":41},{"id":"2403.14333","title":"CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofing","created":"2024-03-21","cited_by_count":39},{"id":"2203.12175","title":"Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofing","created":"2022-03-23","cited_by_count":38},{"id":"2211.16191","title":"SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classification","created":"2022-11-28","cited_by_count":34},{"id":"2207.10015","title":"Generative Domain Adaptation for Face Anti-Spoofing","created":"2022-07-20","cited_by_count":33},{"id":"2110.06753","title":"Learning Meta Pattern for Face Anti-Spoofing","created":"2021-10-13","cited_by_count":29},{"id":"2207.09868","title":"Adaptive Mixture of Experts Learning for Generalizable Face Anti-Spoofing","created":"2022-07-20","cited_by_count":28},{"id":"2009.07529","title":"DRL-FAS: A Novel Framework Based on Deep Reinforcement Learning for Face Anti-Spoofing","created":"2020-09-16","cited_by_count":25},{"id":"2305.03277","title":"FM-ViT: Flexible Modal Vision Transformers for Face Anti-Spoofing","created":"2023-05-05","cited_by_count":22},{"id":"2202.08192","title":"Flexible-Modal Face Anti-Spoofing: A Benchmark","created":"2022-02-16","cited_by_count":21},{"id":"2304.07549","title":"MA-ViT: Modality-Agnostic Vision Transformers for Face Anti-Spoofing","created":"2023-04-15","cited_by_count":18},{"id":"2402.19298","title":"Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing","created":"2024-02-29","cited_by_count":16},{"id":"2409.03501","title":"Towards Data-Centric Face Anti-Spoofing: Improving Cross-domain Generalization via Physics-based Data Synthesis","created":"2024-09-04","cited_by_count":16},{"id":"2303.09914","title":"Rehearsal-Free Domain Continual Face Anti-Spoofing: Generalize More and Forget Less","created":"2023-03-16","cited_by_count":12},{"id":"2309.04038","title":"S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing with Statistical Tokens","created":"2023-09-07","cited_by_count":11},{"id":"2212.03651","title":"Cyclically Disentangled Feature Translation for Face Anti-spoofing","created":"2022-12-07","cited_by_count":10},{"id":"2307.13958","title":"Visual Prompt Flexible-Modal Face Anti-Spoofing","created":"2023-07-26","cited_by_count":9}],"next_cursor":null}