{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"1604.02878","title":"Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks","created":"2016-04-11","cited_by_count":903},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"2102.04378","title":"TransReID: Transformer-based Object Re-Identification","created":"2021-02-08","cited_by_count":435},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361},{"id":"2112.06825","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks","created":"2021-12-13","cited_by_count":320},{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294},{"id":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291},{"id":"2112.03109","title":"General Facial Representation Learning in a Visual-Linguistic Manner","created":"2021-12-06","cited_by_count":195},{"id":"2003.04092","title":"Searching Central Difference Convolutional Networks for Face Anti-Spoofing","created":"2020-03-09","cited_by_count":173},{"id":"1803.11097","title":"Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision","created":"2018-03-29","cited_by_count":167},{"id":"2303.10826","title":"Visual Prompt Multi-Modal Tracking","created":"2023-03-20","cited_by_count":142},{"id":"2004.14043","title":"Single-Side Domain Generalization for Face Anti-Spoofing","created":"2020-04-29","cited_by_count":139},{"id":"2303.03369","title":"Multimodal Prompting with Missing Modalities for Visual Recognition","created":"2023-03-06","cited_by_count":121},{"id":"1511.06316","title":"face anti-spoofing based on color texture analysis","created":"2015-11-19","cited_by_count":82},{"id":"1909.08848","title":"Biometric Face Presentation Attack Detection with Multi-Channel Convolutional Neural Network","created":"2019-09-19","cited_by_count":79},{"id":"1907.04047","title":"Deep Pixel-wise Binary Supervision for Face Presentation Attack Detection","created":"2019-07-09","cited_by_count":76},{"id":"1904.02860","title":"Deep Tree Learning for Zero-shot Face Anti-Spoofing","created":"2019-04-05","cited_by_count":73},{"id":"2203.05340","title":"Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing","created":"2022-03-10","cited_by_count":73},{"id":"2003.08061","title":"Deep Spatial Gradient and Temporal Depth Learning for Face Anti-spoofing","created":"2020-03-18","cited_by_count":70},{"id":"2008.08250","title":"Face Anti-Spoofing Via Disentangled Representation Learning","created":"2020-08-19","cited_by_count":65},{"id":"2106.14948","title":"Deep Learning for Face Anti-Spoofing: A Survey","created":"2021-06-28","cited_by_count":65},{"id":"2007.02157","title":"Face Anti-Spoofing with Human Material Perception","created":"2020-07-04","cited_by_count":62},{"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":"2207.14571","title":"Prompting for Multi-Modal Tracking","created":"2022-07-29","cited_by_count":59},{"id":"1812.00408","title":"A Dataset and Benchmark for Large-scale Multi-modal Face Anti-spoofing","created":"2018-12-02","cited_by_count":51},{"id":"2011.12032","title":"Revisiting Pixel-Wise Supervision for Face Anti-Spoofing","created":"2020-11-24","cited_by_count":45},{"id":"1904.12490","title":"Learning Meta Model for Zero- and Few-shot Face Anti-spoofing","created":"2019-04-29","cited_by_count":44},{"id":"2011.08019","title":"On the Effectiveness of Vision Transformers for Zero-shot Face Anti-Spoofing","created":"2020-11-16","cited_by_count":44},{"id":"2103.00948","title":"Cross Modal Focal Loss for RGBD Face Anti-Spoofing","created":"2021-03-01","cited_by_count":41},{"id":"2104.07419","title":"TransRPPG: Remote Photoplethysmography Transformer for 3D Mask Face Presentation Attack Detection","created":"2021-04-15","cited_by_count":41},{"id":"2106.06560","title":"HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers","created":"2021-06-11","cited_by_count":39},{"id":"2004.08388","title":"Multi-Modal Face Anti-Spoofing Based on Central Difference Networks","created":"2020-04-17","cited_by_count":36},{"id":"2007.11457","title":"Learning One Class Representations for Face Presentation Attack Detection using Multi-channel Convolutional Neural Networks","created":"2020-07-22","cited_by_count":36},{"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":"2302.05744","title":"Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofing","created":"2023-02-11","cited_by_count":19},{"id":"2304.07549","title":"MA-ViT: Modality-Agnostic Vision Transformers for Face Anti-Spoofing","created":"2023-04-15","cited_by_count":18},{"id":"2303.00917","title":"Enhancing General Face Forgery Detection via Vision Transformer with Low-Rank Adaptation","created":"2023-03-02","cited_by_count":16},{"id":"1904.09290","title":"FeatherNets: Convolutional Neural Networks as Light as Feather for Face Anti-spoofing","created":"2019-04-22","cited_by_count":14},{"id":"2203.01562","title":"ViTransPAD: Video Transformer using convolution and self-attention for Face Presentation Attack Detection","created":"2022-03-03","cited_by_count":14},{"id":"1907.04048","title":"Domain Adaptation in Multi-Channel Autoencoder based Features for Robust Face Anti-Spoofing","created":"2019-07-09","cited_by_count":12},{"id":"2110.09108","title":"Asymmetric Modality Translation For Face Presentation Attack Detection","created":"2021-10-18","cited_by_count":4}],"next_cursor":null}