Alert button
Picture for Alex Kot

Alex Kot

Alert button

Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing

Feb 29, 2024
Xun Lin, Shuai Wang, Rizhao Cai, Yizhong Liu, Ying Fu, Zitong Yu, Wenzhong Tang, Alex Kot

Viaarxiv icon

MIMIC: Mask Image Pre-training with Mix Contrastive Fine-tuning for Facial Expression Recognition

Jan 14, 2024
Fan Zhang, Xiaobao Guo, Xiaojiang Peng, Alex Kot

Viaarxiv icon

BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models

Dec 06, 2023
Rizhao Cai, Zirui Song, Dayan Guan, Zhenhao Chen, Xing Luo, Chenyu Yi, Alex Kot

Viaarxiv icon

Biomedical Image Splicing Detection using Uncertainty-Guided Refinement

Sep 28, 2023
Xun Lin, Wenzhong Tang, Shuai Wang, Zitong Yu, Yizhong Liu, Haoran Wang, Ying Fu, Alex Kot

Figure 1 for Biomedical Image Splicing Detection using Uncertainty-Guided Refinement
Figure 2 for Biomedical Image Splicing Detection using Uncertainty-Guided Refinement
Figure 3 for Biomedical Image Splicing Detection using Uncertainty-Guided Refinement
Figure 4 for Biomedical Image Splicing Detection using Uncertainty-Guided Refinement
Viaarxiv icon

S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing with Statistical Tokens

Sep 07, 2023
Rizhao Cai, Zitong Yu, Chenqi Kong, Haoliang Li, Changsheng Chen, Yongjian Hu, Alex Kot

Figure 1 for S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing with Statistical Tokens
Figure 2 for S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing with Statistical Tokens
Figure 3 for S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing with Statistical Tokens
Figure 4 for S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing with Statistical Tokens
Viaarxiv icon

Hyperbolic Face Anti-Spoofing

Aug 17, 2023
Shuangpeng Han, Rizhao Cai, Yawen Cui, Zitong Yu, Yongjian Hu, Alex Kot

Figure 1 for Hyperbolic Face Anti-Spoofing
Figure 2 for Hyperbolic Face Anti-Spoofing
Figure 3 for Hyperbolic Face Anti-Spoofing
Figure 4 for Hyperbolic Face Anti-Spoofing
Viaarxiv icon

Rehearsal-Free Domain Continual Face Anti-Spoofing: Generalize More and Forget Less

Mar 16, 2023
Rizhao Cai, Yawen Cui, Zhi Li, Zitong Yu, Haoliang Li, Yongjian Hu, Alex Kot

Figure 1 for Rehearsal-Free Domain Continual Face Anti-Spoofing: Generalize More and Forget Less
Figure 2 for Rehearsal-Free Domain Continual Face Anti-Spoofing: Generalize More and Forget Less
Figure 3 for Rehearsal-Free Domain Continual Face Anti-Spoofing: Generalize More and Forget Less
Figure 4 for Rehearsal-Free Domain Continual Face Anti-Spoofing: Generalize More and Forget Less
Viaarxiv icon

Adapter Incremental Continual Learning of Efficient Audio Spectrogram Transformers

Feb 28, 2023
Nithish Muthuchamy Selvaraj, Xiaobao Guo, Adams Kong, Bingquan Shen, Alex Kot

Figure 1 for Adapter Incremental Continual Learning of Efficient Audio Spectrogram Transformers
Figure 2 for Adapter Incremental Continual Learning of Efficient Audio Spectrogram Transformers
Figure 3 for Adapter Incremental Continual Learning of Efficient Audio Spectrogram Transformers
Figure 4 for Adapter Incremental Continual Learning of Efficient Audio Spectrogram Transformers
Viaarxiv icon

Raw Image Reconstruction with Learned Compact Metadata

Feb 28, 2023
Yufei Wang, Yi Yu, Wenhan Yang, Lanqing Guo, Lap-Pui Chau, Alex Kot, Bihan Wen

Figure 1 for Raw Image Reconstruction with Learned Compact Metadata
Figure 2 for Raw Image Reconstruction with Learned Compact Metadata
Figure 3 for Raw Image Reconstruction with Learned Compact Metadata
Figure 4 for Raw Image Reconstruction with Learned Compact Metadata
Viaarxiv icon

Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofing

Feb 11, 2023
Zitong Yu, Rizhao Cai, Yawen Cui, Xin Liu, Yongjian Hu, Alex Kot

Figure 1 for Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofing
Figure 2 for Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofing
Figure 3 for Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofing
Figure 4 for Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofing
Viaarxiv icon