no code implementations • 27 Nov 2023 • Siyuan Huang, Yifan Zhou, Ram Prabhakar, Xijun Liu, Yuxiang Guo, Hongrui Yi, Cheng Peng, Rama Chellappa, Chun Pong Lau
To address these limitations, we propose a Local Semantic Extraction (LSE) module inspired by Interactive Segmentation Models.
no code implementations • 27 Nov 2023 • Jiang Liu, Chen Wei, Yuxiang Guo, Heng Yu, Alan Yuille, Soheil Feizi, Chun Pong Lau, Rama Chellappa
We propose Instruct2Attack (I2A), a language-guided semantic attack that generates semantically meaningful perturbations according to free-form language instructions.
no code implementations • 9 Nov 2023 • Siyuan Huang, Ram Prabhakar Kathirvel, Chun Pong Lau, Rama Chellappa
In this paper, we address the challenging task of whole-body biometric detection, recognition, and identification at distances of up to 500m and large pitch angles of up to 50 degree.
no code implementations • 27 Jul 2023 • Yuxiang Guo, Cheng Peng, Ram Prabhakar, Chun Pong Lau, Rama Chellappa
Gait recognition holds the promise of robustly identifying subjects based on their walking patterns instead of color information.
1 code implementation • 23 May 2023 • Jiang Liu, Chun Pong Lau, Rama Chellappa
In this work, we ask: can diffusion models be used to generate adversarial examples to improve both visual quality and attack performance?
no code implementations • 22 May 2023 • Chun Pong Lau, Jiang Liu, Rama Chellappa
In this paper, we propose Attribute Guided Encryption with Facial Texture Masking (AGE-FTM) that performs a dual manifold adversarial attack on FR systems to achieve both good visual quality and high black box attack success rates.
1 code implementation • IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023 • Ketul Shah, Anshul Shah, Chun Pong Lau, Celso M. de Melo, Rama Chellappa
We present a supervised contrastive learning framework to learn a feature embedding robust to changes in viewpoint, by effectively leveraging multi-view data.
Ranked #11 on Action Recognition on NTU RGB+D 120
no code implementations • 8 Oct 2022 • Yuxiang Guo, Cheng Peng, Chun Pong Lau, Rama Chellappa
In this work, we propose Dual-Modal Ensemble (DME), which combines both RGB and silhouette data to achieve more robust performances for indoor and outdoor whole-body based recognition.
no code implementations • 12 Dec 2021 • Chun Pong Lau, Jiang Liu, Hossein Souri, Wei-An Lin, Soheil Feizi, Rama Chellappa
Under JSTM, we develop novel adversarial attacks and defenses.
no code implementations • 9 Dec 2021 • Jiang Liu, Chun Pong Lau, Hossein Souri, Soheil Feizi, Rama Chellappa
In other words, we can make a weak model more robust with the help of a strong teacher model.
1 code implementation • CVPR 2022 • Jiang Liu, Alexander Levine, Chun Pong Lau, Rama Chellappa, Soheil Feizi
In addition, we design a robust shape completion algorithm, which is guaranteed to remove the entire patch from the images if the outputs of the patch segmenter are within a certain Hamming distance of the ground-truth patch masks.
no code implementations • 13 Oct 2021 • Hossein Souri, Pirazh Khorramshahi, Chun Pong Lau, Micah Goldblum, Rama Chellappa
The adversarial attack literature contains a myriad of algorithms for crafting perturbations which yield pathological behavior in neural networks.
no code implementations • NeurIPS 2020 • Wei-An Lin, Chun Pong Lau, Alexander Levine, Rama Chellappa, Soheil Feizi
Using OM-ImageNet, we first show that adversarial training in the latent space of images improves both standard accuracy and robustness to on-manifold attacks.
no code implementations • 7 Oct 2019 • Chun Pong Lau, Hossein Souri, Rama Chellappa
To mitigate the degradation due to turbulence which includes deformation and blur, we propose a generative single frame restoration algorithm which disentangles the blur and deformation due to turbulence and reconstructs a restored image.
no code implementations • 12 Jul 2018 • Wai Ho Chak, Chun Pong Lau, Lok Ming Lui
Instead of requiring a massive training sample size in deep networks, we purpose a training strategy that is based on a new data augmentation method to model turbulence from a relatively small dataset.
no code implementations • 8 Dec 2017 • Chun Pong Lau, Yu Hin Lai, Lok Ming Lui
The energy consists of a fidelity term measuring the discrepancy between the extracted image and the subsampled frames, as well as regularization terms on the extracted image and the subsample.
no code implementations • 11 Oct 2017 • Chun Pong Lau, Chun Pang Yung, Lok Ming Lui
In this paper, we propose a simple and yet effective method to resize an image, which preserves the geometry of the important content, using the Beltrami representation.
no code implementations • 11 Apr 2017 • Chun Pong Lau, Yu Hin Lai, Lok Ming Lui
The subsampled image sequence is then stabilized by applying the Robust Principal Component Analysis (RPCA) on the deformation fields between image frames and warping the image frames by a quasiconformal map associated with the low-rank part of the deformation matrix.