2 citations · 3 across the 6 of their papers we have counts for
7 papers
SignDPO: Multi-level Direct Preference Optimisation for Skeleton-based Gloss-free Sign Language Translation
Muxin Pu, Xiao-Ming Wu, Mei Kuan Lim +3
We present SignDPO, a novel multi-level Direct Preference Optimisation (DPO) framework designed to enhance the alignment of skeleton-based Sign Language Translation. While current…
LA-Sign: Looped Transformers with Geometry-aware Alignment for Skeleton-based Sign Language Recognition
Muxin Pu, Mei Kuan Lim, Chun Yong Chong +1
Skeleton-based isolated sign language recognition (ISLR) demands fine-grained understanding of articulated motion across multiple spatial scales, from subtle finger movements to gl…
Sigma: Semantically Informative Pre-training for Skeleton-based Sign Language Understanding
Muxin Pu, Mei Kuan Lim, Chun Yong Chong +1
Pre-training has proven effective for learning transferable features in sign language understanding (SLU) tasks. Recently, skeleton-based methods have gained increasing attention b…
Siformer: Feature-isolated Transformer for Efficient Skeleton-based Sign Language Recognition
Muxin Pu, Mei Kuan Lim, Chun Yong Chong
Sign language recognition (SLR) refers to interpreting sign language glosses from given videos automatically. This research area presents a complex challenge in computer vision bec…
Robustness Evaluation in Hand Pose Estimation Models using Metamorphic Testing
Muxin Pu, Chun Yong Chong, Mei Kuan Lim
Hand pose estimation (HPE) is a task that predicts and describes the hand poses from images or video frames. When HPE models estimate hand poses captured in a laboratory or under c…
Metamorphic Testing-based Adversarial Attack to Fool Deepfake Detectors
Nyee Thoang Lim, Meng Yi Kuan, Muxin Pu +2
Deepfakes utilise Artificial Intelligence (AI) techniques to create synthetic media where the likeness of one person is replaced with another. There are growing concerns that deepf…
Fairness Evaluation in Deepfake Detection Models using Metamorphic Testing
Muxin Pu, Meng Yi Kuan, Nyee Thoang Lim +2
Fairness of deepfake detectors in the presence of anomalies are not well investigated, especially if those anomalies are more prominent in either male or female subjects. The prima…