September 2024, paper titled 'FedRepOpt: Gradient Re-parametrized Optimizers in Federated Learning' accepted to ACCV 2024.
April 2024, paper titled 'Exploring Federated Self-Supervised Learning for General Purpose Audio Understanding' accepted to ICASSP-2024 workshop on Self-supervision in Audio, Speech and Beyond.
February 2024, paper titled 'AudioRepInceptionNeXt: A lightweight single-stream architecture for efficient audio recognition' accepted in NeuroComputing.
November 2023, paper titled 'Adaptive uncertainty estimation via high-dimensional testing on latent representations' accepted in NeurIPS 2023.
August 2023, paper titled 'Large Separable Kernel Attention: Rethinking the Large Kernel Attention design in CNN' accepted in Expert Systems with Applications.
June 2023, solution got first place award in EPIC-Kitchens-100 2023 Challenges on EPIC-SOUNDS Audio-Based Interaction Recognition, CVPR 2023 Workshop.
June 2022, paper titled 'What Should Be Equivariant in Self-Supervised Learning' accepted to CVPR Workshops on L3D-IVU.
Research Experience
Works at TCL AI Lab on various projects, including audio recognition for smart home robots, anomaly detection for industrial applications, and low-level image enhancement tasks such as super-resolution and diffraction removal for under-display cameras (UDC).
Education
Received B.E. degree in Information Engineering from City University of Hong Kong in 2017; Currently pursuing a part-time Ph.D. degree at the Department of Electrical Engineering, City University of Hong Kong, under the guidance of Dr. Lai-Man Po.
Background
Research interests include Computer Vision, Audio Processing, Image enhancement, Image and audio representation learning, Federated learning, Self-supervised learning, Reparameterization. Works as a Research Engineer at TCL AI Lab, focusing on Computer Vision, Audio Processing, and Deep Learning.