15 citations · 27 across the 10 of their papers we have counts for
13 papers
Fundamental Impossibility Results in AI Safety: Trading Off between Desiderata
Ida Mattsson, Ratip Emin Berker, Emanuel Tewolde +11
Is there a fundamental tradeoff between desiderata for safe AI systems, such as harmlessness and helpfulness? We answer by formalizing the interaction between AI systems and users…
Multi-scale Image Representation Compression
Tianhao Peng, Ho Man Kwan, Fan Zhang +2
Overfitted codecs have demonstrated promising performance for image and video compression. In particular, for image compression, the Cool-chic family of models has shown competitiv…
Scalable Neural Video Representation Compression
Tianhao Peng, Ho Man Kwan, Fan Zhang +2
Scalable video coding (SVC) encodes a video into a layered bitstream consisting of a base layer and one or multiple enhancement layers, enabling decoding at different bitrate/quali…
High-Fidelity Video Compression based on Invertible Neural Transform and Implicit Conditioning
Siyue Teng, Ho Man Kwan, Yuxuan Jiang +2
Learning-based video compression has recently achieved competitive rate-distortion performance compared to conventional video codecs. However, most existing methods rely on non-inv…
Enhanced Neural Video Representation Compression Across Extreme Complexity and Quality Scales
Ho Man Kwan, Tianhao Peng, Fan Zhang +3
Implicit neural representations (INRs) have recently emerged as a promising approach to video compression, delivering competitive rate-distortion performance alongside rapid decodi…
Ultra-lightweight Neural Video Representation Compression
Ho Man Kwan, Tianhao Peng, Ge Gao +4
Recent works have demonstrated the viability of utilizing over-fitted implicit neural representations (INRs) as alternatives to autoencoder-based models for neural video compressio…
Instance Data Condensation for Image Super-Resolution
Tianhao Peng, Ho Man Kwan, Yuxuan Jiang +5
Deep learning based Image Super-Resolution (ISR) relies on large training datasets to optimize model generalization; this requires substantial computational and storage resources d…
HIIF: Hierarchical Encoding based Implicit Image Function for Continuous Super-resolution
Yuxuan Jiang, Ho Man Kwan, Tianhao Peng +5
Recent advances in implicit neural representations (INRs) have shown significant promise in modeling visual signals for various low-vision tasks including image super-resolution (I…
BVI-CR: A Multi-View Human Dataset for Volumetric Video Compression
Ge Gao, Adrian Azzarelli, Ho Man Kwan +4
The advances in immersive technologies and 3D reconstruction have enabled the creation of digital replicas of real-world objects and environments with fine details. These processes…
Immersive Video Compression using Implicit Neural Representations
Ho Man Kwan, Fan Zhang, Andrew Gower +1
Recent work on implicit neural representations (INRs) has evidenced their potential for efficiently representing and encoding conventional video content. In this paper we, for the…
FedSDD: Scalable and Diversity-enhanced Distillation for Model Aggregation in Federated Learning
Ho Man Kwan, Shenghui Song
Recently, innovative model aggregation methods based on knowledge distillation (KD) have been proposed for federated learning (FL). These methods not only improved the robustness o…
HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation
Ho Man Kwan, Ge Gao, Fan Zhang +2
Learning-based video compression is currently a popular research topic, offering the potential to compete with conventional standard video codecs. In this context, Implicit Neural…
SSBNet: Improving Visual Recognition Efficiency by Adaptive Sampling
Ho Man Kwan, Shenghui Song
Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and…