90 citations · 271 across the 49 of their papers we have counts for
Showing eess.IVShow all
3 papers · 1 filter
eess.IV2024
TaQ-DiT: Time-aware Quantization for Diffusion Transformers
Xinyan Liu, Huihong Shi, Yang Xu +1
Transformer-based diffusion models, dubbed Diffusion Transformers (DiTs), have achieved state-of-the-art performance in image and video generation tasks. However, their large model…
eess.IV2023
A Computationally Efficient Neural Video Compression Accelerator Based on a Sparse CNN-Transformer Hybrid Network
Siyu Zhang, Wendong Mao, Huihong Shi +1
Video compression is widely used in digital television, surveillance systems, and virtual reality. Real-time video decoding is crucial in practical scenarios. Recently, neural vide…
eess.IV2021
Transform-Based Feature Map Compression for CNN Inference
Yubo Shi, Meiqi Wang, Siyi Chen +2
To achieve higher accuracy in machine learning tasks, very deep convolutional neural networks (CNNs) are designed recently. However, the large memory access of deep CNNs will lead…