activity
20162025
most citedEffective Quantization Methods for Recurrent Neural Networks

64 citations · 136 across the 13 of their papers we have counts for

collaborators

7 papers

cs.CV20236 cited

UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View

Shengchao Zhou, Weizhou Liu, Chen Hu +2

In the field of 3D object detection for autonomous driving, the sensor portfolio including multi-modality and single-modality is diverse and complex. Since the multi-modal methods…

cs.CV20236 cited

A Dynamic Multi-Scale Voxel Flow Network for Video Prediction

Xiaotao Hu, Zhewei Huang, Ailin Huang +2

The performance of video prediction has been greatly boosted by advanced deep neural networks. However, most of the current methods suffer from large model sizes and require extra…

cs.CV20231 cited

Three Guidelines You Should Know for Universally Slimmable Self-Supervised Learning

Yun-Hao Cao, Peiqin Sun, Shuchang Zhou

We propose universally slimmable self-supervised learning (dubbed as US3L) to achieve better accuracy-efficiency trade-offs for deploying self-supervised models across different de…

cs.CV20229 cited

Perceptual Conversational Head Generation with Regularized Driver and Enhanced Renderer

Ailin Huang, Zhewei Huang, Shuchang Zhou

This paper reports our solution for ACM Multimedia ViCo 2022 Conversational Head Generation Challenge, which aims to generate vivid face-to-face conversation videos based on audio…

cs.CV20221 cited

Synergistic Self-supervised and Quantization Learning

Yun-Hao Cao, Peiqin Sun, Yechang Huang +2

With the success of self-supervised learning (SSL), it has become a mainstream paradigm to fine-tune from self-supervised pretrained models to boost the performance on downstream t…

cs.CV20168 cited

Training Bit Fully Convolutional Network for Fast Semantic Segmentation

He Wen, Shuchang Zhou, Zhe Liang +4

Fully convolutional neural networks give accurate, per-pixel prediction for input images and have applications like semantic segmentation. However, a typical FCN usually requires l…