Yueyu Hu

2 accepted papers

2022

Neural Data-Dependent Transform for Learned Image Compression

Dezhao Wang, Wenhan Yang, Yueyu Hu, Jiaying Liu

CVPR 2022poster

Learned image compression has achieved great success due to its excellent modeling capacity, but seldom further considers the Rate-Distortion Optimization (RDO) of each input image. To explore this potential in the learned codec, we make the first attempt to build a neural data-dependent transform a…

Cited by 63 PDF ↗code ↗Scholar ↗

2017

Online action detection and forecast via Multitask deep Recurrent Neural Networks

Chunhui Liu, Yanghao Li, Yueyu Hu, Jiaying Liu

ICASSP 2017accepted

Online human action detection and forecast on untrimmed 3D skeleton sequences is a novel task based on traditional action recognition and has not been fully studied. Its aim is to localize and recognize one action in a long sequence while doing forecasting task at the same time. In this paper, we pr…

Cited by 0 Source ↗Scholar ↗