Multi-Graph Convolution Network for Pose Forecasting

no code implementations • 11 Apr 2023 • Hongwei Ren, Yuhong Shi, Kewei Liang

The most commonly used models for this task are autoregressive models, such as recurrent neural networks (RNNs) or variants, and Transformer Networks.

Human Pose Forecasting Pose Prediction

PatchDCT: Patch Refinement for High Quality Instance Segmentation

1 code implementation • 6 Feb 2023 • Qinrou Wen, Jirui Yang, Xue Yang, Kewei Liang

To further refine masks obtained by compressed vectors, we propose for the first time a compressed vector based multi-stage refinement framework.

Instance Segmentation Semantic Segmentation +1

DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentation

1 code implementation • CVPR 2021 • Xing Shen, Jirui Yang, Chunbo Wei, Bing Deng, Jianqiang Huang, Xiansheng Hua, Xiaoliang Cheng, Kewei Liang

Generally, a low-resolution grid is not sufficient to capture the details, while a high-resolution grid dramatically increases the training complexity.

Instance Segmentation Semantic Segmentation

Tracklets Predicting Based Adaptive Graph Tracking

no code implementations • 18 Oct 2020 • Chaobing Shan, Chunbo Wei, Bing Deng, Jianqiang Huang, Xian-Sheng Hua, Xiaoliang Cheng, Kewei Liang

It re-extracts the features of the tracklets in the current frame based on motion predicting, which is the key to solve the problem of features inconsistent.

Autonomous Driving Multi-Object Tracking +1

Deep Euler method: solving ODEs by approximating the local truncation error of the Euler method

no code implementations • 21 Mar 2020 • Xing Shen, Xiaoliang Cheng, Kewei Liang

In this paper, we propose a deep learning-based method, deep Euler method (DEM) to solve ordinary differential equations.