Search Results for author: Huaxia Xia

Found 7 papers, 4 papers with code

Target-Driven Structured Transformer Planner for Vision-Language Navigation

1 code implementation19 Jul 2022 Yusheng Zhao, Jinyu Chen, Chen Gao, Wenguan Wang, Lirong Yang, Haibing Ren, Huaxia Xia, Si Liu

Vision-language navigation is the task of directing an embodied agent to navigate in 3D scenes with natural language instructions.

Navigate Vision-Language Navigation

3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection

1 code implementation CVPR 2022 Junyu Luo, Jiahui Fu, Xianghao Kong, Chen Gao, Haibing Ren, Hao Shen, Huaxia Xia, Si Liu

3D visual grounding aims to locate the referred target object in 3D point cloud scenes according to a free-form language description.

3D visual grounding

Twins: Revisiting the Design of Spatial Attention in Vision Transformers

9 code implementations NeurIPS 2021 Xiangxiang Chu, Zhi Tian, Yuqing Wang, Bo Zhang, Haibing Ren, Xiaolin Wei, Huaxia Xia, Chunhua Shen

Very recently, a variety of vision transformer architectures for dense prediction tasks have been proposed and they show that the design of spatial attention is critical to their success in these tasks.

Image Classification Semantic Segmentation

End-to-End Video Instance Segmentation with Transformers

2 code implementations CVPR 2021 Yuqing Wang, Zhaoliang Xu, Xinlong Wang, Chunhua Shen, Baoshan Cheng, Hao Shen, Huaxia Xia

Here, we propose a new video instance segmentation framework built upon Transformers, termed VisTR, which views the VIS task as a direct end-to-end parallel sequence decoding/prediction problem.

Instance Segmentation Segmentation +3

Robust Trajectory Forecasting for Multiple Intelligent Agents in Dynamic Scene

no code implementations27 May 2020 Yanliang Zhu, Dongchun Ren, Mingyu Fan, Deheng Qian, Xin Li, Huaxia Xia

Trajectory forecasting, or trajectory prediction, of multiple interacting agents in dynamic scenes, is an important problem for many applications, such as robotic systems and autonomous driving.

Autonomous Driving Trajectory Forecasting

StarNet: Pedestrian Trajectory Prediction using Deep Neural Network in Star Topology

no code implementations5 Jun 2019 Yanliang Zhu, Deheng Qian, Dongchun Ren, Huaxia Xia

The hub network takes observed trajectories of all pedestrians to produce a comprehensive description of the interpersonal interactions.

Pedestrian Trajectory Prediction Trajectory Prediction

Cannot find the paper you are looking for? You can Submit a new open access paper.