Search Results for author: Joya Chen

Found 6 papers, 4 papers with code

AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant

3 code implementations8 Mar 2022 Benita Wong, Joya Chen, You Wu, Stan Weixian Lei, Dongxing Mao, Difei Gao, Mike Zheng Shou

In this paper, we define a new task called Affordance-centric Question-driven Task Completion, where the AI assistant should learn from instructional videos and scripts to guide the user step-by-step.

DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training

1 code implementation28 Feb 2022 Joya Chen, Kai Xu, Yifei Cheng, Angela Yao

The bulk of memory is occupied by caching intermediate tensors for gradient computation in the backward pass.

Foreground-Background Imbalance Problem in Deep Object Detectors: A Review

no code implementations16 Jun 2020 Joya Chen, Qi Wu, Dong Liu, Tong Xu

Recent years have witnessed the remarkable developments made by deep learning techniques for object detection, a fundamentally challenging problem of computer vision.

Computer Vision object-detection +1

Long-term Joint Scheduling for Urban Traffic

1 code implementation27 Oct 2019 Xianfeng Liang, Likang Wu, Joya Chen, Yang Liu, Runlong Yu, Min Hou, Han Wu, Yuyang Ye, Qi Liu, Enhong Chen

Recently, the traffic congestion in modern cities has become a growing worry for the residents.

Is Heuristic Sampling Necessary in Training Deep Object Detectors?

13 code implementations11 Sep 2019 Joya Chen, Dong Liu, Tong Xu, Shiwei Wu, Yifei Cheng, Enhong Chen

In this paper, we challenge the necessity of such hard/soft sampling methods for training accurate deep object detectors.

General Classification Instance Segmentation +1

Residual Objectness for Imbalance Reduction

no code implementations24 Aug 2019 Joya Chen, Dong Liu, Bin Luo, Xuezheng Peng, Tong Xu, Enhong Chen

For a long time, object detectors have suffered from extreme imbalance between foregrounds and backgrounds.

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