1.6k citations · 4.8k across the 90 of their papers we have counts for
8 papers · 2 filters
Enhance Visual Recognition under Adverse Conditions via Deep Networks
Ding Liu, Bowen Cheng, Zhangyang Wang +2
Visual recognition under adverse conditions is a very important and challenging problem of high practical value, due to the ubiquitous existence of quality distortions during image…
Improving Object Detection from Scratch via Gated Feature Reuse
Zhiqiang Shen, Honghui Shi, Jiahui Yu +7
In this paper, we present a simple and parameter-efficient drop-in module for one-stage object detectors like SSD when learning from scratch (i.e., without pre-trained models). We…
Robust Emotion Recognition from Low Quality and Low Bit Rate Video: A Deep Learning Approach
Bowen Cheng, Zhangyang Wang, Zhaobin Zhang +5
Emotion recognition from facial expressions is tremendously useful, especially when coupled with smart devices and wireless multimedia applications. However, the inadequate network…
Deep GrabCut for Object Selection
Ning Xu, Brian Price, Scott Cohen +2
Most previous bounding-box-based segmentation methods assume the bounding box tightly covers the object of interest. However it is common that a rectangle input could be too large…
When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach
Ding Liu, Bihan Wen, Xianming Liu +2
Conventionally, image denoising and high-level vision tasks are handled separately in computer vision. In this paper, we cope with the two jointly and explore the mutual influence…
Deep Image Matting
Ning Xu, Brian Price, Scott Cohen +1
Image matting is a fundamental computer vision problem and has many applications. Previous algorithms have poor performance when an image has similar foreground and background colo…