87 citations · 502 across the 49 of their papers we have counts for
7 papers · 1 filter
Webly Supervised Image Classification with Metadata: Automatic Noisy Label Correction via Visual-Semantic Graph
Jingkang Yang, Weirong Chen, Litong Feng +3
Webly supervised learning becomes attractive recently for its efficiency in data expansion without expensive human labeling. However, adopting search queries or hashtags as web lab…
Webly Supervised Image Classification with Self-Contained Confidence
Jingkang Yang, Litong Feng, Weirong Chen +4
This paper focuses on webly supervised learning (WSL), where datasets are built by crawling samples from the Internet and directly using search queries as web labels. Although WSL…
Context-Aware RCNN: A Baseline for Action Detection in Videos
Jianchao Wu, Zhanghui Kuang, Limin Wang +2
Video action detection approaches usually conduct actor-centric action recognition over RoI-pooled features following the standard pipeline of Faster-RCNN. In this work, we first e…
RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition
Xiaoyu Yue, Zhanghui Kuang, Chenhao Lin +2
The attention-based encoder-decoder framework has recently achieved impressive results for scene text recognition, and many variants have emerged with improvements in recognition q…
Maximum-and-Concatenation Networks
Xingyu Xie, Hao Kong, Jianlong Wu +3
While successful in many fields, deep neural networks (DNNs) still suffer from some open problems such as bad local minima and unsatisfactory generalization performance. In this wo…
Scale-Equalizing Pyramid Convolution for Object Detection
Xinjiang Wang, Shilong Zhang, Zhuoran Yu +2
Feature pyramid has been an efficient method to extract features at different scales. Development over this method mainly focuses on aggregating contextual information at different…