33 citations · 72 across the 11 of their papers we have counts for
6 papers · 1 filter
Towards Precise End-to-end Weakly Supervised Object Detection Network
Ke Yang, Dongsheng Li, Yong Dou
It is challenging for weakly supervised object detection network to precisely predict the positions of the objects, since there are no instance-level category annotations. Most exi…
Heavy-ball Algorithms Always Escape Saddle Points
Tao Sun, Dongsheng Li, Zhe Quan +3
Nonconvex optimization algorithms with random initialization have attracted increasing attention recently. It has been showed that many first-order methods always avoid saddle poin…
Visual Confusion Label Tree For Image Classification
Yuntao Liu, Yong Dou, Ruochun Jin +1
Convolution neural network models are widely used in image classification tasks. However, the running time of such models is so long that it is not the conforming to the strict rea…
Visual Tree Convolutional Neural Network in Image Classification
Yuntao Liu, Yong Dou, Ruochun Jin +1
In image classification, Convolutional Neural Network(CNN) models have achieved high performance with the rapid development in deep learning. However, some categories in the image…
Exploring Frame Segmentation Networks for Temporal Action Localization
Ke Yang, Xiaolong Shen, Peng Qiao +3
Temporal action localization is an important task of computer vision. Though many methods have been proposed, it still remains an open question how to predict the temporal location…
IF-TTN: Information Fused Temporal Transformation Network for Video Action Recognition
Ke Yang, Peng Qiao, Dongsheng Li +1
Effective spatiotemporal feature representation is crucial to the video-based action recognition task. Focusing on discriminate spatiotemporal feature learning, we propose Informat…