activity
20182020
most citedReceptive Multi-granularity Representation for Person Re-Identification

30 citations · 31 across the 2 of their papers we have counts for

collaborators

10 papers

cs.CV202030 cited

Receptive Multi-granularity Representation for Person Re-Identification

Guanshuo Wang, Yufeng Yuan, Jiwei Li +2

A key for person re-identification is achieving consistent local details for discriminative representation across variable environments. Current stripe-based feature learning appro…

cs.LG20191 cited

Layer Pruning for Accelerating Very Deep Neural Networks

Weiwei Zhang, Changsheng chen, Xuechun Wu +4

In this paper, we propose an adaptive pruning method. This method can cut off the channel and layer adaptively. The proportion of the layer and the channel to be cut is learned ada…

cs.CV2019

Relation-Aware Pyramid Network (RapNet) for temporal action proposal

Jialin Gao, Zhixiang Shi, Jiani Li +3

In this technical report, we describe our solution to temporal action proposal (task 1) in ActivityNet Challenge 2019. First, we fine-tune a ResNet-50-C3D CNN on ActivityNet v1.3 b…

cs.CV2018

Pixel-Anchor: A Fast Oriented Scene Text Detector with Combined Networks

Yuan Li, Yuanjie Yu, Zefeng Li +4

Recently, semantic segmentation and general object detection frameworks have been widely adopted by scene text detecting tasks. However, both of them alone have obvious shortcoming…

cs.CV2018

Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification

Yang Fu, Yunchao Wei, Guanshuo Wang +3

Domain adaptation in person re-identification (re-ID) has always been a challenging task. In this work, we explore how to harness the natural similar characteristics existing in th…

cs.SD2018

An improved hybrid CTC-Attention model for speech recognition

Zhe Yuan, Zhuoran Lyu, Jiwei Li +1

Recently, end-to-end speech recognition with a hybrid model consisting of the connectionist temporal classification(CTC) and the attention encoder-decoder achieved state-of-the-art…