activity
20192021
most citedAdapNet: Adaptability Decomposing Encoder-Decoder Network for Weakly Supervised Action Recognition and Localization

8 citations · 21 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG20212 cited

Deep Unsupervised Active Learning on Learnable Graphs

Handong Ma, Changsheng Li, Xinchu Shi +2

Recently deep learning has been successfully applied to unsupervised active learning. However, current method attempts to learn a nonlinear transformation via an auto-encoder while…

cs.LG2020

On Deep Unsupervised Active Learning

Changsheng Li, Handong Ma, Zhao Kang +3

Unsupervised active learning has attracted increasing attention in recent years, where its goal is to select representative samples in an unsupervised setting for human annotating.…

cs.CV2020

Reconstruction Regularized Deep Metric Learning for Multi-label Image Classification

Changsheng Li, Chong Liu, Lixin Duan +2

In this paper, we present a novel deep metric learning method to tackle the multi-label image classification problem. In order to better learn the correlations among images feature…

cs.CV20198 cited

AdapNet: Adaptability Decomposing Encoder-Decoder Network for Weakly Supervised Action Recognition and Localization

Xiao-Yu Zhang, Changsheng Li, Haichao Shi +3

The point process is a solid framework to model sequential data, such as videos, by exploring the underlying relevance. As a challenging problem for high-level video understanding,…

cs.LG20196 cited

Similarity Learning via Kernel Preserving Embedding

Zhao Kang, Yiwei Lu, Yuanzhang Su +2

Data similarity is a key concept in many data-driven applications. Many algorithms are sensitive to similarity measures. To tackle this fundamental problem, automatically learning…

cs.CV20195 cited

Learning Transferable Self-attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision

Xiao-Yu Zhang, Haichao Shi, Changsheng Li +3

Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume videos are trimmed as short seque…