Picture for Liang Lin

Liang Lin

Learning to Segment Human by Watching YouTube

Feb 28, 2018
Xiaodan Liang, Yunchao Wei, Liang Lin, Yunpeng Chen, Xiaohui Shen, Jianchao Yang, Shuicheng Yan

Figure 1 for Learning to Segment Human by Watching YouTube

Figure 2 for Learning to Segment Human by Watching YouTube

Figure 3 for Learning to Segment Human by Watching YouTube

Figure 4 for Learning to Segment Human by Watching YouTube

* 10.1109/TPAMI.2016.2598340
* Very-weakly supervised learning framework. New state-of-the-art performance on the human segmentation task! (Published in T-PAMI 2017)

Access Paper or Ask Questions

Batch Kalman Normalization: Towards Training Deep Neural Networks with Micro-Batches

Feb 28, 2018
Guangrun Wang, Jiefeng Peng, Ping Luo, Xinjiang Wang, Liang Lin

Figure 1 for Batch Kalman Normalization: Towards Training Deep Neural Networks with Micro-Batches

Figure 2 for Batch Kalman Normalization: Towards Training Deep Neural Networks with Micro-Batches

Figure 3 for Batch Kalman Normalization: Towards Training Deep Neural Networks with Micro-Batches

Figure 4 for Batch Kalman Normalization: Towards Training Deep Neural Networks with Micro-Batches

* We presented how to improve and accelerate the training of DNNs, particularly under the context of micro-batches. (Submitted to IJCAI 2018)

Access Paper or Ask Questions

Hierarchical Scene Parsing by Weakly Supervised Learning with Image Descriptions

Jan 27, 2018
Ruimao Zhang, Liang Lin, Guangrun Wang, Meng Wang, Wangmeng Zuo

Figure 1 for Hierarchical Scene Parsing by Weakly Supervised Learning with Image Descriptions

Figure 2 for Hierarchical Scene Parsing by Weakly Supervised Learning with Image Descriptions

Figure 3 for Hierarchical Scene Parsing by Weakly Supervised Learning with Image Descriptions

Figure 4 for Hierarchical Scene Parsing by Weakly Supervised Learning with Image Descriptions

* Accepted by Transactions on Pattern Analysis and Machine Intelligence (T-PAMI) 2018

Access Paper or Ask Questions

Structured Inhomogeneous Density Map Learning for Crowd Counting

Jan 20, 2018
Hanhui Li, Xiangjian He, Hefeng Wu, Saeed Amirgholipour Kasmani, Ruomei Wang, Xiaonan Luo, Liang Lin

Figure 1 for Structured Inhomogeneous Density Map Learning for Crowd Counting

Figure 2 for Structured Inhomogeneous Density Map Learning for Crowd Counting

Figure 3 for Structured Inhomogeneous Density Map Learning for Crowd Counting

Figure 4 for Structured Inhomogeneous Density Map Learning for Crowd Counting

* 10 pages, 7 figures

Access Paper or Ask Questions

Learning a Wavelet-like Auto-Encoder to Accelerate Deep Neural Networks

Dec 20, 2017
Tianshui Chen, Liang Lin, Wangmeng Zuo, Xiaonan Luo, Lei Zhang

Figure 1 for Learning a Wavelet-like Auto-Encoder to Accelerate Deep Neural Networks

Figure 2 for Learning a Wavelet-like Auto-Encoder to Accelerate Deep Neural Networks

Figure 3 for Learning a Wavelet-like Auto-Encoder to Accelerate Deep Neural Networks

Figure 4 for Learning a Wavelet-like Auto-Encoder to Accelerate Deep Neural Networks

* Accepted at AAAI 2018

Access Paper or Ask Questions

Recurrent Attentional Reinforcement Learning for Multi-label Image Recognition

Dec 20, 2017
Tianshui Chen, Zhouxia Wang, Guanbin Li, Liang Lin

Figure 1 for Recurrent Attentional Reinforcement Learning for Multi-label Image Recognition

Figure 2 for Recurrent Attentional Reinforcement Learning for Multi-label Image Recognition

Figure 3 for Recurrent Attentional Reinforcement Learning for Multi-label Image Recognition

Figure 4 for Recurrent Attentional Reinforcement Learning for Multi-label Image Recognition

* Accepted at AAAI 2018

Access Paper or Ask Questions

Multi-label Image Recognition by Recurrently Discovering Attentional Regions

Nov 08, 2017
Zhouxia Wang, Tianshui Chen, Guanbin Li, Ruijia Xu, Liang Lin

Figure 1 for Multi-label Image Recognition by Recurrently Discovering Attentional Regions

Figure 2 for Multi-label Image Recognition by Recurrently Discovering Attentional Regions

Figure 3 for Multi-label Image Recognition by Recurrently Discovering Attentional Regions

Figure 4 for Multi-label Image Recognition by Recurrently Discovering Attentional Regions

* Accepted at ICCV 2017

Access Paper or Ask Questions

Content-Adaptive Sketch Portrait Generation by Decompositional Representation Learning

Oct 04, 2017
Dongyu Zhang, Liang Lin, Tianshui Chen, Xian Wu, Wenwei Tan, Ebroul Izquierdo

Figure 1 for Content-Adaptive Sketch Portrait Generation by Decompositional Representation Learning

Figure 2 for Content-Adaptive Sketch Portrait Generation by Decompositional Representation Learning

Figure 3 for Content-Adaptive Sketch Portrait Generation by Decompositional Representation Learning

Figure 4 for Content-Adaptive Sketch Portrait Generation by Decompositional Representation Learning

* Published in TIP 2017

Access Paper or Ask Questions