During 2013 to 2016, I worked a lot on semantic segmentation where goal was to understanding the semantic meaning of each pixel in an image, including its object class and depth value. Over the years, we have developed several semantic segmentation algorithms.
The related publications from this line of research is listed below.
CASENet: Deep Category-Aware Semantic Edge Detection
Zhiding Yu, Chen Feng, Ming-Yu Liu, Srikumar Ramalingam
Conference on Computer Vision and Pattern Recognition (CVPR), 2017, Honolulu, Hawaii,
Gaussian Conditional Random Field Network for Semantic Segmentation
Raviteja Vemulapalli, Oncel Tuzel, Ming-Yu Liu, Rama Chellappa
Conference on Computer Vision and Pattern Recognition (CVPR) (Spotlight), 2016, Las Vegas, Nevada,
Layered Interpretation of Street View Images
Ming-Yu Liu, Shuoxin Lin, Srikumar Ramalingam, Oncel Tuzel
Robotics: Science and Systems Conference (RSS) (Best paper finalist), 2015, Rome, Italy
Recursive Context Propagation Network for Semantic Scene Labeling
Abhishek Sharma, Oncel Tuzel, Ming-Yu Liu
Neural Information Processing Systems (NIPS), 2014, Montreal, Canada