WELCOME to the COMPUTER VISION LAB


vision lab logo

The Computer Vision Laboratory was established in the Computer Science Department at the University of Massachusetts in 1974 with the goal of investigating the scientific principles underlying the construction of integrated vision systems and the application of vision to problems of real-world importance. The emphasis of our work is on vision systems that are capable of functioning flexibly and robustly in complex changing environments.


Click on the panels below to learn more about our latest work:


[Approximate Convex Decompositions]
Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions, Matheus Gadelha*, Aruni RoyChowdhury*, Gopal Sharma, Evangelos Kalogerakis, Liangliang Cao, Erik Learned-Miller, Rui Wang, Subhransu Maji, ECCV 2020
 [Unlabeled Faces in the Wild]
Improving Face Recognition by Clustering Unlabeled Faces in the Wild, Aruni RoyChowdhury, Xiang Yu, Kihyuk Sohn, Erik Learned-Miller and Manmohan Chandraker, ECCV 2020
[Pixel Adaptive Convolution]
Pixel Adaptive Convolutional Neural Networks, Hang Su, Varun Jampani, Deqing Sun, Orazio Gallo, Erik Learned-Miller, and Jan Kautz, CVPR 2019
 [Self-train]
Automatic Adaptation of Object Detectors to new domains using Self-training, Aruni RoyChowdhury, Prithvijit Chakrabarty, Ashish Singh, SouYoung Jin, Huaizu Jiang, Liangliang Cao, Erik Learned-Miller, CVPR 2019
[SSR_DEPTH]
Self-Supervised Relative Depth Learning for Urban Scene Understanding, Huaizu Jiang, Gustav Larsson, Michael Maire, Greg Shakhnarovich, and Erik Learned-Miller, ECCV 2018
[Hard Example]
Unsupervised Hard Example Mining from Videos for Improved Object Detection, SouYoung Jin*, Aruni RoyChowdhury*, Huaizu Jiang, Ashish Singh, Aditya Prasad, Deep Chakraborty, and Erik Learned-Miller, ECCV 2018
[super-slomo]
Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation, Huaizu Jiang, Deqing Sun, Varun Jampani, Ming-Hsuan Yang, Erik Learned-Miller, Jan Kautz, CVPR 2018 (spotlight)
 [SPLATNet]
SPLATNet: Sparse Lattice Networks for Point Cloud Processing, Hang Su, Varun Jampani, Deqing Sun, Subhransu Maji, Evangelos Kalogerakis, Ming-Hsuan Yang, and Jan Kautz, CVPR 2018 (oral)
[Pia-cvpr18]
The best of both worlds: Combining CNNs and geometric constraints for hierarchichal motion segmentation, Pia Bideau, Aruni RoyChowdhury, Rakesh Menon, and Erik Learned-Miller, CVPR 2018
 [CSGNet]
CSGNet: Neural Shape Parser for Constructive Solid Geometry, Gopal Sharma, Rishabh Goyal, Difan Liu, Evangelos Kalogerakis and Subhransu Maji, CVPR 2018
[CrossQualityDistillation]
Adapting Models to Signal Degradation using Distillation, Jong-Chyi Su and Subhransu Maji, BMVC 2017
[VisDiff]
Reasoning about Fine-grained Attribute Phrases using Reference Games, Jong-Chyi Su*, Chenyun Wu*, Huaizu Jiang and Subhransu Maji, ICCV 2017
*indicates equal contribution.
[motionSegmentation]
Causal Motion Segmentation in Moving Camera Videos, Pia Bideau and Erik Learned-Miller, ECCV 2016
[erClustering]
End-to-end Face Detection and Cast Grouping in Movies Using Erdős–Rényi Clustering, SouYoung Jin, Hang Su, Chris Stauffer and Erik Learned-Miller, ICCV 2017
[BCNN]
Bilinear CNN Models for Fine-grained Visual Recognition, Tsung-Yu Lin, Aruni Roy Chowdhury, Subhransu Maji, ICCV 2015, CVPR 2016, PAMI 2017, BMVC 2017
[MVCNN]
Multi-view CNN for 3D Shape Recognition, Hang Su, Subhransu Maji, Evangelos Kalogerakis and Erik Learned-Miller, ICCV 2015
[DFS FOR TRACKING]
Tracking with Distribution Fields, Laura Sevilla-Lara and Erik Learned-Miller, CVPR 2012
[BG]
Background Modeling using Adaptive Pixelwise Kernel Variances in a Hybrid Feature Space, Manjunath Narayana, Allen Hanson, and Erik Learned-Miller, CVPR 2012
[CRBM]
Learning Hierarchical Representations for Face Verification with Convolutional Deep Belief Networks, Gary B. Huang, Honglak Lee, and Erik Learned-Miller, CVPR 2012
[OCR]
Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling
Andrew Kae*, Kihyuk Sohn*, Honglak Lee, and Erik Learned-Miller,CVPR 2013
*indicates equal contribution.
[STR]
Improving Open-Vocabulary Scene Text Recognition, Jacqueline Feild, Erik Learned-Miller, ICDAR 2013
[IR]
Scene Text Segmentation via Inverse Rendering
Yahan Zhou, Jacqueline Feild, Rui Wang, Erik Learned-Miller, ICDAR 2013