Tsung-Yu Lin

Research Assistant
Computer Science
University of Massachusetts Amherst
tsungyulin at cs.umass.edu

I am a fourth year Computer Science PhD student at University of Massachusetts Amherst. I am working at Computer Vision Lab led by Prof. Erik Learned-Miller and Prof. Subhransu Maji. My research interests are in computer vision and machine learning. Specifically, I am interested in extracting high-level visual information for image recognition problem.

I had been working as intern under the supervision of R. Manmatha and Deva Ranmanan at Amazon AI. I had been working at Academia Sinica with Dr. Tyng-Luh Liu before I joined UMass. Before that, I completed my MS degree at National Tsing Hua University advised by Prof. Shang-Hong Lai. See more on my CV. Also, you can check out my Google scholar.

Home

Research

Publication

CV

Projects

	Second-order Democratic Aggregation		Dark Ecology: tracking bird migration with computer vision and deep learning techniques
	Visualizing and Understanding Deep Texture Representations		Bilinear CNN for Fine-Grained Classification
	People localization in a camera network pdf		Shape Prior Non-Rigid SfM for deformable Surfaces pdf
	Multi-camera and multi-target surveillance tracking		3D Face Model Deformation

Publications

Second-order Democratic Aggregation
Tsung-Yu Lin, Subhransu Maji and Piotr Koniusz
ECCV 2018 [project] [pdf] [arXiv]

Improved Bilinear Pooling with CNNs
Tsung-Yu Lin, and Subhransu Maji
BMVC 2017 (Oral) [project] [pdf] [arXiv]

Bilinear Convolutional Neural Networks for Fine-grained Visual Recognition
Tsung-Yu Lin, Aruni RoyChowdhury and Subhransu Maji
PAMI 2017 [project] [pdf]

Visualizing and Understanding Deep Texture Representations
Tsung-Yu Lin, and Subhransu Maji
CVPR 2016 [project] [pdf] [arXiv]

One-to-many face recognition with Bilinear CNNs
Aruni RoyChowdhury, Tsung-Yu Lin, Subhransu Maji, and Erik Learned-Miller
WACV 2016 [pdf]

Implicit Sparse Code Hashing
Tsung-Yu Lin, Tsung-Wei Ke, Tyng-Luh Liu
arXiv:1512.00130 , 2015 [arXiv]

Bilinear CNN Models for Fine-grained Visual Recognition
Tsung-Yu Lin, Aruni RoyChowdhury, Subhransu Maji
ICCV 2015 (Oral, Acceptance rate: 3.3%) [project] [pdf] [pdf-supp] [arXiv] [slides] [poster] [bibtex]

Efficient binary codes for extremely high-dimensional data
Tsung-Yu Lin, Tyng-Lug Liu
ICIP 2014 [pdf]

People localization in a camera network combining background subtraction and scene-aware human detection
Tung-Ying Lee, Tsung-Yu Lin, Szu-Hao Huang, Shang-Hong Lai, Shang-Chih Hung
MMM 2011 [pdf]