Tsung-Yi Lin

I received my PhD at Cornell NYC Tech supervised by Serge Belongie in 2017. Before I came to NYC, I spent two wonderful years at UCSD. My research interest are in Computer Vision, in particular learning visual representations for cross-view image matching and object detection. Luckily, I had great opportunity to work with James Hays on cross-view image geolocalization and Piotr Dollár on object detection. Currently, I am a research scientist at Google Brain. [cv]

Publications

2019

Class-Balanced Loss Based on Effective Number of Samples

Cui, Yin; Jia, Menglin; Lin, Tsung-Yi; Song, Yang; Belongie, Serge

Class-Balanced Loss Based on Effective Number of Samples

Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, 2019.

(Links | BibTeX)

2017

Focal Loss for Dense Object Detection (Best Student Paper Award)

Lin, Tsung-Yi; Goyal, Priya; Girshick, Ross; He, Kaiming; Dollár, Piotr

Focal Loss for Dense Object Detection (Best Student Paper Award)

International Conference on Computer Vision (ICCV), Venice, Italy, 2017, (Oral).

(Links | BibTeX)

Feature Pyramid Networks for Object Detection

Lin, Tsung-Yi; Dollár, Piotr; Girshick, Ross; He, Kaiming; Hariharan, Bharath; Belongie, Serge

Feature Pyramid Networks for Object Detection

Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 2017.

(Links | BibTeX)

Collaborative Metric Learning

Hsieh, Cheng-Kang; Yang, Longqi; Cui, Yin; Lin, Tsung-Yi; Belongie, Serge; Estrin, Deborah

Collaborative Metric Learning

International Conference on World Wide Web (WWW), Perth, 2017.

(Links | BibTeX)

2016

Learning to Refine Object Segments

Pinheiro, Pedro; Lin, Tsung-Yi; Collobert, Ronan; Dollár, Piotr

Learning to Refine Object Segments

European Conference on Computer Vision (ECCV), Amsterdam, 2016, (spotlight).

(Links | BibTeX)

A MultiPath Network for Object Detection

Zagoruyko, Sergey; Lerer, Adam; Lin, Tsung-Yi; Pinheiro, Pedro; Gross, Sam; Chintala, Soumith; Dollár, Piotr

A MultiPath Network for Object Detection

British Machine Vision Conference (BMVC), York, UK, 2016.

(Links | BibTeX)

Lin, Tsung-Yi; Belongie, Serge; Hays, James

Cross-View Image Geo-localization

Zamir, Amir; Hakeem, Asaad; Gool, Luc Van; Shah, Mubarak; Szeliski, Richard (Ed.): Large-Scale Visual Geo-Localization, pp. 59-76, Springer, 2016.

(Links | BibTeX)

2015

Learning Deep Representations for Ground-to-Aerial Geolocalization

Lin, Tsung-Yi; Cui, Yin; Belongie, Serge; Hays, James

Learning Deep Representations for Ground-to-Aerial Geolocalization

Computer Vision and Pattern Recognition (CVPR), Boston, MA, 2015, (Oral).

(Links | BibTeX)

Microsoft COCO Captions: Data Collection and Evaluation Server

Chen, Xinlei; Hao Fang, Tsung-Yi Lin; Vedantam, Ramakrishna; Gupta, Saurabh; Dollár, Piotr; Zitnick, Lawrence

Microsoft COCO Captions: Data Collection and Evaluation Server

arXiv preprint arXiv:1504.00325, 2015.

(Links | BibTeX)

2014

Microsoft COCO: Common Objects in Context

Lin, Tsung-Yi; Maire, Michael; Belongie, Serge; Hays, James; Perona, Pietro; Ramanan, Deva; Dollár, Piotr; Zitnick, Lawrence

Microsoft COCO: Common Objects in Context

European Conference on Computer Vision (ECCV), Zürich, 2014, (Oral).

(Links | BibTeX)

2013

Cross-view Image Geolocalization

Lin, Tsung-Yi; Belongie, Serge; Hays, James

Cross-view Image Geolocalization

CVPR, Portland, OR, 2013.

(Links | BibTeX)