Andreas Veit

I received my PhD in Computer Science working with Serge Belongie at Cornell University and Cornell Tech in 2018. My research interests are in Deep Learning, Computer Vision and Machine Learning.
I received a BS and MS in Information Engineering and Management both from Karlsruhe Institute of Technology (KIT), Germany, in 2010 and 2013.

Currently, I am a research scientist at Google NYC [CV].

See also my personal web page.

Publications

2019

Convolutional Networks with Adaptive Inference Graphs

Veit, Andreas; Belongie, Serge

Convolutional Networks with Adaptive Inference Graphs

International Journal of Computer Vision (IJCV), 2019.

(Links | BibTeX)

2018

Convolutional Networks with Adaptive Inference Graphs

Veit, Andreas; Belongie, Serge

Convolutional Networks with Adaptive Inference Graphs

European Conference on Computer Vision (ECCV), Munich, Germany, 2018.

(Links | BibTeX)

Semantic Segmentation with Scarce Data

Katsman, Isay; Tripathi, Rohun; Veit, Andreas; Belongie, Serge

Semantic Segmentation with Scarce Data

International Conference of Machine Learning Workshop (ICMLW), Stockholm, Sweden, 2018.

(Links | BibTeX)

Separating Self-Expression and Visual Content in Hashtag Supervision

Veit, Andreas; Nickel, Maximilian; Belongie, Serge; van der Maaten, Laurens

Separating Self-Expression and Visual Content in Hashtag Supervision

Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, 2018.

(Links | BibTeX)

Learning to Evaluate Image Captioning

Cui, Yin; Yang, Guandao; Veit, Andreas; Huang, Xun; Belongie, Serge

Learning to Evaluate Image Captioning

Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, 2018.

(Links | BibTeX)

2017

Crowd Research: Open and Scalable University Laboratories

Vaish, Rajan; Gaikwad, Snehalkumar (Neil); Kovacs, Geza; Veit, Andreas; Krishna, Ranjay; Ibarra, Imanol Arrieta; Simoiu, Camelia; Wilber, Michael; Belongie, Serge; Goel, Sharad; Davis, James; Bernstein, Michael

Crowd Research: Open and Scalable University Laboratories

User Interface Software and Technology (UIST), ACM, Quebec City, 2017.

(Links | BibTeX)

Conditional Similarity Networks

Veit, Andreas; Belongie, Serge; Karaletsos, Theofanis

Conditional Similarity Networks

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

(Links | BibTeX)

Learning From Noisy Large-Scale Datasets With Minimal Supervision

Veit, Andreas; Alldrin, Neil; Chechik, Gal; Krasin, Ivan; Gupta, Abhinav; Belongie, Serge

Learning From Noisy Large-Scale Datasets With Minimal Supervision

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

(Links | BibTeX)

2016

Residual Networks Behave Like Ensembles of Relatively Shallow Networks

Veit, Andreas; Wilber, Michael; Belongie, Serge

Residual Networks Behave Like Ensembles of Relatively Shallow Networks

Neural Information Processing Systems (NIPS), Barcelona, 2016.

(Links | BibTeX)

Learning to Detect and Match Keypoints with Deep Architectures

Altwaijry, Hani; Veit, Andreas; Belongie, Serge

Learning to Detect and Match Keypoints with Deep Architectures

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

(Links | BibTeX)

COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images

Veit, Andreas; Matera, Tomas; Neumann, Lukas; Matas, Jiri; Belongie, Serge

COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images

arXiv preprint arXiv:1601.07140, 2016.

(Links | BibTeX)

2015

Learning Visual Clothing Style with Heterogeneous Dyadic Co-occurrences

Veit*, Andreas; Kovacs*, Balazs; Bell, Sean; McAuley, Julian; Bala, Kavita; Belongie, Serge

Learning Visual Clothing Style with Heterogeneous Dyadic Co-occurrences

International Conference on Computer Vision (ICCV), Santiago, Chile, 2015, (*Equal Contribution).

(Abstract | Links | BibTeX)

On Optimizing Human-Machine Task Assignments

Veit, Andreas; Wilber, Michael; Vaish, Rajan; Belongie, Serge; Davis, James; others,

On Optimizing Human-Machine Task Assignments

AAAI Conference on Human Computation and Crowdsourcing (HCOMP), San Diego, CA, 2015, (Work in Progress).

(Abstract | Links | BibTeX)