Michael Gygli, Computer Vision engineer at gifs.com and PhD Student at ETH Zurich

Hi and welcome. My name is Michael Gygli and I am a fifth year PhD candidate under the supervision of Prof. Luc Van Gool at the Computer Vision Laboratory of ETH Zurich. Most importantly, I am also a Computer Vision engineer at gifs.com, where we use Machine Learning and Computer Vision to make video editing and gif creation intelligent and easy. We are hiring Computer Vision and Machine Learning engineers - please get in touch, if you are interested.

The research during my PhD was focused on video summarization, but I am also interested in deep learning, affective attributes, submodularity and data summarization in general.

Check the publications page or my Google Scholar profile for previous publications. I also provide code for some of my work on Github.

Slides for my CVPR tutorial talk "Video Summarization as Subset Selection": Click here

This is me, a happy consumer of

Check github.com/Lasagne/Recipes
for some great recipes.


2017 Mar: Our pre-print Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs is now on arXiv.
2017 Mar: Our pre-print PathTrack: Fast Trajectory Annotation with Path Supervision is now on arXiv.
2017 Jan: Our work AENet: Learning Deep Audio Features for Video Analysis is available on arXiv. We provide the pre-trained network and code to run it on GitHub.
2017 Jan: I joined gifs.com as a Computer Vision engineer. We are hiring - get in touch if you are interested.
2016 Aug-Nov: I was interning at Google Brain.
2016 Jun: I co-organized the tutorial "Optimization Algorithms for Subset Selection and Summarization in Large Data Sets" at CVPR 2016. You can find my slides on Video Summarization as Subset Selection here.
2016 Jun: We now provide the pretrained model and some demo code for the Video2GIF paper on GitHub.
2016 Jun: We now have a demo for the Video2GIF paper.

Recent Publications
ACM MM 2016

Analyzing and Predicting GIF Interestingness
M. Gygli, M. Soleymani (equal contribution)

InterSpeech 2016

Deep Convolutional Neural Networks and Data Augmentation for Acoustic Event Detection
N. Takahashi M. Gygli, B. Pfister, L. Van Gool

CVPR 2016

Video2GIF: Automatic Generation of Animated GIFs from Video
M. Gygli, Y. Song, L. Cao

CVPR 2016

Predicting When Saliency Maps are Accurate and Eye Fixations Consistent
A. Volokitin, M. Gygli, X. Boix

MediaEval 2015

ETH-CVL @ MediaEval 2015: Learning Objective Functions for Improved Image Retrieval
S. Srivatsa R, M. Gygli, L. Van Gool

CVPR 2015

Video Summarization by Learning Submodular Mixtures of Objectives
M. Gygli, H. Grabner, L. Van Gool