Probabilistic Cross-Modal Embeddings @ CVPR 2021 (March 2021)

Our work on Probabilistic Embeddings for Cross-Modal Retrieval was accepted at CVPR 2021. This is a collaboration with Sanghyuk Chun and Seong Joon Oh from the NAVER AI Lab in Korea as well as Rafael S. de Rezende and Diane Larlus from NAVER LABS Europe.

Concept Generalization (CoG) Benchmark (December 2020)

A pre-print for our work on Concept Generalization in Visual Representation Learning is now public. Check out our project page for code and results or this Twitter thread for a summary of results. Work led by the amazing Mert Bulent Sariyildiz and together with Diane Larlus and Karteek Alahari.

Hard Negative Mixing @ NeurIPS 2020 (September 2020)

Our work on Hard Negative Mixing for Contrastive Learning was accepted as a poster presentation at NeurIPS 2020. Resources: [Project page] (with pretrained models), [Blog Post], [slides].

Call for an awesome PhD position (August 2020)

[Position has now been filled].
Seeking for a highly motivated candidate for a PhD position at CTU in Prague, sponsored by NAVER LABS Europe and co-supervised by Prof. Giorgos Tolias and myself. Candidates belonging to underrepresented groups in AI research are highly encouraged to apply.

Cyclical Visual Grounding @ ECCV 2020 (July 2020)

Our paper Learning to Generate Grounded Image Captions without Localization Supervision. was accepted at ECCV 2020. [Project Page], [code]

New chapter: Naver Labs Europe (March 2020)

After three amazing years at Facebook AI, joined the Computer Vision Group at Naver Labs Europe in Grenoble as a research scientist.

Paper and Workshop accepted @ ICLR 2020 (December 2019)

Excited to announce that our paper Decoupling Representation and Classifier for Long-Tailed Recognition was accepted at the International Conference on Representation Learning (ICLR) 2020!

Moreover, the 1st workshop on Computer Vision for Agriculture (CV4A), the second workshop of the Computer Vision for Global Challenges initiative, will be held in April 2020 in conjunction with ICLR, in Addis Ababa, Ethiopia. Find more information at the CV4A Workshop webpage.

Data Science Africa 2019 (Accra, Ghana) (October 2019)

Excited to teach a short tutorial on "Image representations and fine-grained recognition" at Data Science Africa, in Accra, Ghana, on October 22nd. The tutorial slides can be found here in normal resolution (~6.2MB) or lower resolution (~1.6MB).

The slides from my DSA talk on "Learnings from the Computer Vision for Global Challenges (CV4GC) initiative" can be found here.

Octave Convolution @ ICCV 2019 (July 2019)

Our paper Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution. was accepted at ICCV 2019! Work with awesome collaborators from the National University of Singapore.

Official code is at the facebook research github repo, and will further be updated and extended soon. Numerous implementations of OctConv can be found on Papers With Code.

Four papers accepted @ CVPR 2019 (February 2019)

Delighted to announce that four papers (3 poster and 1 oral) were accepted at CVPR 2019!

Computer Vision for Global Challenges Workshop @ CVPR 2019 (January 2019)

The first Workshop on Computer vision for Global Challenges (CV4GC) was accepted at CVPR this year! Really excited about organizing an initiative to bring the computer vision community closer to socially impactful tasks, datasets and applications for the whole world. More info:
- The CV4GC website
- Computer vision and global challenges: New research and applications
- Computer Vision for Global Challenges research award winners

Paper accepted in TPAMI (January 2019)

Our paper Focal Visual-Text Attention for Memex Question Answering was accepted for publication at the IEEE Transactions on Pattern Analysis and Machine Inteligence (impact factor: 9.455). It introduces our MemexQA Dataset, the first publicly available multimodal question answering dataset consisting of real personal photo albums.

Large-scale Visual Relationship Detection @ AAAI 2019 (November 2018)

Our paper Large-scale Visual Relationship Detection was accepted at the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI 2019, acceptance rate 16.2%).
[Update Feb 2019]: Code is now on github.

Double Attention Networks @ NeurIPS 2018 (September 2018)

Our paper A^2-Nets: Double Attention Networks was accepted at NeurIPS 2018. See you in Montreal! Work with awesome collaborators from the National University of Singapore.

Multi-Fiber Networks @ ECCV 2018 (July 2018)

Our paper Multi-Fiber Networks for Video Recognition was accepted at the European Conference on Computer Vision (ECCV) 2018. Work with awesome collaborators from the National University of Singapore. Code on GitHub.

Do Silhouettes Dream? (May 2017)

Our interactive art installation entitled Do Silhouettes Dream? will be on display from July 26th till August 2nd 2017 at the ArtScience Museum in Singapore. More information at this page. You may watch a short interview with Cheng and me here.

Similarity Search at Flickr (March 2017)

Our work on visual similarity search over the whole Flickr corpus just launched! Try it yourselves by clicking on the magnifying glass icon at the top right corner of any photopage! Story covered in The Verge, Engadget, Petapixel, Digital Trends and Venture Beat.

New chapter: Facebook Research (February 2017)

After two amazing years at Yahoo Research, joined the Computer Vision Group at Facebook Research in Menlo Park.

Best paper at LSCVS Workshop in NeurIPS 2016 (December 2016)

Our paper "Tag Prediction in Flickr: A view from the darkroom" on large scale image classification with noisy training data received the best paper award at the 1st Workshop on Large Scale Computer Vision Systems at NeurIPS 2016.

Paper accepted at CHI 2017 (December 2016)

Our paper "Multimodal Classification of Moderated Online Pro-Eating Disorder Content" was accepted at the ACM CHI 2017 conference (25% acceptance rate).

Guest Lecturer at Stanford CS-131 (October 2016)

Will be a guest lecturer at Fei-Fei's and Juan Carlos' CS 131 Computer Vision: Foundations and Applications course at Stanford during the 2016-2017 Fall Semester.


A short research bio

Grew up and lived in Greece until 2015 with brief breaks in Sweden, Spain and the United States. Lived in San Francisco and Oakland from 2015 till 2020. I am currently based in Grenoble but probably spend as much time in Barcelona.

Got my PhD in late 2014 from the National Technical University of Athens under the supervision of Prof. Stefanos Kollias and Yannis Avrithis, working closely with my research brother Giorgos Tolias. My PhD was on large-scale geometry indexing, nearest neighbor search and clustering.

From 2015 to 2017 I was a research scientist at Yahoo Research in San Francisco. The large-scale visual similarity search work of my PhD came to a nice closure when we applied it on a trully web-scale real-time application, powering the visual search feature on Flickr. At the same time, my interests expanded towards modeling of vision and language and collaborated with Stanford on the Visual Genome project.

From 2017 and till 2020, I was a research scientist at Facebook AI in Menlo Park, California. During this time my interests expanded to video understanding and deep learning architecture modeling.

On March 2020 I started working as a research scientist at Naver Labs Europe in Grenoble, France. Currently, my research interests include self-supervised representation learning, continual and streaming learning, multi-modal learning, video understanding and vision & language.

I am also very passionate about urging the research community tackle more socially impactful problems. Together with Laura Sevilla-Lara, we lead the Computer Vision for Global Challenges initative. Under this umbrella, we organized the CV4GC workshop at CVPR 2019, and the Computer Vision for Agrigulture (CV4A) workshop at ICLR 2020.

Contact Details

email: ykalant(at) yannis.kalantidis(at)

Selected Publications

Full list at my Google Scholar profile.


2020 2019 2018 2017 2016 2015 2014 2011 - 2013