Shashanka Venkataramanan

I am a final year doctoral student with the LinkMedia team at INRIA, where I am advised by Dr. Yannis Avrithis. My work mainly focuses on developing algorithms to enhance instance and category-level visual representations in the supervised and self-supervised settings.

I recently interned with the video efficiency team at Qualcomm AI Research in the beautiful city of Amsterdam. I graduated with my Masters in C.S from the Center for Research in Computer Vision at the University of Central Florida, USA with Dr. Abhijit Mahalanobis. Prior joining UCF, I spent some time at the Indian Institute of Science as a research assistant with Dr. Soma Biswas and Dr. Sivaram Prasad Mudunuri. I feel lucky and am grateful to have worked with them.

Email  /  CV  /  Google Scholar  /  Twitter  /  LinkedIn  /  GitHub

profile photo
News

  May 2024: DoRA received an Outstanding paper honorable mention at ICLR 2024 🥳 
  April 2024: Hosting the 1st edition of our tutorial Self-Supervised Learning Beyond Images at ECCV 2024 in Milan!!
  April 2024: Invited to give a talk at Meta AI (FAIR) in Paris
  Jan 2024: Invited to give a talk at IBM Research, Zurich (online)
  Jan 2024: SkipAT and DoRA are accepted to ICLR 2024; DoRA accepted as an Oral
  Sept 2023: MultiMix is accepted to NeurIPS 2023
  July 2023: Attending the ICVSS Summer School in Sicily
  January 2023: SkipAT released on arXiv
  September 2022: Attending the ELLIS Video Sympsium (invite only) in Amsterdam
  June 2022: Starting internship with Video Efficiency team at Qualcomm AI Research in Amsterdam
  May 2022: MultiMix released on arXiv
  February 2022: AlignMixup is accepted to CVPR 2022
  January 2022: Metrix is accepted to ICLR 2022
  December 2021: Teaching Deep Metric learning course at MathSTIC
  September 2021: Attending the ELLIS doctoral symposium in Tubingen
  December 2020: Started my PhD at INRIA

Publications
DoRA-2023 Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video
Shashanka Venkataramanan, Mamshad Nayeem Rizve, João Carreira, Yuki M. Asano*, Yannis Avrithis*
International Conference on Learning Representations (ICLR), 2024
Outstanding paper honorable mention
paper /  OpenReview /  project page /  HF dataset /  code /  bibtex
skipAT-2023 Skip-Attention: Improving Vision Transformers by Paying Less Attention
Shashanka Venkataramanan, Amir Ghodrati, Yuki M. Asano, Fatih Porikli, Amirhossein Habibian
International Conference on Learning Representations (ICLR), 2024
paper /  Code /  bibtex
MultiMix-2023 Embedding Space Interpolation Beyond Mini-Batch, Beyond Pairs and Beyond Examples
Shashanka Venkataramanan, Ewa Kijak, Laurent Amsaleg, Yannis Avrithis
Neural Information Processing Systems (NeurIPS), 2023
arxiv /  HAL /  bibtex /  code /  video /  slides /  poster
alignmix-cvpr2022 AlignMixup: Improving Representations By Interpolating Aligned Features
Shashanka Venkataramanan, Ewa Kijak, Laurent Amsaleg, Yannis Avrithis
IEEE/CVF Proceedings on Computer Vision and Pattern Recognition (CVPR), 2022
arxiv /  HAL /  bibtex /  code

metrix-iclr2022 It Takes Two to Tango: Mixup for Deep Metric Learning
Shashanka Venkataramanan, Bill Psomas, Ewa Kijak, Laurent Amsaleg, Konstantinos Karantzalos, Yannis Avrithis
International Conference on Learning Representations (ICLR), 2022
arxiv /  bibtex /  code /  video /  slides /  poster
cavga-eccv2020 Attention Guided Anomaly Localization in Images
Shashanka Venkataramanan, Kuan-Chuan Peng, Rajat Vikram Singh, Abhijit Mahalanobis
In European Conference on Computer Vision (ECCV), 2020
paper /  bibtex /  arxiv /  teaser video /  main video
tclr-icip2020 Target Detection in Cluttered Environments using Infra-red Images
Bruce McIntosh, Shashanka Venkataramanan, Abhijit Mahalanobis
IEEE International Conference on Image Processing (ICIP), 2020
arxiv /  bibtex
dalign-tifs2019 Dictionary alignment with re-ranking for low-resolution NIR-VIS face recognition
Sivaram Prasad Mudunuri*, Shashanka Venkataramanan*, Soma Biswas
IEEE Transactions on Information Forensics and Security, 2019
paper /  bibtex /  code
Workshops and Tutorials
skipAT-2023 Time is precious: Self-Supervised Learning Beyond Images
Shashanka Venkataramanan, Mohammadreza Salehi, Yuki M. Asano
ECCV, 2024
Academic Services

  • [2023] Reviewer for CVPR
  • [2022] Reviewer for ICLR, CVPR, ECCV, NeurIPS
  • [2021] Reviewer for ICCV, ACM Multimedia, ACM Multimedia Asia