Shashanka Venkataramanan

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

I recently 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 beautiful 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

News

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

	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, Oral (top 1.2%) paper / OpenReview / Project Page / Dataset / Code / bibtex
	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 / bibtex
	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
	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
	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
	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
	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
	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

Academic Services

[2023] Reviewer for CVPR

[2022] Reviewer for ICLR, CVPR, ECCV, NeurIPS

[2021] Reviewer for ICCV, ACM Multimedia, ACM Multimedia Asia