dibyadip (at) u.nus.edu

I am a third-year PhD Student in the School of Computing at the National University of Singapore. I am a part of CVML@NUS advised by Angela Yao. My graduate research is supported by the President's Graduate Fellowship.

In the summer of 2024, I interned at Meta Reality Labs, hosted by Fadime Sener. I completed my bachelor's in ECE from Jadavpur University where I worked with Sanjoy Kumar Saha and Ananda S. Chowdhury. My bachelor's thesis was on Open-Set Metric Learning for Person Re-identification in the Wild.

Broadly, I am interested in understanding how humans perceive the 4D (3D+time) world. My current research focuses on developing large vision-language models for video understanding and generation, as well as 4D modeling of human-object interactions.

News

[06/2025] ProVideLLM has been accepted to ICCV 2025.
[05/2025] Recognized as an Outstanding Reviewer at CVPR 2025.
[04/2025] Check out our latest work ProVideLLM. Now available on arXiv.
[07/2024] HandFormer has been accepted to ECCV 2024.
[06/2024] Joined Meta Reality Labs in Zürich as a Research Scientist Intern. Working with Fadime Sener and Edoardo Remelli.
[06/2024] Assembly101 was awarded the 2022/2023 Distinguished Paper Award at the EgoVis workshop.
[05/2024] HandFormer will be presented at the EgoVis workshop during CVPR 2024.
[03/2024] Check out our latest work "On the Utility of 3D Hand Poses for Action Recognition". Now available on arXiv.
[09/2023] "Opening the Vocabulary of Egocentric Actions" has been accepted to NeurIPS 2023.
[08/2023] Our latest work "Opening the Vocabulary of Egocentric Actions" is now available on arXiv.
[07/2023] Awarded the President's Graduate Fellowship for my PhD at NUS.
[07/2023] Joining CVML@NUS as a PhD student starting this Fall 2023.
[10/2022] Organized Human Body, Hands, and Activities from Egocentric and Multi-view Cameras (HBHA) workshop at ECCV 2022.
[03/2022] Paper proposing a new procedural activity dataset Assembly101 has been accepted to CVPR 2022.

Publications & Preprints
	Memory-efficient Streaming VideoLLMs for Real-Time Procedural Video Understanding Dibyadip Chatterjee, Edoardo Remelli, Yale Song, Bugra Tekin, Abhay Mittal, Bharat Bhatnagar, Necati Cihan Camgöz, Shreyas Hampali, Eric Sauser, Shugao Ma, Angela Yao, Fadime Sener ICCV 2025 (New) Paper Page
	On the Utility of 3D Hand Poses for Action Recognition Md Salman Shamil, Dibyadip Chatterjee, Fadime Sener, Shugao Ma, Angela Yao ECCV 2024 Paper Page
	Opening the Vocabulary of Egocentric Actions Dibyadip Chatterjee, Fadime Sener, Shugao Ma, Angela Yao NeurIPS 2023 Paper Page
	Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities Fadime Sener, Dibyadip Chatterjee, Daniel Shelepov, Kun He, Dipika Singhania, Robert Wang, Angela Yao CVPR 2022 EgoVis 2022/2023 Distinguished Paper Winner Paper Page Video
	Technical Report: Temporal Aggregate Representations Fadime Sener, Dibyadip Chatterjee, Angela Yao arXiv 2021 Paper Code
	Open-set Metric Learning for Person Re-Identification in the Wild Arindam Sikdar, Dibyadip Chatterjee, Arpan Bhowmik, Ananda S. Chowdhury ICIP 2020 Paper

Academic Service

Conference Reviewer: CVPR, ICCV, ECCV, BMVC, ACCV, AAAI, TPAMI, IJCV
Teaching Assistant: CS4243 (Computer Vision and Pattern Recognition), BT3017 (Feature Engineering for Machine Learning)