Aritra Bhowmik

​I am a PhD candidate at the Video and Image Sense (VIS) Lab at the University of Amsterdam, under the supervision of Cees G. M. Snoek. My research interests encompass computer vision, with a focus on vision-language models, video understanding, and object detection. I obtained my master's degree in artificial intelligence from the Indian Institute of Science, Bangalore, where I worked under the guidance of Chandra Sekhar Seelamantula on image super-resolution.

Following my master's, I joined the Computer Graphics and Visualization (CGV) group at TU Dresden, collaborating with Stefan Gumhold on a project with FSD . Our team developed a platform for testing self-driving car algorithms.

Currently, my research focuses on video understanding and video generation.

Publications

Structured-Noise Masked Modeling for Video, Audio and Beyond
Preprint, 2025

Aritra Bhowmik, Fida Mohammad Thoker, Carlos Hinojosa, Bernard Ghanem, Cees G. M. Snoek
arXiv
TWIST & SCOUT: Grounding Multimodal LLM-Experts by Forget-Free Tuning
Preprint, 2025

Aritra Bhowmik, Mohammad Mahdi Derakhshani, Dennis Koelma, Yuki M. Asano, Martin R. Oswald, Cees G. M. Snoek
arXiv
Union-over-Intersections: Object Detection beyond Winner-Takes-All
ICLR 2025 spotlight

Aritra Bhowmik, Pascal Mettes, Martin R. Oswald, Cees G. M. Snoek
arXiv
Detecting Objects with Context-Likelihood Graphs and Graph Refinement
ICCV 2023

Aritra Bhowmik, Yu Wang, Nora Baka, Martin R. Oswald, Cees G. M. Snoek
arXiv
ArtiVisual: A Platform to Generate and Compare Art
ACM Multimedia 2021

Jardenna Mohazzab, Abe Vos, Jonathan Van Westendorp, Lucas Lageweg, Dylan Prins, Aritra Bhowmik
Paper
Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task
CVPR 2020 oral

Aritra Bhowmik, Stefan Gumhold, Carsten Rother, Eric Brachmann
Paper
Bayesian Deep Deconvolutional Neural Networks
NIPS 2017 Workshop

Aritra Bhowmik, Aniruddha Adiga, Chandra Sekhar Seelamantula, Fabian Hauser, Jaroslaw Jacak, Bettina Heise
Paper
Bayesian Deep Deconvolutional Neural Networks
NIPS 2017 Workshop

Aritra Bhowmik, Suprosanna Shit, Chandra Sekhar Seelamantula
Paper