Arka Haldi

I am a final-year Masters of Technology by Research(M.Tech res) student at the Computational and Data Sciences (CDS) Department, of the Indian Institute of Science, Bengaluru, where I work on multi-modal computer vision. I'm a part of both Visual Computing Lab (VCL) and Vision and AI Lab (VAL) under the joint supervision of my PI's Asst. Prof. Anirban Chakraborty & Prof. R. Venkatesh Babu respectively.

I completed by B.Tech. in Computer Science & Engineering from Sardar Patel Institute of Technology, Andheri in 2022, and worked for a year in Barclays as a Data Quality Engineer before pursuing my masters.

During my batchelors I published my first paper on Fire Class Detection based on YOLO, that won the IAPR best paper for CVIP 22

My research interests lie in Multi-Modal Learning, Conditional Generative Modeling, 3D Vision, Latent knowledge and Explainability. I'm actively looking for collaborators, please feel free to reach out if you are interested in brainstorming interesting ideas in these directions!

Email  /  GitHub  /  Google Scholar  /  LinkedIn  /  X (Twitter)  /  Instagram

profile photo

Relevant Courses

Courses related to my area of interest during my Masters.

Credited Courses

Audited Courses

E1 222 Stochastic Models and Applications
E9 241 Digital Image Processing
DS 216 Machine Learning for Data Science
E0 230 Computational Methods in Optimization
DS 265 Deep Learning and Computer Vision

E2 335 Topics in Artificial Intelligence
E1 213 Pattern Recognition and Neural Networks
E0 298 Linear Algebra and Its Applications
E9 247Learning for 3D Vision and Inverse Graphics

Research

I'm interested in computer vision, machine learning, optimization, and graphics.




Ongoing Projects

These include ongoing research, side projects and unpublished research work.

project image

Untitled


ongoing
2025-06-23

description of project


 |   |   |   |   | 


Design and source code from Jon Barron's website