Jan 2023 – Jun 2023 · 5 mos

May 2022 – Jul 2022 · 2 mos

• Topic: optical flow estimation via unsupervised learning

Dec 2021 – May 2022 · 5 mos

• Topic: video classification using graph neural network on multi-modal data

May 2021 – Aug 2021 · 3 mos · Bangalore Urban, Karnataka, India

Jan 2021 – Jun 2023 · 2 yrs 5 mos

• Working on developing methods for training video action detection model under limited annotations

Nov 2020 – Dec 2021 · 1 yr 1 mo

• Worked on Segmenting transparent object in RGB images which are captured in a diverse environment

May 2020 – Aug 2020 · 3 mos · Delhi, India

• Worked on cross-domain synthetic image pair generation for the Person Re-Identification task and developing a more accurate model with better rank accuracy such as CMC and mAP.

Feb 2020 – Apr 2020 · 2 mos

• Worked on Image restoration and enhancing.
• Developed a GAN based CNN architecture for Single Image Dehazing. The architecture was end-to-end trainable with state of the art results and real-time speed.
• The paper was accepted at ECCV'20 Workshop AIM 2020.

Oct 2019 – Nov 2020 · 1 yr 1 mo

• Worked on achieving temporal consistency in videos to video tasks such as video super resolution. Technique such as GANS, image to image CNN network, optical flow calculation and warping were explored. The research was supported by NSERC.

Jan 2019 – Jun 2023 · 4 yrs 5 mos · Dhanbad Area, India