Prakash Chandra Chhipa — accepted AI-conference papers

2026

VidTAG: Temporally Aligned Video to GPS Geolocalization with Denoising Sequence Prediction at a Global Scale

Parth Parag Kulkarni, Rohit Gupta, Prakash Chandra Chhipa, Mubarak Shah

CVPR 2026

The task of video geolocalization aims to determine the precise GPS coordinates of a video's origin and map its trajectory; with applications in forensics, social media, and exploration. Existing classification-based approaches operate at a coarse city-level granularity and fail to capture fine-grai

Cited by 0 Source ↗code ↗Scholar ↗

2025

ASTrA: Adversarial Self-supervised Training with Adaptive-Attacks

Prakash Chandra Chhipa, Gautam Vashishtha, Settur Jithamanyu, Rajkumar Saini, Mubarak Shah, Marcus Liwicki

ICLR 2025poster

Existing self-supervised adversarial training (self-AT) methods rely on hand-crafted adversarial attack strategies for PGD attacks, which fail to adapt to the evolving learning dynamics of the model and do not account for instance-specific characteristics of images. This results in sub-optimal adver…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗