Conference & Journal Papers
TIGeR: A Unified Framework for Time, Images and Geo-location Retrieval
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026
David G. Shatwell, Sirnam Swetha, Mubarak Shah
Many real-world applications in digital forensics, urban monitoring, and environmental analysis require jointly reasoning about visual appearance, geolocation, and time. We formalize this problem as Geo-Time Aware Image Retrieval and curate a benchmark of 4.5M paired image–location–time triplets for training and 85k triplets for evaluation. We propose TIGeR, a multimodal transformer model mapping images, geolocation, and time into a unified geo-temporal embedding space.
VRR-QA: Visual Relational Reasoning in Videos Beyond Explicit Cues
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026
Sirnam Swetha, Rohit Gupta, Parth Parag Kulkarni, David G. Shatwell, Jeffrey A. Chan Santiago, Nyle Siddiqui, Joseph Fioresi, Mubarak Shah
Current VideoQA benchmarks overwhelmingly focus on explicit content directly visible in individual frames. To address implicit reasoning gaps across cinematic cuts and implied relations, we introduce VRR-QA, an expert-annotated benchmark from creative storytelling videos revealing significant performance drops in current models.
GT-Loc: Unifying When and Where in Images Through a Joint Embedding Space
International Conference on Computer Vision, ICCV 2025
Oral Presentation (top 0.6%)
David G. Shatwell, Ishan Rajendrakumar Dave, Sirnam Swetha, Mubarak Shah
GT-Loc introduces a retrieval-based framework to jointly predict hour, date, and GPS coordinates using cyclical toroidal representations and unified embedding spaces, outperforming prior time prediction baselines even when provided ground-truth locations.
Real Time Ore Sorting Using Color and Texture Analysis
International Journal of Mining Science and Technology, 2023
David Shatwell, Victor Murray, Augusto Barton
Sensor-based ore sorting combining wavelet texture features, color statistics, and neural classifiers to separate high-grade ore from waste rock under 44 ms processing latency.