collaborators

5 papers

cs.CV2026

CalibFree: Self-Supervised View Feature Separation for Calibration-Free Multi-Camera Multi-Object Tracking

Ruiqi Xian, Deep Patel, Iain Melvin +3

Multi-camera multi-object tracking (MCMOT) faces significant challenges in maintaining consistent object identities across varying camera perspectives, particularly when precise ca…

cs.CV2025

ProbRes: Probabilistic Jump Diffusion for Open-World Egocentric Activity Recognition

Sanjoy Kundu, Shanmukha Vellamcheti, Sathyanarayanan N. Aakur

Open-world egocentric activity recognition poses a fundamental challenge due to its unconstrained nature, requiring models to infer unseen activities from an expansive, partially o…

cs.RO2025

EASE: Embodied Active Event Perception via Self-Supervised Energy Minimization

Zhou Chen, Sanjoy Kundu, Harsimran S. Baweja +1

Active event perception, the ability to dynamically detect, track, and summarize events in real time, is essential for embodied intelligence in tasks such as human-AI collaboration…

cs.CV2025

Hallucinate, Ground, Repeat: A Framework for Generalized Visual Relationship Detection

Shanmukha Vellamcheti, Sanjoy Kundu, Sathyanarayanan N. Aakur

Understanding relationships between objects is central to visual intelligence, with applications in embodied AI, assistive systems, and scene understanding. Yet, most visual relati…

cs.CV2025

A Probabilistic Jump-Diffusion Framework for Open-World Egocentric Activity Recognition

Sanjoy Kundu, Shanmukha Vellamcheti, Sathyanarayanan N. Aakur

Open-world egocentric activity recognition poses a fundamental challenge due to its unconstrained nature, requiring models to infer unseen activities from an expansive, partially o…