5 papers
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…
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…
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…
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…
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…