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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kundu, Sanjoy, Vellamcheti, Shanmukha, Aakur, Sathyanarayanan N.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912640733806592
author Kundu, Sanjoy
Vellamcheti, Shanmukha
Aakur, Sathyanarayanan N.
author_facet Kundu, Sanjoy
Vellamcheti, Shanmukha
Aakur, Sathyanarayanan N.
contents Open-world egocentric activity recognition poses a fundamental challenge due to its unconstrained nature, requiring models to infer unseen activities from an expansive, partially observed search space. We introduce ProbRes, a Probabilistic Residual search framework based on jump-diffusion that efficiently navigates this space by balancing prior-guided exploration with likelihood-driven exploitation. Our approach integrates structured commonsense priors to construct a semantically coherent search space, adaptively refines predictions using Vision-Language Models (VLMs) and employs a stochastic search mechanism to locate high-likelihood activity labels while minimizing exhaustive enumeration efficiently. We systematically evaluate ProbRes across multiple openness levels (L0-L3), demonstrating its adaptability to increasing search space complexity. In addition to achieving state-of-the-art performance on benchmark datasets (GTEA Gaze, GTEA Gaze+, EPIC-Kitchens, and Charades-Ego), we establish a clear taxonomy for open-world recognition, delineating the challenges and methodological advancements necessary for egocentric activity understanding. Our results highlight the importance of structured search strategies, paving the way for scalable and efficient open-world activity recognition.
format Preprint
id arxiv_https___arxiv_org_abs_2504_03948
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ProbRes: Probabilistic Jump Diffusion for Open-World Egocentric Activity Recognition
Kundu, Sanjoy
Vellamcheti, Shanmukha
Aakur, Sathyanarayanan N.
Computer Vision and Pattern Recognition
Open-world egocentric activity recognition poses a fundamental challenge due to its unconstrained nature, requiring models to infer unseen activities from an expansive, partially observed search space. We introduce ProbRes, a Probabilistic Residual search framework based on jump-diffusion that efficiently navigates this space by balancing prior-guided exploration with likelihood-driven exploitation. Our approach integrates structured commonsense priors to construct a semantically coherent search space, adaptively refines predictions using Vision-Language Models (VLMs) and employs a stochastic search mechanism to locate high-likelihood activity labels while minimizing exhaustive enumeration efficiently. We systematically evaluate ProbRes across multiple openness levels (L0-L3), demonstrating its adaptability to increasing search space complexity. In addition to achieving state-of-the-art performance on benchmark datasets (GTEA Gaze, GTEA Gaze+, EPIC-Kitchens, and Charades-Ego), we establish a clear taxonomy for open-world recognition, delineating the challenges and methodological advancements necessary for egocentric activity understanding. Our results highlight the importance of structured search strategies, paving the way for scalable and efficient open-world activity recognition.
title ProbRes: Probabilistic Jump Diffusion for Open-World Egocentric Activity Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.03948