CARLOR @ Ego4D Step Grounding Challenge: Bayesian temporal-order priors for test time refinement
Year: 2024
Type: preprint
Abstract: The goal of the Step Grounding task is to locate temporal boundaries of activities based on natural language descriptions. This technical report introduces a Bayesian-VSLNet to address the challenge of identifying such temporal segments in lengthy, untrimmed egocentric videos. Our model significantly improves upon traditional models by incorporating a novel Bayesian temporal-order prior during inference, enhancing the accuracy of moment predictions. This prior adjusts for cyclic and repetitive actions within videos. Our evaluations demonstrate superior performance over existing methods, achieving state-of-the-art results on the Ego4D Goal-Step dataset with a 35.18 Recall Top-1 at 0.3 IoU and 20.48 Recall Top-1 at 0.5 IoU on the test set.
Source: arXiv (Cornell University)
Institution: Universidad de Zaragoza
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: G6971569238, G851157260
OpenAlex ID: W4399758665