[Submitted on 13 Jun 2024]
View a PDF of the paper titled CARLOR @ Ego4D Step Grounding Challenge: Bayesian temporal-order priors for test time refinement, by Carlos Plou and 2 other authors
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.
Submission history
From: Lorenzo Mur-Labadia [view email]
[v1]
Thu, 13 Jun 2024 20:31:28 UTC (13,406 KB)
Source link
lol
