CARLOR @ Ego4D Step Grounding Challenge: Bayesian temporal-order priors for test time refinement
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929385647374336 |
|---|---|
| author | Plou, Carlos Mur-Labadia, Lorenzo Martinez-Cantin, Ruben Murillo, Ana C. |
| author_facet | Plou, Carlos Mur-Labadia, Lorenzo Martinez-Cantin, Ruben Murillo, Ana C. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_09575 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CARLOR @ Ego4D Step Grounding Challenge: Bayesian temporal-order priors for test time refinement Plou, Carlos Mur-Labadia, Lorenzo Martinez-Cantin, Ruben Murillo, Ana C. Computer Vision and Pattern Recognition 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. |
| title | CARLOR @ Ego4D Step Grounding Challenge: Bayesian temporal-order priors for test time refinement |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.09575 |