SimBase: A Simple Baseline for Temporal Video Grounding
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910695768981504 |
|---|---|
| author | Bao, Peijun Kot, Alex C. |
| author_facet | Bao, Peijun Kot, Alex C. |
| contents | This paper presents SimBase, a simple yet effective baseline for temporal video grounding. While recent advances in temporal grounding have led to impressive performance, they have also driven network architectures toward greater complexity, with a range of methods to (1) capture temporal relationships and (2) achieve effective multimodal fusion. In contrast, this paper explores the question: How effective can a simplified approach be? To investigate, we design SimBase, a network that leverages lightweight, one-dimensional temporal convolutional layers instead of complex temporal structures. For cross-modal interaction, SimBase only employs an element-wise product instead of intricate multimodal fusion. Remarkably, SimBase achieves state-of-the-art results on two large-scale datasets. As a simple yet powerful baseline, we hope SimBase will spark new ideas and streamline future evaluations in temporal video grounding. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_07945 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SimBase: A Simple Baseline for Temporal Video Grounding Bao, Peijun Kot, Alex C. Computer Vision and Pattern Recognition This paper presents SimBase, a simple yet effective baseline for temporal video grounding. While recent advances in temporal grounding have led to impressive performance, they have also driven network architectures toward greater complexity, with a range of methods to (1) capture temporal relationships and (2) achieve effective multimodal fusion. In contrast, this paper explores the question: How effective can a simplified approach be? To investigate, we design SimBase, a network that leverages lightweight, one-dimensional temporal convolutional layers instead of complex temporal structures. For cross-modal interaction, SimBase only employs an element-wise product instead of intricate multimodal fusion. Remarkably, SimBase achieves state-of-the-art results on two large-scale datasets. As a simple yet powerful baseline, we hope SimBase will spark new ideas and streamline future evaluations in temporal video grounding. |
| title | SimBase: A Simple Baseline for Temporal Video Grounding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.07945 |