# SimBase: A Simple Baseline for Temporal Video Grounding

arXiv: https://arxiv.org/abs/2411.07945 · HTML: https://mlsanity.com/paper/2411.07945/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 0 of its 25 references that are in the map.
- First posted on arXiv 12 Nov 2024.

## Built on by (most cited first, 3 of 3)

- [Vid-Morp: Video Moment Retrieval Pretraining from Unlabeled Videos in the Wild](https://mlsanity.com/paper/2412.00811/) (2024)
- [Training-Free Temporal Abstraction for General Video Understanding](https://mlsanity.com/paper/2608.27929/) (2026)
- [Pocket-STVG: lightweight architecture for Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2609.31135/) (2026)

## Abstract (arXiv)

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.