English

TubeDETR: Spatio-Temporal Video Grounding with Transformers

Computer Vision and Pattern Recognition 2022-06-10 v2 Computation and Language Machine Learning

Abstract

We consider the problem of localizing a spatio-temporal tube in a video corresponding to a given text query. This is a challenging task that requires the joint and efficient modeling of temporal, spatial and multi-modal interactions. To address this task, we propose TubeDETR, a transformer-based architecture inspired by the recent success of such models for text-conditioned object detection. Our model notably includes: (i) an efficient video and text encoder that models spatial multi-modal interactions over sparsely sampled frames and (ii) a space-time decoder that jointly performs spatio-temporal localization. We demonstrate the advantage of our proposed components through an extensive ablation study. We also evaluate our full approach on the spatio-temporal video grounding task and demonstrate improvements over the state of the art on the challenging VidSTG and HC-STVG benchmarks. Code and trained models are publicly available at https://antoyang.github.io/tubedetr.html.

Keywords

Cite

@article{arxiv.2203.16434,
  title  = {TubeDETR: Spatio-Temporal Video Grounding with Transformers},
  author = {Antoine Yang and Antoine Miech and Josef Sivic and Ivan Laptev and Cordelia Schmid},
  journal= {arXiv preprint arXiv:2203.16434},
  year   = {2022}
}

Comments

Updated vIoU results compared to the CVPR'22 camera-ready version; 17 pages; 8 figures

R2 v1 2026-06-24T10:32:08.517Z