Dense Regression Network for Video Grounding



  • Chuang Gan
  • Runhao Zeng
  • Haoming Xu
  • Wenbing Huang
  • Peihao Chen
  • Mingkui Tan

Published on


We address the problem of video grounding from natural language queries. The key challenge in this task is that one training video might only contain a few annotated starting/ending frames that can be used as positive examples for model training. Most conventional approaches directly train a binary classifier using such imbalance data, thus achieving inferior results. The key idea of this paper is to use the distances between the frame within the ground truth and the starting (ending) frame as dense supervisions to improve the video grounding accuracy. Specifically, we design a novel dense regression network (DRN) to regress the distances from each frame to the starting (ending) frame of the video segment described by the query. We also propose a simple but effective IoU regression head module to explicitly consider the localization quality of the grounding results (i.e., the IoU between the predicted location and the ground truth). Experimental results show that our approach significantly outperforms state-of-the-arts on three datasets (i.e., Charades-STA, ActivityNet-Captions, and TACoS).

Please cite our work using the BibTeX below.

author = {Zeng, Runhao and Xu, Haoming and Huang, Wenbing and Chen, Peihao and Tan, Mingkui and Gan, Chuang},
title = {Dense Regression Network for Video Grounding},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
Close Modal