Joint Event Detection and Description in Continuous Video Streams

Huijuan Xu, Boyang Li, Vasili Ramanishka, Leonid Sigal, Kate Saenko

WACV 2019 pp. 396-405

doi:10.1109/WACV.2019.00048 /wacv/2019/xu2019wacv-joint/

Abstract

Dense video captioning involves first localizing events in a video and then generating captions for the identified events. We present the Joint Event Detection and Description Network (JEDDi-Net) for solving this task in an end-to-end fashion, which encodes the input video stream with three-dimensional convolutional layers, proposes variable- length temporal events based on pooled features, and then uses a two-level hierarchical LSTM module with context modeling to transcribe the event proposals into captions. We show the effectiveness of our proposed JEDDi-Net on the large-scale ActivityNet Captions dataset.

PDF WACV Semantic Scholar

Cite

Text

Xu et al. "Joint Event Detection and Description in Continuous Video Streams." IEEE/CVF Winter Conference on Applications of Computer Vision, 2019. doi:10.1109/WACV.2019.00048

Markdown

[Xu et al. "Joint Event Detection and Description in Continuous Video Streams." IEEE/CVF Winter Conference on Applications of Computer Vision, 2019.](https://mlanthology.org/wacv/2019/xu2019wacv-joint/) doi:10.1109/WACV.2019.00048

BibTeX

@inproceedings{xu2019wacv-joint,
  title     = {{Joint Event Detection and Description in Continuous Video Streams}},
  author    = {Xu, Huijuan and Li, Boyang and Ramanishka, Vasili and Sigal, Leonid and Saenko, Kate},
  booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
  year      = {2019},
  pages     = {396-405},
  doi       = {10.1109/WACV.2019.00048},
  url       = {https://mlanthology.org/wacv/2019/xu2019wacv-joint/}
}