REVECA -- Rich Encoder-decoder framework for Video Event CAptioner

We describe an approach used in the Generic Boundary Event Captioning challenge at the Long-Form Video Understanding Workshop held at CVPR 2022. We designed a Rich Encoder-decoder framework for Video Event CAptioner (REVECA) that utilizes spatial and temporal information from the video to generate a...

Full description

Saved in:
Bibliographic Details
Main Authors Heo, Jaehyuk, Jeong, YongGi, Kim, Sunwoo, Kim, Jaehee, Kang, Pilsung
Format Journal Article
LanguageEnglish
Published 18.06.2022
Subjects
Computer Science - Artificial Intelligence
Computer Science - Computer Vision and Pattern Recognition
Online AccessGet full text
DOI10.48550/arxiv.2206.09178

Cover

More Information
Summary:We describe an approach used in the Generic Boundary Event Captioning challenge at the Long-Form Video Understanding Workshop held at CVPR 2022. We designed a Rich Encoder-decoder framework for Video Event CAptioner (REVECA) that utilizes spatial and temporal information from the video to generate a caption for the corresponding the event boundary. REVECA uses frame position embedding to incorporate information before and after the event boundary. Furthermore, it employs features extracted using the temporal segment network and temporal-based pairwise difference method to learn temporal information. A semantic segmentation mask for the attentional pooling process is adopted to learn the subject of an event. Finally, LoRA is applied to fine-tune the image encoder to enhance the learning efficiency. REVECA yielded an average score of 50.97 on the Kinetics-GEBC test data, which is an improvement of 10.17 over the baseline method. Our code is available in https://github.com/TooTouch/REVECA.
DOI:10.48550/arxiv.2206.09178