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

TL;DR

REVECA is a novel framework for video event captioning that effectively integrates spatial, temporal, and semantic information to generate accurate event descriptions, demonstrating significant performance improvements in the CVPR 2022 challenge.

Contribution

It introduces a comprehensive encoder-decoder architecture with frame position embedding, temporal features, semantic segmentation, and LoRA fine-tuning, advancing video captioning methods.

Findings

Achieved an average score of 50.97 on Kinetics-GEBC test data.

Improved performance by 10.17 points over baseline.

Effectively incorporates spatial, temporal, and semantic cues for captioning.

Abstract

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.