# The Forgettable-Watcher Model for Video Question Answering

## TL;DR

This paper introduces the Forgettable-Watcher model for video question answering, leveraging re-watching and re-reading mechanisms to better understand temporal video data, and presents a new dataset for evaluation.

## Contribution

The paper proposes a novel Forgettable-Watcher model with re-watching and re-reading mechanisms tailored for video QA, along with a new TGIF-QA dataset generated via automatic question creation.

## Key findings

- The model effectively captures temporal information in videos.
- The proposed dataset enables comprehensive evaluation of video QA models.
- Experimental results demonstrate the model's superior performance.

## Abstract

A number of visual question answering approaches have been proposed recently, aiming at understanding the visual scenes by answering the natural language questions. While the image question answering has drawn significant attention, video question answering is largely unexplored. Video-QA is different from Image-QA since the information and the events are scattered among multiple frames. In order to better utilize the temporal structure of the videos and the phrasal structures of the answers, we propose two mechanisms: the re-watching and the re-reading mechanisms and combine them into the forgettable-watcher model. Then we propose a TGIF-QA dataset for video question answering with the help of automatic question generation. Finally, we evaluate the models on our dataset. The experimental results show the effectiveness of our proposed models.