Heterogeneous Knowledge Transfer in Video Emotion Recognition, Attribution and Summarization

TL;DR

This paper introduces a novel framework for transferring knowledge from images and text to improve video emotion recognition, attribution, and summarization, addressing challenges posed by unstructured user-generated videos.

Contribution

It is the first to transfer knowledge from heterogeneous sources like images and text to enhance multiple aspects of video emotion understanding.

Findings

Knowledge transfer improves emotion recognition accuracy.

Zero-shot recognition enables identifying unseen emotion classes.

Framework effectively supports emotion attribution and summarization.

Abstract

Emotion is a key element in user-generated videos. However, it is difficult to understand emotions conveyed in such videos due to the complex and unstructured nature of user-generated content and the sparsity of video frames expressing emotion. In this paper, for the first time, we study the problem of transferring knowledge from heterogeneous external sources, including image and textual data, to facilitate three related tasks in understanding video emotion: emotion recognition, emotion attribution and emotion-oriented summarization. Specifically, our framework (1) learns a video encoding from an auxiliary emotional image dataset in order to improve supervised video emotion recognition, and (2) transfers knowledge from an auxiliary textual corpora for zero-shot recognition of emotion classes unseen during training. The proposed technique for knowledge transfer facilitates novel applications of emotion attribution and emotion-oriented summarization. A comprehensive set of experiments on multiple datasets demonstrate the effectiveness of our framework.