A Multi-task Neural Approach for Emotion Attribution, Classification and Summarization

TL;DR

This paper introduces BEAC-Net, a neural framework that combines emotion attribution, recognition, and summarization in videos, addressing emotional sparsity and improving analysis accuracy.

Contribution

It presents a novel multi-task neural network with a new dataset for emotion attribution, integrating segmentation and classification for better emotion analysis.

Findings

BEAC-Net outperforms existing methods on two video datasets.

The attribution network effectively identifies key emotional segments.

Dual-stream architecture enhances emotion recognition accuracy.

Abstract

Emotional content is a crucial ingredient in user-generated videos. However, the sparsity of emotional expressions in the videos poses an obstacle to visual emotion analysis. In this paper, we propose a new neural approach, Bi-stream Emotion Attribution-Classification Network (BEAC-Net), to solve three related emotion analysis tasks: emotion recognition, emotion attribution, and emotion-oriented summarization, in a single integrated framework. BEAC-Net has two major constituents, an attribution network and a classification network. The attribution network extracts the main emotional segment that classification should focus on in order to mitigate the sparsity issue. The classification network utilizes both the extracted segment and the original video in a bi-stream architecture. We contribute a new dataset for the emotion attribution task with human-annotated ground-truth labels for emotion segments. Experiments on two video datasets demonstrate superior performance of the proposed framework and the complementary nature of the dual classification streams.