AICVAug 10, 2021

TrUMAn: Trope Understanding in Movies and Animations

arXiv:2108.04542v36 citations
AI Analysis

This work addresses the challenge of enabling machines to understand storytelling tropes in videos, which could enhance data mining applications, but it is incremental with modest performance gains.

The paper tackles the problem of deep video reasoning beyond visual signals by introducing a new task and dataset, Trope Understanding in Movies and Animations (TrUMAn), and proposes a method that improves accuracy from 12.01% to 13.94% on this dataset.

Understanding and comprehending video content is crucial for many real-world applications such as search and recommendation systems. While recent progress of deep learning has boosted performance on various tasks using visual cues, deep cognition to reason intentions, motivation, or causality remains challenging. Existing datasets that aim to examine video reasoning capability focus on visual signals such as actions, objects, relations, or could be answered utilizing text bias. Observing this, we propose a novel task, along with a new dataset: Trope Understanding in Movies and Animations (TrUMAn), with 2423 videos associated with 132 tropes, intending to evaluate and develop learning systems beyond visual signals. Tropes are frequently used storytelling devices for creative works. By coping with the trope understanding task and enabling the deep cognition skills of machines, data mining applications and algorithms could be taken to the next level. To tackle the challenging TrUMAn dataset, we present a Trope Understanding and Storytelling (TrUSt) with a new Conceptual Storyteller module, which guides the video encoder by performing video storytelling on a latent space. Experimental results demonstrate that state-of-the-art learning systems on existing tasks reach only 12.01% of accuracy with raw input signals. Also, even in the oracle case with human-annotated descriptions, BERT contextual embedding achieves at most 28% of accuracy. Our proposed TrUSt boosts the model performance and reaches 13.94% performance. We also provide detailed analysis to pave the way for future research. TrUMAn is publicly available at:https://www.cmlab.csie.ntu.edu.tw/project/trope

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes