Skip to content

LongEmo: Towards Emotion Understanding and Reasoning in Long Videos

Sep 2026 · arXiv.org · Vol abs/2609.40079 · 0 citations · 34 references
Computer Science

TL;DR

This work proposes LongEmo, a novel memory-augmented agentic framework designed to tackle the immense challenges of long-range affective reasoning, and achieves state-of-the-art performance, demonstrating the efficacy of its event-centric memory architecture.

Abstract

While recent Multimodal Large Language Models (MLLMs) have shown promise in affective computing, their reasoning capabilities are largely confined to short video clips with limited interactions. However, real-world emotions are not merely isolated instantaneous reactions but dynamic and cumulative processes deeply shaped by past experiences and ongoing events. To bridge this gap, we introduce LongEmoBench, a benchmark dedicated to emotion understanding and reasoning in long videos. It assesses progressive capabilities scaling from continuous scene interactions to complex episodic developments. Furthermore, we propose LongEmo, a novel memory-augmented agentic framework designed to tackle the immense challenges of long-range affective reasoning. LongEmo processes continuous video streams to construct an Event Memory Graph, explicitly modeling long-range dependencies and capturing emotional dynamics across discrete events. Given a question, the agent retrieves a query-relevant event stream from the graph, iteratively integrating multimodal memories and relational dependencies to deduce the final answer. Extensive evaluations of 17 representative methods reveal that they struggle significantly with emotion understanding and reasoning in long videos. In contrast, LongEmo achieves state-of-the-art performance, demonstrating the efficacy of its event-centric memory architecture.

View source

Similar papers

Book Open access Nov 2026

Towards Human-like Empathy: Confidence-Driven Fast-Slow Reasoning for Multimodal Empathetic Response Generation

Multimodal Empathetic Response Generation (MERG) integrates textual, visual, and acoustic signals to synthesize nuanced affective responses. While Large Language Models (LLMs) demonstrate strong capabilities in emotional reasoning, they still suffer from reasoning redundancy and contextual prolixity. Applying static, h...

Xinzehua Li, Cheng-Ji Wang, Wang-Da Zhu et al. · 1 citation
#artificial intelligence Preprint Oct 2026

Cognition-Oriented Emotion Tracing from Causes to Consequences in Real-World Social Scenes

Affective computing has progressed from categorical emotion recognition to open-ended affective analysis with large multimodal models. Yet affective science describes emotion as an unfolding process shaped by appraisal, regulation, and social interpretation, which remains underexplored computationally. We propose TRACE...

Hao Li, Jin-Ye Zhang, Bobo Li et al. · 0 citations
#artificial intelligence Preprint Oct 2026

From Surface to Depth: Towards Cognitive Appraisal Reasoning in Multimodal Emotion Understanding

Recent multimodal large language models (MLLMs) increasingly incorporate explainable reasoning for emotion understanding. However, reasoning based mainly on observable affective cues can reduce emotion understanding to superficial cue-label associations, giving rise to the Clever Hans effect. Such shortcuts become unre...

Jia Li, Yi-Chao He, Yang-Chen Yu et al. · 0 citations
Book Open access Nov 2026

Beyond Surface Cues: Multimodal Implicit Emotion Understanding with a New Dataset, Reasoning Framework, and Benchmark

Implicit emotion understanding addresses a fundamental yet underexplored challenge: observable expressions do not always faithfully reflect underlying emotional states, requiring models to infer latent emotions from limited multimodal signals. Existing approaches largely assume direct correspondence between overt cues...

Ke-Han Wang, Huan Zhao, Guang-Hui Ye et al. · 0 citations
Book Open access Nov 2026

MEIR: Memory-Enhanced Incongruity-Aware Reasoning for Multimodal Sarcasm Detection and Explanation

Memory-Enhanced Incongruity Reasoner (MEIR), a novel framework for multimodal sarcasm detection and explanation, is proposed, which is the first unified framework to jointly perform multimodal sarcasm detection and natural language explanation generation.

Guo-Jian Li, Fei Ma, Hong-Bo Xu et al. · 0 citations
#natural language process... Conference Open access Oct 2026

Emotion Is Not External Knowledge: Internal Attention Signals for Affective State Reasoning

Large Language Models (LLMs) increasingly operate in multi-turn interactions that require maintaining latent conversational states, not only explicit facts. We study affective state as an implicit state inferred from sparse contextual cues that remain relevant after topic shifts, and ask whether LLMs expose internal at...

Wen Tang, Zhen Wan, Yi Wang et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.