The paper introduces DAN, a training‑free inference‑time framework that improves affective reasoning in multimodal large language models. It combines a Hierarchical Emotional Reasoning Chain (HERC) to better capture fine‑grained visual cues and a Contrastive Discriminative Visual Pruning (CDVP) module to isolate discriminative tokens for semantically similar emotions. Experiments show significant gains, notably a +10.47% improvement on the WebEmo25 benchmark with Qwen3‑VL‑8B‑Instruct.
By Cheng Ye, Weidong Chen, Zhaobo Qi, Beier Zhu, Zhendong Mao
arXiv:2609.36563v1 Announce Type: new
Abstract: Visual emotion recognition commonly assumes that all evidence required for prediction is contained in the observed image or video. Yet the same visible...
By Yihao Qian, Runhao Zeng, Sicheng Zhao, Feng Liang, Hongmin Cai, Mingkui Tan
The paper introduces a steering‑vector‑based causal attribution framework to study how large vision‑language models (LVLMs) translate visual input into emotional narratives. By creating a specialized dataset, the authors uncover a functional decoupling in the LVLM’s three‑stage Adapt‑Aggregate‑Execute mechanism: visual emotional cues are first aggregated in middle layers via sentiment‑specific attention heads, then translated into narrative generation in deeper layers through emotion‑general pathways. Using these insights, they regulate emotional information routing to strengthen attention flow and amplify semantic activation, achieving significant performance gains on the MER‑UniBench and reducing emotional hallucinations through inference‑time intervention.
By Chengsheng Zhang, Chenghao Sun, Zhining Xie, Xinmei Tian
In this paper, we present the solution developed by our team, XInsight Lab, which achieved first place in Track 3 of the 4th EI-MIGA-IJCAI Challenge with a test accuracy of 0. 76923.
arXiv:2609.36776v1 Announce Type: new
Abstract: Emotional Video Captioning aims to generate factually accurate and emotionally empathetic descriptions. While recent methods have recognized the import...
By Cheng Ye, Weidong Chen, Peipei Song, Zhendong Mao
Affective Image Content Analysis (AICA) aims to recognize and understand emotions elicited by visual content, representing an indispensable step toward Artificial General Intelligence (AGI). However, despite the rapid progress of Multimodal Large Language Models (MLLMs), systematic evaluation of their visual emotional intelligence remains largely absent from recent model releases.
arXiv:2608. 10448v1 Announce Type: new Abstract: Multimodal emotion recognition in conversation (MERC) requires understanding complex interactions between verbal and non-verbal cues.
By Sujung Oh, Jung Uk Kim, Sangmin Lee
Video2Reaction is a multimodal dataset that links short movie segments to the emotional reactions of viewers, gathered from social media comments. The dataset models reactions as distributions over categorical emotions, capturing the subjective and ambiguous nature of emotional perception. Experiments show that vision‑language models fine‑tuned with LoRA learn effectively from Video2Reaction and outperform specialized baselines, and that models pre‑fine‑tuned on this dataset transfer well to other emotion prediction tasks.
By Sidong Zhang, Trang Nguyen, Shiv Shankar, Gauri Jagatap, Deepak Chandran, Andrea Fanelli, Madalina Fiterau
arXiv:2606. 02522v1 Announce Type: cross Abstract: Video multimodal large language models (MLLMs) have made rapid progress on general and long-form video understanding, yet their ability to preserve brief answer-critical visual evidence remains underexplored.
By Xiaolin Liu, Yilun Zhu, Xiangyu Zhao, Xuehui Wang, Yan Li, Xin Li, Haoyu Cao, Xing Sun, Shaofeng Zhang, Xu Yang, Zhihang Zhong, Xue Yang
arXiv:2607. 12774v1 Announce Type: cross Abstract: This article presents our results for the 11th Affective Behavior Analysis in-the-Wild (ABAW) competition.
By Aleksei Bakin, Andrey V. Savchenko
HUG‑VIS is a unified multimodal benchmark for human‑centered visual intelligence, comprising 8,400 half‑body videos of 30 professional actors performing 280 emotion‑action prompts in Mandarin. The dataset provides synchronized video, audio, text, and alpha mattes for four tasks—human emotion recognition, video generation, voice cloning, and video matting—allowing evaluation of both open‑ and closed‑source models under a zero‑shot protocol. Results reveal that linguistic cues dominate emotion recognition, visual affect is weakest, and that automatic metrics and human judgments diverge in generation and cloning tasks, while motion‑related boundary fidelity remains a key challenge for matting.
By Fei Ma, Zebang Cheng, Minghui Li, Hongbo Xu, Yuyong Tan, Yihua Shao, Hanling Wang, Zhou Liu, Yuqing Gao, Dong Wang, Long Ma, Laizhong Cui, Nicu Sebe, Qi Tian
arXiv:2608. 08873v1 Announce Type: cross Abstract: Facial Emotion Recognition (FER) is an important task that has significant implications across various fields such as biometrics, health, and human-computer interaction.
By Aya Manel Zitouni, Aicha Zenakhri, Karim Haroun, Larbi Boubchir