# StimuVAR: Spatiotemporal Stimuli-aware Video Affective Reasoning with Multimodal Large Language Models

arXiv: https://arxiv.org/abs/2409.00304 · HTML: https://mlsanity.com/paper/2409.00304/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 51 of its 78 references that are in the map.
- First posted on arXiv 31 Aug 2024.

## Placed in

- LLM reasoning / [Audio-language model reasoning](https://mlsanity.com/lr/audio-language-model-reasoning/)
- Multimodal LLMs / vision-language models / [Multimodal emotion understanding](https://mlsanity.com/mllm/multimodal-emotion-understanding/)

## Builds on (most cited first, 30 of 51)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)
- [LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding](https://mlsanity.com/paper/2407.15754/) (2024)
- [mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration](https://mlsanity.com/paper/2311.04257/) (2023)
- [Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding](https://mlsanity.com/paper/2311.08046/) (2023)
- [Valley: Video Assistant with Large Language model Enhanced abilitY](https://mlsanity.com/paper/2306.07207/) (2023)
- [Revisiting the "Video" in Video-Language Understanding](https://mlsanity.com/paper/2206.01720/) (2022)
- [LongVLM: Efficient Long Video Understanding via Large Language Models](https://mlsanity.com/paper/2404.03384/) (2024)
- [AdaFrame: Adaptive Frame Selection for Fast Video Recognition](https://mlsanity.com/paper/1811.12432/) (2018)

## Built on by (most cited first, 8 of 8)

- [Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models](https://mlsanity.com/paper/2502.07601/) (2025)
- [Emotion-LLaMAv2 and MMEVerse: A New Framework and Benchmark for Multimodal Emotion Understanding](https://mlsanity.com/paper/2601.16449/) (2026)
- [Chart-to-Experience: Benchmarking Multimodal LLMs for Predicting Experiential Impact of Charts](https://mlsanity.com/paper/2505.17374/) (2025)
- [FocusGraph: Graph-Structured Frame Selection for Embodied Long Video Question Answering](https://mlsanity.com/paper/2603.04349/) (2026)
- [Chain-of-Glimpse: Search-Guided Progressive Object-Grounded Reasoning for Video Understanding](https://mlsanity.com/paper/2604.14692/) (2026)
- [Benchmarking Dynamic Affective Reasoning: A Viewer-Centric Video Emotion Dataset](https://mlsanity.com/paper/2607.10238/) (2026)
- [Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation](https://mlsanity.com/paper/2505.18168/) (2025)
- [Modeling Induced Pleasure through Cognitive Appraisal Prediction via Multimodal Fusion](https://mlsanity.com/paper/2604.23753/) (2026)

## Abstract (arXiv)

Predicting and reasoning how a video would make a human feel is crucial for developing socially intelligent systems. Although Multimodal Large Language Models (MLLMs) have shown impressive video understanding capabilities, they tend to focus more on the semantic content of videos, often overlooking emotional stimuli. Hence, most existing MLLMs fall short in estimating viewers' emotional reactions and providing plausible explanations. To address this issue, we propose StimuVAR, a spatiotemporal Stimuli-aware framework for Video Affective Reasoning (VAR) with MLLMs. StimuVAR incorporates a two-level stimuli-aware mechanism: frame-level awareness and token-level awareness. Frame-level awareness involves sampling video frames with events that are most likely to evoke viewers' emotions. Token-level awareness performs tube selection in the token space to make the MLLM concentrate on emotion-triggered spatiotemporal regions. Furthermore, we create VAR instruction data to perform affective training, steering MLLMs' reasoning strengths towards emotional focus and thereby enhancing their affective reasoning ability. To thoroughly assess the effectiveness of VAR, we provide a comprehensive evaluation protocol with extensive metrics. StimuVAR is the first MLLM-based method for viewer-centered VAR. Experiments demonstrate its superiority in understanding viewers' emotional responses to videos and providing coherent and insightful explanations. Our code is available at https://github.com/EthanG97/StimuVAR