# Advancing Egocentric Video Question Answering with Multimodal Large Language Models

arXiv: https://arxiv.org/abs/2504.04550 · HTML: https://mlsanity.com/paper/2504.04550/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 6 Apr 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 21 of 21)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions](https://mlsanity.com/paper/2105.08276/) (2021)
- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding](https://mlsanity.com/paper/2407.15754/) (2024)
- [ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering](https://mlsanity.com/paper/1906.02467/) (2019)
- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering](https://mlsanity.com/paper/1704.04497/) (2017)
- [LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment](https://mlsanity.com/paper/2310.01852/) (2023)
- [HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training](https://mlsanity.com/paper/2005.00200/) (2020)
- [PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning](https://mlsanity.com/paper/2404.16994/) (2024)
- [EgoTaskQA: Understanding Human Tasks in Egocentric Videos](https://mlsanity.com/paper/2210.03929/) (2022)
- [Grounded Question-Answering in Long Egocentric Videos](https://mlsanity.com/paper/2312.06505/) (2023)
- [EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models](https://mlsanity.com/paper/2311.15596/) (2023)
- [From Representation to Reasoning: Towards both Evidence and Commonsense Reasoning for Video Question-Answering](https://mlsanity.com/paper/2205.14895/) (2022)
- [MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA](https://mlsanity.com/paper/2410.07177/) (2024)

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

- [Object Detection with Multimodal Large Vision-Language Models: An In-depth Review](https://mlsanity.com/paper/2508.19294/) (2025)
- [PhysBrain: Human Egocentric Data as a Bridge from Vision Language Models to Physical Intelligence](https://mlsanity.com/paper/2512.16793/) (2025)
- [EASG-Bench: Video Q&A Benchmark with Egocentric Action Scene Graphs](https://mlsanity.com/paper/2506.05787/) (2025)
- [How Far Can Off-the-Shelf Multimodal Large Language Models Go in Online Episodic Memory Question Answering?](https://mlsanity.com/paper/2506.16450/) (2025)
- [Do You See What I Am Pointing At? Gesture-Based Egocentric Video Question Answering](https://mlsanity.com/paper/2603.12533/) (2026)
- [Decoding Pedestrian Crossing Intention from Egocentric Vision via Vision Language Models](https://mlsanity.com/paper/2606.09142/) (2026)
- [Rethinking RAG in Long Videos: What to Retrieve and How to Use It?](https://mlsanity.com/paper/2606.13141/) (2026)
- [Graph it first! Enabling Reasoning on Long-form Egocentric Videos through Scene Graphs](https://mlsanity.com/paper/2606.25842/) (2026)

## Abstract (arXiv)

Egocentric Video Question Answering (QA) requires models to handle long-horizon temporal reasoning, first-person perspectives, and specialized challenges like frequent camera movement. This paper systematically evaluates both proprietary and open-source Multimodal Large Language Models (MLLMs) on QaEgo4Dv2 - a refined dataset of egocentric videos derived from QaEgo4D. Four popular MLLMs (GPT-4o, Gemini-1.5-Pro, Video-LLaVa-7B and Qwen2-VL-7B-Instruct) are assessed using zero-shot and fine-tuned approaches for both OpenQA and CloseQA settings. We introduce QaEgo4Dv2 to mitigate annotation noise in QaEgo4D, enabling more reliable comparison. Our results show that fine-tuned Video-LLaVa-7B and Qwen2-VL-7B-Instruct achieve new state-of-the-art performance, surpassing previous benchmarks by up to +2.6% ROUGE/METEOR (for OpenQA) and +13% accuracy (for CloseQA). We also present a thorough error analysis, indicating the model's difficulty in spatial reasoning and fine-grained object recognition - key areas for future improvement.