Papers
arxiv:2601.10228

Optimizing Multimodal LLMs for Egocentric Video Understanding: A Solution for the HD-EPIC VQA Challenge

Published on Jan 15
Authors:
,
,
,
,
,
,

Abstract

A multimodal framework combining query preprocessing, domain-specific fine-tuning, temporal chain-of-thought prompting, and post-processing achieves improved video question answering performance on challenging benchmarks.

Multimodal Large Language Models (MLLMs) struggle with complex video QA benchmarks like HD-EPIC VQA due to ambiguous queries/options, poor long-range temporal reasoning, and non-standardized outputs. We propose a framework integrating query/choice pre-processing, domain-specific Qwen2.5-VL fine-tuning, a novel Temporal Chain-of-Thought (T-CoT) prompting for multi-step reasoning, and robust post-processing. This system achieves 41.6% accuracy on HD-EPIC VQA, highlighting the need for holistic pipeline optimization in demanding video understanding. Our code, fine-tuned models are available at https://github.com/YoungSeng/Egocentric-Co-Pilot.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2601.10228
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2601.10228 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2601.10228 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.