default author photo

Zhiqing Luo

Chongqing University

Shazheng Str 174, Shapingba District

Shazheng street, Shapingba district

Chongqing 400044, 400030

China

  • Chongqing University

SCHOLARLY PAPERS

1

DOWNLOADS

54

TOTAL CITATIONS

0

Scholarly Papers (1)

Actions:
Email selected abstracts
1.

DualFocus: A Framework for Efficient Decoupling of Visual Representation and Focus Fusion in Video LLM

Number of pages: 16 Posted: 04 Dec 2025
Mingyu Sun, Hongwei Zhou, Zhiqing Luo, Xing Li, Jinhao Zhu, Tianwei Yan and Zhibo Rao
Nanchang Hangkong University, Nanchang Hangkong University, Chongqing University, Northwestern Polytechnic University (NPU), affiliation not provided to SSRN, National University of Defense Technology and Nanchang Hangkong University
Downloads 54 (1,031,043)

Abstract:

Loading...

Multimodal Large Language ModelVisual Question AnsweringVideo Question AnsweringVision Language ModelVideo Large Language Model