TiFRe: Text-guided Video Frame Reduction for Efficient Video Multi-modal Large Language Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zheng, Xiangtian, Wang, Zishuo, Peng, Yuxin
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911434947952640
author Zheng, Xiangtian
Wang, Zishuo
Peng, Yuxin
author_facet Zheng, Xiangtian
Wang, Zishuo
Peng, Yuxin
contents With the rapid development of Large Language Models (LLMs), Video Multi-Modal Large Language Models (Video MLLMs) have achieved remarkable performance in video-language tasks such as video understanding and question answering. However, Video MLLMs face high computational costs, particularly in processing numerous video frames as input, which leads to significant attention computation overhead. A straightforward approach to reduce computational costs is to decrease the number of input video frames. However, simply selecting key frames at a fixed frame rate (FPS) often overlooks valuable information in non-key frames, resulting in notable performance degradation. To address this, we propose Text-guided Video Frame Reduction (TiFRe), a framework that reduces input frames while preserving essential video information. TiFRe uses a Text-guided Frame Sampling (TFS) strategy to select key frames based on user input, which is processed by an LLM to generate a CLIP-style prompt. Pre-trained CLIP encoders calculate the semantic similarity between the prompt and each frame, selecting the most relevant frames as key frames. To preserve video semantics, TiFRe employs a Frame Matching and Merging (FMM) mechanism, which integrates non-key frame information into the selected key frames, minimizing information loss. Experiments show that TiFRe effectively reduces computational costs while improving performance on video-language tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2602_08861
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TiFRe: Text-guided Video Frame Reduction for Efficient Video Multi-modal Large Language Models
Zheng, Xiangtian
Wang, Zishuo
Peng, Yuxin
Computer Vision and Pattern Recognition
With the rapid development of Large Language Models (LLMs), Video Multi-Modal Large Language Models (Video MLLMs) have achieved remarkable performance in video-language tasks such as video understanding and question answering. However, Video MLLMs face high computational costs, particularly in processing numerous video frames as input, which leads to significant attention computation overhead. A straightforward approach to reduce computational costs is to decrease the number of input video frames. However, simply selecting key frames at a fixed frame rate (FPS) often overlooks valuable information in non-key frames, resulting in notable performance degradation. To address this, we propose Text-guided Video Frame Reduction (TiFRe), a framework that reduces input frames while preserving essential video information. TiFRe uses a Text-guided Frame Sampling (TFS) strategy to select key frames based on user input, which is processed by an LLM to generate a CLIP-style prompt. Pre-trained CLIP encoders calculate the semantic similarity between the prompt and each frame, selecting the most relevant frames as key frames. To preserve video semantics, TiFRe employs a Frame Matching and Merging (FMM) mechanism, which integrates non-key frame information into the selected key frames, minimizing information loss. Experiments show that TiFRe effectively reduces computational costs while improving performance on video-language tasks.
title TiFRe: Text-guided Video Frame Reduction for Efficient Video Multi-modal Large Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.08861