Prompt-aware of Frame Sampling for Efficient Text-Video Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Deyu, Long, Tingting, Zhang, Jinrui, Chen, Ligeng, Ren, Ju, Zhang, Yaoxue
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916853785296896
author Zhang, Deyu
Long, Tingting
Zhang, Jinrui
Chen, Ligeng
Ren, Ju
Zhang, Yaoxue
author_facet Zhang, Deyu
Long, Tingting
Zhang, Jinrui
Chen, Ligeng
Ren, Ju
Zhang, Yaoxue
contents Enabling efficient text-video retrieval on edge-end devices is critical for real-world applications. Yet, existing methods face a critical challenge in balancing accuracy and computational efficiency: uniform frame sampling methods ensure content coverage but incur prohibitive computational costs, while salient-frame sampling methods reduce overhead but suffer from query-agnostic frame selection that biases retrieval results. To address this, we propose ProCLIP, a user-centric framework that achieves state-of-the-art accuracy with significantly improved efficiency. We design a prompt-aware frame sampling strategy that dynamically guides lightweight feature extractors using textual prompts to select semantically relevant frames, overcoming the limitations of existing salient-frame sampling methods which rely on static, query-agnostic selection criteria. Moreover, we adopt a two-stage candidate pruning strategy that combines rapid coarse filtering via a lightweight module with CLIP-powered fine-grained re-ranking, enhancing retrieval efficiency while preserving accuracy. Experiments across benchmarks show ProCLIP achieves 75.3% latency reduction versus baselines while maintaining competitive accuracy, i.e., R@1=49.0 in MSR-VTT dataset. Code is available at https://github.com/tiffylong/ProCLIP.
format Preprint
id arxiv_https___arxiv_org_abs_2507_15491
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Prompt-aware of Frame Sampling for Efficient Text-Video Retrieval
Zhang, Deyu
Long, Tingting
Zhang, Jinrui
Chen, Ligeng
Ren, Ju
Zhang, Yaoxue
Multimedia
Computer Vision and Pattern Recognition
Enabling efficient text-video retrieval on edge-end devices is critical for real-world applications. Yet, existing methods face a critical challenge in balancing accuracy and computational efficiency: uniform frame sampling methods ensure content coverage but incur prohibitive computational costs, while salient-frame sampling methods reduce overhead but suffer from query-agnostic frame selection that biases retrieval results. To address this, we propose ProCLIP, a user-centric framework that achieves state-of-the-art accuracy with significantly improved efficiency. We design a prompt-aware frame sampling strategy that dynamically guides lightweight feature extractors using textual prompts to select semantically relevant frames, overcoming the limitations of existing salient-frame sampling methods which rely on static, query-agnostic selection criteria. Moreover, we adopt a two-stage candidate pruning strategy that combines rapid coarse filtering via a lightweight module with CLIP-powered fine-grained re-ranking, enhancing retrieval efficiency while preserving accuracy. Experiments across benchmarks show ProCLIP achieves 75.3% latency reduction versus baselines while maintaining competitive accuracy, i.e., R@1=49.0 in MSR-VTT dataset. Code is available at https://github.com/tiffylong/ProCLIP.
title Prompt-aware of Frame Sampling for Efficient Text-Video Retrieval
topic Multimedia
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.15491