DREAM: Improving Video-text Retrieval Through Relevance-based Augmentation Using Large Foundation Models

Abstract

Recent progress in video-text retrieval has been driven largely by advancements in model architectures and training strategies. However, the representation learning capabilities of videotext retrieval models remain constrained by lowquality and limited training data annotations. To address this issue, we present a novel ViDeoText Retrieval Paradigm with RElevance-based AugMentation, namely DREAM, which enhances video and text data using large foundation models to learn more generalized features. Specifically, we first adopt a simple augmentation method, which generates self-similar data by randomly duplicating or dropping subwords and frames. In addition, inspired by the recent advancement in visual and language generative models, we propose a more robust augmentation method through textual paraphrasing and video stylization using large language models (LLMs) and visual generative models (VGMs). To further enrich video and text information, we propose a relevance-based augmentation met

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keywang2024dream

Related papers

• A Little More Like This: Text-to-image Retrieval With Vision-language Models Using Relevance Feedback (2025)0.00
• Vidvec: Unlocking Video MLLM Embeddings For Video-text Retrieval (2026)0.00
• A Feature-space Multimodal Data Augmentation Technique For Text-video Retrieval (2022)12.43
• Self-enhancement Improves Text-image Retrieval In Foundation Visual-language Models (2023)1.56
• Narrating The Video: Boosting Text-video Retrieval Via Comprehensive Utilization Of Frame-level Captions (2025)6.77
• Feature Re-learning With Data Augmentation For Video Relevance Prediction (2020)6.34
• Distilling Vision-language Models On Millions Of Videos (2024)7.50
• RAVEN: Multitask Retrieval Augmented Vision-language Learning (2024)0.00