Delving Deeper: Hierarchical Visual Perception For Robust Video-text Retrieval

Abstract

Video-text retrieval (VTR) aims to locate relevant videos using natural language queries. Current methods, often based on pre-trained models like CLIP, are hindered by video's inherent redundancy and their reliance on coarse, final-layer features, limiting matching accuracy. To address this, we introduce the HVP-Net (Hierarchical Visual Perception Network), a framework that mines richer video semantics by extracting and refining features from multiple intermediate layers of a vision encoder. Our approach progressively distills salient visual concepts from raw patch-tokens at different semantic levels, mitigating redundancy while preserving crucial details for alignment. This results in a more robust video representation, leading to new state-of-the-art performance on challenging benchmarks including MSRVTT, DiDeMo, and ActivityNet. Our work validates the effectiveness of exploiting hierarchical features for advancing video-text retrieval. Our codes are available at https://github.com/b

Stats

• citations0
• S2 citations—
• github stars2
• HF likes0
• heat score1.24
• arxiv keyxie2026delving

Related papers

• HVD: Human Vision-driven Video Representation Learning For Text-video Retrieval (2026)0.00
• Boosting Video-text Retrieval With Explicit High-level Semantics (2022)7.50
• Hanet: Hierarchical Alignment Networks For Video-text Retrieval (2021)0.00
• Fine-grained Video-text Retrieval With Hierarchical Graph Reasoning (2020)18.27
• Tencent Text-video Retrieval: Hierarchical Cross-modal Interactions With Multi-level Representations (2022)7.81
• UATVR: Uncertainty-adaptive Text-video Retrieval (2023)15.46
• Hivlp: Hierarchical Vision-language Pre-training For Fast Image-text Retrieval (2022)0.00
• Multilevel Language And Vision Integration For Text-to-clip Retrieval (2018)17.67