Multilevel Language And Vision Integration For Text-to-clip Retrieval

Abstract

We address the problem of text-based activity retrieval in video. Given a sentence describing an activity, our task is to retrieve matching clips from an untrimmed video. To capture the inherent structures present in both text and video, we introduce a multilevel model that integrates vision and language features earlier and more tightly than prior work. First, we inject text features early on when generating clip proposals, to help eliminate unlikely clips and thus speed up processing and boost performance. Second, to learn a fine-grained similarity metric for retrieval, we use visual features to modulate the processing of query sentences at the word level in a recurrent neural network. A multi-task loss is also employed by adding query re-generation as an auxiliary task. Our approach significantly outperforms prior work on two challenging benchmarks: Charades-STA and ActivityNet Captions.

Stats

• citations226
• S2 citations—
• github stars0
• HF likes0
• heat score17.67
• arxiv keyxu2018multilevel

Related papers

• Clip2video: Mastering Video-text Retrieval Via Image CLIP (2021)0.00
• Delving Deeper: Hierarchical Visual Perception For Robust Video-text Retrieval (2026)1.24
• CLIP2TV: Align, Match And Distill For Video-text Retrieval (2021)0.00
• Lightclip: Learning Multi-level Interaction For Lightweight Vision-language Models (2023)0.00
• Tencent Text-video Retrieval: Hierarchical Cross-modal Interactions With Multi-level Representations (2022)7.81
• Improving Video-text Retrieval By Multi-stream Corpus Alignment And Dual Softmax Loss (2021)0.00
• HVD: Human Vision-driven Video Representation Learning For Text-video Retrieval (2026)0.00
• Tagging Before Alignment: Integrating Multi-modal Tags For Video-text Retrieval (2023)10.74