Video Corpus Moment Retrieval With Contrastive Learning

Abstract

Given a collection of untrimmed and unsegmented videos, video corpus moment retrieval (VCMR) is to retrieve a temporal moment (i.e., a fraction of a video) that semantically corresponds to a given text query. As video and text are from two distinct feature spaces, there are two general approaches to address VCMR: (i) to separately encode each modality representations, then align the two modality representations for query processing, and (ii) to adopt fine-grained cross-modal interaction to learn multi-modal representations for query processing. While the second approach often leads to better retrieval accuracy, the first approach is far more efficient. In this paper, we propose a Retrieval and Localization Network with Contrastive Learning (ReLoCLNet) for VCMR. We adopt the first approach and introduce two contrastive learning objectives to refine video encoder and text encoder to learn video and text representations separately but with better alignment for VCMR. The video contrastive

Stats

• citations81
• S2 citations—
• github stars0
• HF likes0
• heat score14.35
• arxiv keyzhang2021video

Related papers

• Improving Video Corpus Moment Retrieval With Partial Relevance Enhancement (2024)7.89
• Coarse To Fine: Video Retrieval Before Moment Localization (2021)0.00
• Vlanet: Video-language Alignment Network For Weakly-supervised Video Moment Retrieval (2020)13.28
• Normalized Contrastive Learning For Text-video Retrieval (2022)6.77
• Improving Video-text Retrieval By Multi-stream Corpus Alignment And Dual Softmax Loss (2021)0.00
• X-CLIP: End-to-end Multi-grained Contrastive Learning For Video-text Retrieval (2022)18.12
• TC-MGC: Text-conditioned Multi-grained Contrastive Learning For Text-video Retrieval (2025)6.93
• Hybrid-learning Video Moment Retrieval Across Multi-domain Labels (2024)0.00