2019/11/24 by Ruicong Xu, Xu, Ruicong, Li Niu +5
Computer Science · #Advanced Image and Video Retrieval Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Human Pose and Action Recognition #Image and Video Processing (eess.IV) #Multimedia (cs.MM) #Multimodal Machine Learning Applications #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1911.10531
openalex publication_date 2019/11/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Activity image-to-video retrieval task aims to retrieve videos containing the similar activity as the query image, which is a challenging task because videos generally have many background segments irrelevant to the activity. In this paper, we utilize R-C3D model to represent a video by a bag of activity proposals, which can filter out background segments to some extent. However, there are still noisy proposals in each bag. Thus, we propose an Activity Proposal-based Image-to-Video Retrieval (APIVR) approach, which incorporates multi-instance learning into cross-modal retrieval framework to address the proposal noise issue. Specifically, we propose a Graph Multi-Instance Learning (GMIL) module with graph convolutional layer, and integrate this module with classification loss, adversarial loss, and triplet loss in our cross-modal retrieval framework. Moreover, we propose geometry-aware triplet loss based on point-to-subspace distance to preserve the structural information of activity proposals. Extensive experiments on three widely-used datasets verify the effectiveness of our approach.