2020/12/20 by Chao Yang, Yang, Chao, Guoqing Wang +10
Computer Science · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Multimedia (cs.MM) #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling #cs.AI #cs.CV #cs.MM
paper · pdf · doi:10.48550/arxiv.2012.10890
arxiv created 2020/12/20 · openalex publication_date 2020/12/20 · arxiv updated 2020/12/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Reference expression comprehension (REC) aims to find the location that the phrase refer to in a given image. Proposal generation and proposal representation are two effective techniques in many two-stage REC methods. However, most of the existing works only focus on proposal representation and neglect the importance of proposal generation. As a result, the low-quality proposals generated by these methods become the performance bottleneck in REC tasks. In this paper, we reconsider the problem of proposal generation, and propose a novel phrase-guided proposal generation network (PPGN). The main implementation principle of PPGN is refining visual features with text and generate proposals through regression. Experiments show that our method is effective and achieve SOTA performance in benchmark datasets.