CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not

Author:

Sain Aneeshan1,Bhunia Ayan Kumar1,Chowdhury Pinaki Nath1,Koley Subhadeep1,Xiang Tao1,Song Yi-Zhe1

Affiliation:

1. University of Surrey,SketchX, CVSSP,United Kingdom

Publisher

IEEE

Reference75 articles.

1. What Can Human Sketches Do for Object Detection?

2. Very deep convolutional networks for large-scale image recognition;simonyan;ICLRE,2015

3. SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text

4. Information radius;sibson;Probability Theory and Related Fields,1969

5. Bert: Pre-training of deep bidirectional transformers for language understanding;devlin;NAACL,2019

Cited by 23 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Text-guided image-to-sketch diffusion models;Knowledge-Based Systems;2024-11

2. Multi-colour sketch-based image retrieval with an explicable feature embedding;Engineering Applications of Artificial Intelligence;2024-09

3. Triplane-Smoothed Video Dehazing with CLIP-Enhanced Generalization;International Journal of Computer Vision;2024-08-01

4. Fault Diagnosis of Transmission Lines Based on Sketch Retrieval for Small Targets and Small Samples;IEEE Transactions on Industrial Informatics;2024-07

5. RSG-Search Plus:An Advanced Traffic Scene Retrieval Methods based on Road Scene Graph;2024 IEEE Intelligent Vehicles Symposium (IV);2024-06-02

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3