Comprehensive Visual Features and Pseudo Labeling for Robust Natural Language-based Vehicle Retrieval

Author:

Ngo Bach Hoang1,Nguyen Dat Thanh2,Do-Tran Nhat-Tuong1,Huy Thien Phuc Pham3,An Minh-Hung2,Nguyen Tuan-Ngoc1,Hoang Loi Nguyen1,Dinh Nguyen Vinh4,Dinh Quang-Vinh1

Affiliation:

1. AI Vietnam Research,Vietnam

2. FPT Telecom,Vietnam

3. Ho Chi Minh City University of Technology,Faculty of Computer Science and Engineering

4. Eastern International University,School of Computing and Information Technology,Vietnam

Publisher

IEEE

Reference26 articles.

1. Sparse spatio-temporal representation with adaptive regularized dictionaries for super-resolution based video coding;pan;2012 Data Compression Conference,2012

2. Representation learning with contrastive predictive coding;van den oord,2018

3. Learning transferable visual models from natural language supervision;radford;Machine Learning Research,2021

4. Cityflow-nl: Tracking and retrieval of vehicles at city scale by natural language descriptions;feng,2021

5. Learning Framework for Robust Obstacle Detection, Recognition, and Tracking

Cited by 1 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. The 7th AI City Challenge;2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW);2023-06

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