咨询与建议

限定检索结果

文献类型

  • 3 篇 会议
  • 1 篇 期刊文献

馆藏范围

  • 4 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 4 篇 工学
    • 3 篇 电气工程
    • 3 篇 计算机科学与技术...
    • 1 篇 软件工程
  • 1 篇 医学
    • 1 篇 临床医学

主题

  • 4 篇 visual feature l...
  • 1 篇 deep semi-superv...
  • 1 篇 bag of n-grams
  • 1 篇 deep neural netw...
  • 1 篇 domain adaptatio...
  • 1 篇 audio-visual spe...
  • 1 篇 biocellular imag...
  • 1 篇 image retrieval
  • 1 篇 cnn
  • 1 篇 visual classific...
  • 1 篇 incremental proc...
  • 1 篇 mac
  • 1 篇 semi supervised
  • 1 篇 cost-effective m...
  • 1 篇 explainable ai

机构

  • 1 篇 univ chinese aca...
  • 1 篇 hong kong polyte...
  • 1 篇 univ jean monnet...
  • 1 篇 minist educ engn...
  • 1 篇 chinese univ hon...
  • 1 篇 anhui univ sch c...
  • 1 篇 beijing univ pos...
  • 1 篇 sun yat sen univ...
  • 1 篇 queen mary univ ...
  • 1 篇 tencent youtu la...
  • 1 篇 univ jean monnet...
  • 1 篇 chinese acad sci...
  • 1 篇 meituan dianping...

作者

  • 1 篇 wang lan
  • 1 篇 li ruifan
  • 1 篇 niu tianrui
  • 1 篇 ducottet christo...
  • 1 篇 peng pai
  • 1 篇 wang xiao
  • 1 篇 wang keze
  • 1 篇 liu xunying
  • 1 篇 feng fangxiang
  • 1 篇 jiang huixing
  • 1 篇 wang xiaojie
  • 1 篇 lin liang
  • 1 篇 izquierdo ebroul
  • 1 篇 muselet damien
  • 1 篇 su rongfeng
  • 1 篇 chen ziliang
  • 1 篇 blanchard martin
  • 1 篇 delezay olivier

语言

  • 4 篇 英文
检索条件"主题词=Visual Feature Learning"
4 条 记 录,以下是1-10 订阅
排序:
Semi-supervised Cross-domain visual feature learning for Audio-visual Broadcast Speech Transcription  19
Semi-supervised Cross-domain Visual Feature Learning for Aud...
收藏 引用
19th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2018)
作者: Su, Rongfeng Liu, Xunying Wang, Lan Chinese Acad Sci Shenzhen Inst Adv Technol CAS Key Lab Human Machine Intelligence Synergy Sy Beijing Peoples R China Univ Chinese Acad Sci Shenzhen Coll Adv Technol Beijing Peoples R China Chinese Univ Hong Kong Hong Kong Peoples R China
visual information can be incorporated into automatic speech recognition (ASR) systems to improve their robustness in adverse acoustic conditions. Conventional audio-visual speech recognition (AVSR) systems require hi... 详细信息
来源: 评论
DELVING INTO THE EXPLAINABILITY OF PROTOTYPE-BASED CNN FOR BIOLOGICAL CELL ANALYSIS  31
DELVING INTO THE EXPLAINABILITY OF PROTOTYPE-BASED CNN FOR B...
收藏 引用
2024 International Conference on Image Processing
作者: Blanchard, Martin Delezay, Olivier Ducottet, Christophe Muselet, Damien Univ Jean Monnet St Etienne CNRS Inst Optique Grad Sch Lab Hubert CurienUMR 5516 St Etienne France Univ Jean Monnet Lab Sainboise INSERM UMR 1059 St Etienne France
Deep learning for automated cell imaging analysis has become a tool of choice to process large amounts of data. But many of these methods lack explainability, slowing down their deployment for tasks such as diagnosis.... 详细信息
来源: 评论
learning visual features from Product Title for Image Retrieval  20
Learning Visual Features from Product Title for Image Retrie...
收藏 引用
28th ACM International Conference on Multimedia (MM)
作者: Feng, Fangxiang Niu, Tianrui Li, Ruifan Wang, Xiaojie Jiang, Huixing Beijing Univ Posts & Telecommun Sch Artificial Intelligence Beijing Peoples R China Meituan Dianping Grp Beijing Peoples R China
There is a huge market demand for searching for products by images in e-commerce sites. visual features play the most important role in solving this content-based image retrieval task. Most existing methods leverage p... 详细信息
来源: 评论
Deep Co-Space: Sample Mining Across feature Transformation for Semi-Supervised learning
收藏 引用
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2018年 第10期28卷 2667-2678页
作者: Chen, Ziliang Wang, Keze Wang, Xiao Peng, Pai Izquierdo, Ebroul Lin, Liang Sun Yat Sen Univ Sch Data & Comp Sci Guangzhou 510006 Guangdong Peoples R China Minist Educ Engn Res Ctr Adv Comp Engn Software Guangzhou 510006 Guangdong Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong Hong Kong Peoples R China Anhui Univ Sch Comp Sci Hefei 100044 Anhui Peoples R China Tencent Youtu Lab Shanghai 200233 Peoples R China Queen Mary Univ London Sch Elect Engn & Comp Sci London E1 4NS England
Aiming at improving the performance of visual classification in a cost-effective manner, this paper proposes an incremental semi-supervised learning paradigm called deep co-space (DCS). Unlike many conventional semi-s... 详细信息
来源: 评论