咨询与建议

限定检索结果

文献类型

  • 3 篇 会议
  • 2 篇 期刊文献

馆藏范围

  • 5 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 5 篇 工学
    • 5 篇 计算机科学与技术...
    • 3 篇 电气工程
    • 1 篇 信息与通信工程
    • 1 篇 软件工程
  • 1 篇 理学
    • 1 篇 物理学

主题

  • 5 篇 vision-language ...
  • 1 篇 transformer
  • 1 篇 transductive lea...
  • 1 篇 multimodal fusio...
  • 1 篇 task analysis
  • 1 篇 unsupervised dom...
  • 1 篇 transformers
  • 1 篇 multimodal deep ...
  • 1 篇 multi-modal lear...
  • 1 篇 sentiment classi...
  • 1 篇 contrastive lear...
  • 1 篇 text-based perso...
  • 1 篇 pedestrians
  • 1 篇 visualization
  • 1 篇 noisy label lear...
  • 1 篇 feature extracti...
  • 1 篇 self-training
  • 1 篇 search problems
  • 1 篇 sentiment analys...
  • 1 篇 image inpainting

机构

  • 2 篇 huawei cloud peo...
  • 1 篇 zhejianng univ c...
  • 1 篇 zhejiang univ pe...
  • 1 篇 univ sci & techn...
  • 1 篇 univ sains malay...
  • 1 篇 gandong univ sch...
  • 1 篇 south china univ...
  • 1 篇 univ sci & techn...
  • 1 篇 hikvis res inst ...
  • 1 篇 eastern inst tec...

作者

  • 1 篇 zainon wan mohd ...
  • 1 篇 jin xin
  • 1 篇 ding binfen
  • 1 篇 xie di
  • 1 篇 tian qi
  • 1 篇 chen zhibo
  • 1 篇 xiao lei
  • 1 篇 an jieyu
  • 1 篇 zhou wengang
  • 1 篇 huang junchu
  • 1 篇 xie lingxi
  • 1 篇 bao liping
  • 1 篇 pu shiliang
  • 1 篇 yang shicai
  • 1 篇 feng ruoyu
  • 1 篇 liu lin
  • 1 篇 yu tao
  • 1 篇 xing wei
  • 1 篇 wei longhui
  • 1 篇 li ailin

语言

  • 5 篇 英文
检索条件"主题词=Vision-Language Pre-trained Model"
5 条 记 录,以下是1-10 订阅
排序:
Improving multimodal sentiment prediction through vision-language feature interaction
收藏 引用
MULTIMEDIA SYSTEMS 2025年 第1期31卷 1-12页
作者: An, Jieyu Ding, Binfen Zainon, Wan Mohd Nazmee Wan Gandong Univ Sch Informat Engn Fuzhou 344000 Jiangxi Peoples R China Univ Sains Malaysia Sch Comp Sci George Town 11800 Malaysia
Multimodal sentiment analysis aims to accurately assess the sentiment expressed in a given data source by integrating and analyzing multiple modalities, such as text and images. Extracting discriminative features for ... 详细信息
来源: 评论
Multi-Granularity Matching Transformer for Text-Based Person Search
收藏 引用
IEEE TRANSACTIONS ON MULTIMEDIA 2024年 26卷 4281-4293页
作者: Bao, Liping Wei, Longhui Zhou, Wengang Liu, Lin Xie, Lingxi Li, Houqiang Tian, Qi Univ Sci & Technol China Dept Elect Engn & Informat Sci Hefei 230027 Peoples R China Univ Sci & Technol China Dept Elect Engn & Informat Sci Hefei 230027 Peoples R China Huawei Cloud Shenzhen 518129 Peoples R China
Text-based person search aims to retrieve the most relevant pedestrian images from an image gallery based on textual descriptions. Most existing methods rely on two separate encoders to extract the image and text feat... 详细信息
来源: 评论
RETHINKING DOMAIN ADAPTATION AND GENERALIZATION IN THE ERA OF CLIP  31
RETHINKING DOMAIN ADAPTATION AND GENERALIZATION IN THE ERA O...
收藏 引用
2024 International Conference on Image Processing
作者: Feng, Ruoyu Yu, Tao Jin, Xin Yu, Xiaoyuan Xiao, Lei Chen, Zhibo Univ Sci & Technol China Beijing Peoples R China Eastern Inst Technol Ningbo Peoples R China Huawei Cloud Ningbo Peoples R China
In recent studies on domain adaptation, significant emphasis has been placed on the advancement of learning shared knowledge from a source domain to a target domain. Recently, the large vision-language pre-trained mod... 详细信息
来源: 评论
Towards Interactive Facial Image Inpainting by Text or Exemplar Image  29th
Towards Interactive Facial Image Inpainting by Text or Exemp...
收藏 引用
29th International Conference on MultiMedia modeling (MMM)
作者: Li, Ailin Zhao, Lei Zuo, Zhiwen Wang, Zhizhong Xing, Wei Lu, Dongming Zhejianng Univ Coll Comp Sci & Technol Hangzhou Peoples R China
Facial image inpainting aims to fill visually realistic and semantically new pixels for masked or missing pixels in a face image. Although current methods have made progress in achieving high visual quality, the contr... 详细信息
来源: 评论
TRANSDUCTIVE CLIP WITH CLASS-CONDITIONAL CONTRASTIVE LEARNING  47
TRANSDUCTIVE CLIP WITH CLASS-CONDITIONAL CONTRASTIVE LEARNIN...
收藏 引用
47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
作者: Huang, Junchu Chen, Weijie Yang, Shicai Xie, Di Pu, Shiliang Zhuang, Yueting South China Univ Technol Guangzhou Peoples R China Hikvis Res Inst Hangzhou Peoples R China Zhejiang Univ Hangzhou Peoples R China
Inspired by the remarkable zero-shot generalization capacity of vision-language pre-trained model, we seek to leverage the supervision from CLIP model to alleviate the burden of data labeling. However, such supervisio... 详细信息
来源: 评论