CSpace

浏览/检索结果: 共6条,第1-6条 帮助

限定条件            
已选(0)清除 条数/页:   排序方式:
Amorphous Region Context Modeling for Scene Recognition 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2022, 卷号: 24, 页码: 141-151
作者:  Zeng, Haitao;  Song, Xinhang;  Chen, Gongwei;  Jiang, Shuqiang
收藏  |  浏览/下载:18/0  |  提交时间:2022/12/07
Semantics  Feature extraction  Image segmentation  Convolution  Context modeling  Saliency detection  Layout  Graph neural network  scene recognition  semantic segmentation  
Learning Scene Attribute for Scene Recognition 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2020, 卷号: 22, 期号: 6, 页码: 1519-1530
作者:  Zeng, Haitao;  Song, Xinhang;  Chen, Gongwei;  Jiang, Shuqiang
收藏  |  浏览/下载:41/0  |  提交时间:2020/12/10
Feature extraction  Visualization  Semantics  Context modeling  Image recognition  Computer vision  Aggregates  Scene recognition  scene attribute  
Scene Recognition With Prototype-Agnostic Scene Layout 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 卷号: 29, 页码: 5877-5888
作者:  Chen, Gongwei;  Song, Xinhang;  Zeng, Haitao;  Jiang, Shuqiang
收藏  |  浏览/下载:38/0  |  提交时间:2020/12/10
Layout  Semantics  Prototypes  Image recognition  Convolution  Neural networks  Deformable models  Scene classification  convolution neural networks  graph neural networks  scene layout  
Image Representations With Spatial Object-to-Object Relations for RGB-D Scene Recognition 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 卷号: 29, 页码: 525-537
作者:  Song, Xinhang;  Jiang, Shuqiang;  Wang, Bohan;  Chen, Chengpeng;  Chen, Gongwei
收藏  |  浏览/下载:40/0  |  提交时间:2020/12/10
Feature extraction  Object detection  Image recognition  Layout  Data models  Recurrent neural networks  Scene recognition  object-to-object relation  sequential representations  RGB-D  object detection  
Learning Effective RGB-D Representations for Scene Recognition 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 卷号: 28, 期号: 2, 页码: 980-993
作者:  Song, Xinhang;  Jiang, Shuqiang;  Herranz, Luis;  Chen, Chengpeng
收藏  |  浏览/下载:71/0  |  提交时间:2019/04/03
Scene recognition  deep learning  multimodal  RGB-D  video  CNN  RNN  
Multi-Scale Multi-Feature Context Modeling for Scene Recognition in the Semantic Manifold 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 卷号: 26, 期号: 6, 页码: 2721-2735
作者:  Song, Xinhang;  Jiang, Shuqiang;  Herranz, Luis
收藏  |  浏览/下载:51/0  |  提交时间:2019/12/12
Scene recognition  semantic manifold  semantic multinomial  multi-scale  context model  Markov random field  convolutional neural networks