中文版 | English

在结果中检索

CSpace

浏览/检索结果: 共217条，第1-10条 帮助

已选(0)清除 条数/页：   排序方式：
Composite Object Relation Modeling for Few-Shot Scene Recognition 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 卷号: 32, 页码: 5678-5691
作者:  Song, Xinhang;  Liu, Chenlong;  Zeng, Haitao;  Zhu, Yaohui;  Chen, Gongwei;  Qin, Xiaorong;  Jiang, Shuqiang
收藏  |  浏览/下载：7/0  |  提交时间：2023/12/04
Scene recognition  few-shot learning  graph modeling  generalization ability  
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：16/0  |  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  
Chinese Traffic Police Gesture Recognition Based on Graph Convolutional Network in Natural Scene 期刊论文
APPLIED SCIENCES-BASEL, 2021, 卷号: 11, 期号: 24, 页码: 19
作者:  Liu, Kang;  Zheng, Ying;  Yang, Junyi;  Bao, Hong;  Zeng, Haoming
收藏  |  浏览/下载：21/0  |  提交时间：2022/12/07
graph convolution network  attention mechanism  traffic police gesture recognition  
Bridging Text and Video: A Universal Multimodal Transformer for Audio-Visual Scene-Aware Dialog 期刊论文
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2021, 卷号: 29, 页码: 2476-2483
作者:  Li, Zekang;  Li, Zongjia;  Zhang, Jinchao;  Feng, Yang;  Zhou, Jie
收藏  |  浏览/下载：38/0  |  提交时间：2021/12/01
Task analysis  Feature extraction  Visualization  Speech processing  History  Social networking (online)  Pattern recognition  Dialogue System  Multimodal  Natural Language Processing  Video Understanding  
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：40/0  |  提交时间：2020/12/10
Feature extraction  Visualization  Semantics  Context modeling  Image recognition  Computer vision  Aggregates  Scene recognition  scene attribute  
Learning to Recognize Visual Concepts for Visual Question Answering With Structural Label Space 期刊论文
IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2020, 卷号: 14, 期号: 3, 页码: 494-505
作者:  Gao, Difei;  Wang, Ruiping;  Shan, Shiguang;  Chen, Xilin
收藏  |  浏览/下载：53/0  |  提交时间：2020/12/10
Visualization  Semantics  Grounding  Knowledge discovery  Sports  Task analysis  Image recognition  Visual question answering  visual concept recognition  structural label space  
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：37/0  |  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：39/0  |  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  
Accelerating DNN-based 3D point cloud processing for mobile computing 期刊论文
SCIENCE CHINA-INFORMATION SCIENCES, 2019, 卷号: 62, 期号: 11, 页码: 11
作者:  Liu, Bosheng;  Chen, Xiaoming;  Han, Yinhe;  Li, Jiajun;  Xu, Haobo;  Li, Xiaowei
收藏  |  浏览/下载：223/0  |  提交时间：2019/12/10
deep neural network acceleration  point cloud data  neighbor point search  mobile robotics  hardware architecture  
Cross-Modality Bridging and Knowledge Transferring for Image Understanding 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2019, 卷号: 21, 期号: 10, 页码: 2675-2685
作者:  Yan, Chenggang;  Li, Liang;  Zhang, Chunjie;  Liu, Bingtao;  Zhang, Yongdong;  Dai, Qionghai
收藏  |  浏览/下载：276/0  |  提交时间：2019/12/10
Object and scene recognition  image semantic search  cross-modality bridging  multi-task learning  knowledge transferring