CASIA OpenIR

Browse/Search Results:  1-8 of 8 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
面向自然人机交互的语言-视觉物体定位方法研究 学位论文
工学博士, 中国科学院自动化研究所: 中国科学院自动化研究所, 2022
Authors:  李钱钟
Adobe PDF(42933Kb)  |  Favorite  |  View/Download:56/3  |  Submit date:2022/06/13
自然人机交互  零样本物体检测  自然语言-图像指代表达理解  自然语言-视频指代表达理解  
Cross-Modality Synergy Network for Referring Expression Comprehension and Segmentation 期刊论文
Neurocomputing, 2022, 卷号: 467, 期号: /, 页码: 99-114
Authors:  Li, Qianzhong;  Zhang, Yujia;  Sun, Shiying;  Wu, Jinting;  Zhao, Xiaoguang;  Tan, Min
Adobe PDF(4555Kb)  |  Favorite  |  View/Download:45/1  |  Submit date:2021/12/28
Referring expression comprehension  Referring expression segmentation  Cross-modality synergy  Attention mechanism  
Beyond Crack: Fine-Grained Pavement Defect Segmentation Using Three-Stream Neural Networks 期刊论文
IEEE Transactions on Intelligent Transportation Systems, 2021, 卷号: /, 期号: /, 页码: /
Authors:  Zhang, Yujia;  Wu, Junxian;  Li, Qianzhong;  Zhao, Xiaoguang;  Tan, Min
Adobe PDF(12585Kb)  |  Favorite  |  View/Download:35/5  |  Submit date:2022/04/02
Fine-grained defect segmentation  Crack detection  Semantic segmentation  Pavement inspection  
Generalized zero-shot emotion recognition from body gestures 期刊论文
APPLIED INTELLIGENCE, 2021, 页码: 19
Authors:  Wu, Jinting;  Zhang, Yujia;  Sun, Shiying;  Li, Qianzhong;  Zhao, Xiaoguang
Adobe PDF(2059Kb)  |  Favorite  |  View/Download:27/1  |  Submit date:2021/12/28
Generalized zero-shot learning  Emotion recognition  Body gesture recognition  Prototype learning  
Rethinking semantic-visual alignment in zero-shot object detection via a softplus margin focal loss 期刊论文
Neurocomputing, 2021, 卷号: 449, 页码: 117-135
Authors:  Li, Qianzhong;  Zhang, Yujia;  Sun, Shiying;  Zhao, Xiaoguang;  Li, Kang;  Tan, Min
Adobe PDF(8753Kb)  |  Favorite  |  View/Download:52/2  |  Submit date:2021/08/15
Zero-shot object detection  Softplus margin focal loss  Semantic-visual alignment  Auto-encoder architecture  
Robot learning through observation via coarse-to-fine grained video summarization 期刊论文
APPLIED SOFT COMPUTING, 2021, 卷号: 99, 期号: /, 页码: 106913
Authors:  Zhang, Yujia;  Li, Qianzhong;  Zhao, Xiaoguang;  Tan, Min
Adobe PDF(5989Kb)  |  Favorite  |  View/Download:75/1  |  Submit date:2021/03/08
Robotic vision  Learning through observation  Coarse-to-fine video summarization  
TB-Net: A Three-Stream Boundary-Aware Network for Fine-Grained Pavement Disease Segmentation 会议论文
, Virtual, 2021-1
Authors:  Zhang, Yujia;  Li, Qianzhong;  Zhao, Xiaoguang;  Tan, Min
Adobe PDF(1903Kb)  |  Favorite  |  View/Download:16/1  |  Submit date:2022/04/02
Inverse reinforcement learning-based time-dependent A* planner for human-aware robot navigation with local vision 期刊论文
ADVANCED ROBOTICS, 2020, 页码: 14
Authors:  Sun Shiying;  Zhao Xiaoguang;  Li Qianzhong;  Tan Min
Adobe PDF(3726Kb)  |  Favorite  |  View/Download:101/1  |  Submit date:2020/06/02
Human-aware navigation  inverse reinforcement learning  path planning  service robot