中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共77条，第1-10条 帮助

已选(0)清除 条数/页：   排序方式：
Cross-modal Contrastive Learning for Generalizable and Efficient Image-text Retrieval 期刊论文
Machine Intelligence Research, 2023, 卷号: 20, 期号: 4, 页码: 569-582
作者:  Haoyu Lu;  Yuqi Huo;  Mingyu Ding;  Nanyi Fei;  Zhiwu Lu
Adobe PDF(2928Kb)  |  收藏  |  浏览/下载：11/2  |  提交时间：2024/04/23
Image-text retrieval, multimodal modeling, contrastive learning, weak correlation, computer vision  
Region-adaptive Concept Aggregation for Few-shot Visual Recognition 期刊论文
Machine Intelligence Research, 2023, 卷号: 20, 期号: 4, 页码: 554-568
作者:  Mengya Han;  Yibing Zhan;  Baosheng Yu;  Yong Luo;  Han Hu;  Bo Du;  Yonggang Wen;  Dacheng Tao
Adobe PDF(4324Kb)  |  收藏  |  浏览/下载：13/4  |  提交时间：2024/04/23
Few-shot learning, metric-based meta learning, concept learning, region-adaptive, concept-aggregation  
Transformer: A General Framework from Machine Translation to Others 期刊论文
Machine Intelligence Research, 2023, 卷号: 20, 期号: 4, 页码: 514-538
作者:  Yang Zhao;  Jiajun Zhang;  Chengqing Zong
Adobe PDF(1415Kb)  |  收藏  |  浏览/下载：14/5  |  提交时间：2024/04/23
Neural machine translation, Transformer, document neural machine translation (NMT), multimodal NMT, low-resource NMT  
Video Polyp Segmentation: A Deep Learning Perspective 期刊论文
Machine Intelligence Research, 2022, 卷号: 19, 期号: 6, 页码: 531-549
作者:  Ge-Peng Ji;  Guobao Xiao;  Yu-Cheng Chou;  Deng-Ping Fan;  Kai Zhao;  Geng Chen;  Luc Van Gool
Adobe PDF(9520Kb)  |  收藏  |  浏览/下载：14/2  |  提交时间：2024/04/23
Video polyp segmentation (VPS)  dataset  self-attention  colonoscopy  abdomen  
Efficient Visual Recognition: A Survey on Recent Advances and Brain-inspired Methodologies 期刊论文
Machine Intelligence Research, 2022, 卷号: 19, 期号: 5, 页码: 366-411
作者:  Yang Wu;  Ding-Heng Wang;  Xiao-Tong Lu;  Fan Yang;  Man Yao;  Wei-Sheng Dong;  Jian-Bo Shi;  Guo-Qi Li
Adobe PDF(6780Kb)  |  收藏  |  浏览/下载：15/3  |  提交时间：2024/04/23
Visual recognition  deep neural networks (DNNS)  brain-inspired methodologies  network compression  dynamic inference  survey  
Visual Semantic Segmentation Based on Few/Zero-Shot Learning: An Overview 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2024, 卷号: 11, 期号: 5, 页码: 1106-1126
作者:  Wenqi Ren;  Yang Tang;  Qiyu Sun;  Chaoqiang Zhao;  Qing-Long Han
Adobe PDF(12695Kb)  |  收藏  |  浏览/下载：21/2  |  提交时间：2024/04/10
Computer vision  deep learning  few-shot learning  low-shot learning  semantic segmentation  zero-shot learning  
A Weakly-Supervised Crowd Density Estimation Method Based on Two-Stage Linear Feature Calibration 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2024, 卷号: 11, 期号: 4, 页码: 965-981
作者:  Yong-Chao Li;  Rui-Sheng Jia;  Ying-Xiang Hu;  Hong-Mei Sun
Adobe PDF(10448Kb)  |  收藏  |  浏览/下载：33/14  |  提交时间：2024/03/18
Crowd density estimation  linear feature calibration  vision transformer  weakly-supervision learning  
A Novel Tensor Decomposition-Based Efficient Detector for Low-Altitude Aerial Objects With Knowledge Distillation Scheme 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2024, 卷号: 11, 期号: 2, 页码: 487-501
作者:  Nianyin Zeng;  Xinyu Li;  Peishu Wu;  Han Li;  Xin Luo
Adobe PDF(12478Kb)  |  收藏  |  浏览/下载：65/17  |  提交时间：2024/01/23
Attention mechanism  knowledge distillation (KD)  object detection  tensor decomposition (TD)  unmanned aerial vehicles (UAVs)  
Noise-Tolerant ZNN-Based Data-Driven Iterative Learning Control for Discrete Nonaffine Nonlinear MIMO Repetitive Systems 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2024, 卷号: 11, 期号: 2, 页码: 344-361
作者:  Yunfeng Hu;  Chong Zhang;  Bo Wang;  Jing Zhao;  Xun Gong;  Jinwu Gao;  Hong Chen
Adobe PDF(15857Kb)  |  收藏  |  浏览/下载：77/19  |  提交时间：2024/01/23
Adaptive control  control system synthesis  data-driven iterative learning control  neurocontroller  nonlinear discrete time systems  
TR-MISR: Multiimage super-resolution based on feature fusion with transformers 期刊论文
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 卷号: 15, 页码: 1373-1388
作者:  An T(安泰);  Zhang X(张鑫);  Huo CL(霍春雷);  Xue B(薛斌);  Wang LF(汪凌峰);  Pan CH(潘春洪)
Adobe PDF(6058Kb)  |  收藏  |  浏览/下载：119/10  |  提交时间：2024/01/17
Deep learning  end-to-end networks  feature extraction and fusion  multiimage super-resolution (MISR)  remote sensing  transformers