CASIA OpenIR

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:
从视频到语言:视频标题生成与描述研究综述 期刊论文
自动化学报, 2022, 卷号: 48, 期号: 2, 页码: 375-397
作者:  汤鹏杰;  王瀚漓
Adobe PDF(8546Kb)  |  收藏  |  浏览/下载:46/8  |  提交时间:2024/05/20
视频描述  卷积神经网络  循环神经网络  语段生成  情感表达  逻辑语义  
Compositional Prompting Video-language Models to Understand Procedure in Instructional Videos 期刊论文
Machine Intelligence Research, 2023, 卷号: 20, 期号: 2, 页码: 249-262
作者:  Guyue Hu;  Bin He;  Hanwang Zhang
Adobe PDF(2167Kb)  |  收藏  |  浏览/下载:62/26  |  提交时间:2024/04/23
Prompt learning  video-language pretrained models  instructional videos  procedure understanding  knowledge distilling  
Editorial for Special Issue on Large-scale Pre-training: Data, Models, and Fine-tuning 期刊论文
Machine Intelligence Research, 2023, 卷号: 20, 期号: 2, 页码: 145-146
作者:  Ji-Rong Wen;  Zi Huang;  Hanwang Zhang
Adobe PDF(513Kb)  |  收藏  |  浏览/下载:9/5  |  提交时间:2024/04/23
Coarse-to-Fine Video Instance Segmentation With Factorized Conditional Appearance Flows 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2023, 卷号: 10, 期号: 5, 页码: 1192-1208
作者:  Zheyun Qin;  Xiankai Lu;  Xiushan Nie;  Dongfang Liu;  Yilong Yin;  Wenguan Wang
Adobe PDF(42794Kb)  |  收藏  |  浏览/下载:94/27  |  提交时间:2023/04/26
Embedding learning  generative model  normalizing flows  video instance segmentation (VIS)  
Toward Data-Driven Digital Therapeutics Analytics: Literature Review and Research Directions 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2023, 卷号: 10, 期号: 1, 页码: 42-66
作者:  Uichin Lee;  Gyuwon Jung;  Eun-Yeol Ma;  Jin San Kim;  Heepyung Kim;  Jumabek Alikhanov;  Youngtae Noh;  Heeyoung Kim
Adobe PDF(2887Kb)  |  收藏  |  浏览/下载:538/355  |  提交时间:2023/01/03
Causal inference  data-driven analytics framework  digital therapeutics (DTx)  mobile and wearable data  technical and behavioral engagement  
STRNet: Triple-stream Spatiotemporal Relation Network for Action Recognition 期刊论文
International Journal of Automation and Computing, 2021, 卷号: 18, 期号: 5, 页码: 718-730
作者:  Zhi-Wei Xu;  Xiao-Jun Wu;  Josef Kittler
Adobe PDF(1129Kb)  |  收藏  |  浏览/下载:213/55  |  提交时间:2021/09/13
Action recognition  spatiotemporal relation  multi-branch fusion  long-term representation  video classification