中国科学院机构知识库网格系统: 检索

浏览/检索结果: 共3条，第1-3条

帮助

条数/页：排序方式：
	Bridging Text and Video: A Universal Multimodal Transformer for Audio-Visual Scene-Aware Dialog 期刊论文 OAI收割 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：52/0 \| 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
	Spatiotemporal Statistics for Video Quality Assessment 期刊论文 OAI收割 ieee transactions on image processing, 2016, 卷号: 25, 期号: 7, 页码: 3329-3342 作者: Li, Xuelong; Guo, Qun; Lu, Xiaoqiang 收藏 \| 浏览/下载：23/0 \| 提交时间：2016/09/22 Video quality assessment no-reference 3D-DCT natural video spatiotemporal statistics
	A video synthesis method for flow patterns (EI CONFERENCE) 会议论文 OAI收割 2010 2nd IEEE International Conference on Network Infrastructure and Digital Content, IC-NIDC 2010, September 24, 2010 - September 26, 2010, Beijing, China 作者: Chen J.; Liu J.; Yu D.; Yu D.; Li J. 收藏 \| 浏览/下载：24/0 \| 提交时间：2013/03/25 This paper presents a new video synthesis method for flow patterns. We can use it to synthesize video of natural phenomena that exhibit continuous flow patterns. It is based on flow-based video synthesis algorithm and combines partial ideas of graph cuts algorithm. This algorithm can process input videos of natural phenomena of flow patterns (e.g. rivers flames and waterfalls) and synthesize more realistic and active seamless video of arbitrary length than other algorithms. It is simple to implement. The results show that our method can produce satisfactory effects based on user inputs. 2010 IEEE.