中国科学院机构知识库网格系统: 检索

Chinese Title Generation for Short Videos: Dataset, Metric and Algorithm 期刊论文 OAI收割
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 卷号: 46, 期号: 7, 页码: 5192-5208
作者: Zhang, Ziqi; Ma, Zongyang; Yuan, Chunfeng; Chen, Yuxin; Wang, Peijin

|

收藏 | 浏览/下载：17/0 | 提交时间：2024/09/09

Videos Task analysis Measurement Semantics Benchmark testing Electronic commerce Annotations Video and language short video multi-modal benchmark video titling title evaluation text-video retrieval

I(2)Transformer: Intra- and Inter-Relation Embedding Transformer for TV Show Captioning 期刊论文 OAI收割
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 卷号: 31, 页码: 3565-3577
作者: Tu, Yunbin; Li, Liang; Su, Li; Gao, Shengxiang; Yan, Chenggang

|

收藏 | 浏览/下载：46/0 | 提交时间：2022/12/07

Transformers Semantics Task analysis Visualization TV Electronic mail Graph neural networks TV Show captioning video and subtitle intra-relation embedding inter-relation embedding transformer

Visualizing and Analyzing Video Content With Interactive Scalable Maps 期刊论文 OAI收割
IEEE TRANSACTIONS ON MULTIMEDIA, 2016, 卷号: 18, 期号: 11, 页码: 2171-2183
作者: Ma, Cui-Xia; Liu, Yong-Jin; Zhao, Guozhen; Wang, Hong-An

收藏 | 浏览/下载：24/0 | 提交时间：2016/12/26

Interaction map metaphor multi-scale representation video visualization and analysis

Facial video coding/decoding at ultra-low bit-rate: a 2D/3D model-based approach 期刊论文 OAI收割
MULTIMEDIA TOOLS AND APPLICATIONS, 2016, 卷号: 75, 期号: 19, 页码: 12021-12041
作者: Yu, Jun; Luo, Changwei; Yu, Lingyun

收藏 | 浏览/下载：32/0 | 提交时间：2017/12/18

Video Coding/decoding Facial Motion Tracking Facial Animation Hair Analysis And Modeling

Visualizing and Analyzing Video Content With Interactive Scalable Maps 期刊论文 OAI收割
IEEE TRANSACTIONS ON MULTIMEDIA, 2016, 卷号: 18, 期号: 11, 页码: 2171-2183
Ma, CX; Liu, YJ; Zhao, GZ; Wang, HA

|

收藏 | 浏览/下载：23/0 | 提交时间：2016/12/09

Interaction map metaphor multi-scale representation video visualization and analysis

多目标跟踪及其在航拍视频中的应用 学位论文 OAI收割
工学博士, 中国科学院自动化研究所: 中国科学院大学, 2013
作者: 史信楚

收藏 | 浏览/下载：96/0 | 提交时间：2015/09/02

多目标跟踪数据关联秩一张量近似场景和运动上下文关系航 multiple target tracking data association rank-1 tensor approximation scene and motion context aerial video analysis

Script-to-Movie: A Computational Framework for Story Movie Composition 期刊论文 OAI收割
IEEE TRANSACTIONS ON MULTIMEDIA, 2013, 卷号: 15, 期号: 2, 页码: 401-414
作者: Liang, Chao; Xu, Changsheng; Cheng, Jian; Min, Weiqing; Lu, Hanqing

收藏 | 浏览/下载：25/0 | 提交时间：2015/08/12

Movie composition script and video analysis computational framework

The new approach for infrared target tracking based on the particle filter algorithm (EI CONFERENCE) 会议论文 OAI收割
International Symposium on Photoelectronic Detection and Imaging 2011: Advances in Infrared Imaging and Applications, May 24, 2011 - May 24, 2011, Beijing, China
作者: Sun H.; Han H.-X.; Sun H.

收藏 | 浏览/下载：59/0 | 提交时间：2013/03/25

Target tracking on the complex background in the infrared image sequence is hot research field. It provides the important basis in some fields such as video monitoring precision and video compression human-computer interaction. As a typical algorithms in the target tracking framework based on filtering and data connection the particle filter with non-parameter estimation characteristic have ability to deal with nonlinear and non-Gaussian problems so it were widely used. There are various forms of density in the particle filter algorithm to make it valid when target occlusion occurred or recover tracking back from failure in track procedure but in order to capture the change of the state space it need a certain amount of particles to ensure samples is enough and this number will increase in accompany with dimension and increase exponentially this led to the increased amount of calculation is presented. In this paper particle filter algorithm and the Mean shift will be combined. Aiming at deficiencies of the classic mean shift Tracking algorithm easily trapped into local minima and Unable to get global optimal under the complex background. From these two perspectives that "adaptive multiple information fusion" and "with particle filter framework combining" we expand the classic Mean Shift tracking framework.Based on the previous perspective we proposed an improved Mean Shift infrared target tracking algorithm based on multiple information fusion. In the analysis of the infrared characteristics of target basis Algorithm firstly extracted target gray and edge character and Proposed to guide the above two characteristics by the moving of the target information thus we can get new sports guide grayscale characteristics and motion guide border feature. Then proposes a new adaptive fusion mechanism used these two new information adaptive to integrate into the Mean Shift tracking framework. Finally we designed a kind of automatic target model updating strategy to further improve tracking performance. Experimental results show that this algorithm can compensate shortcoming of the particle filter has too much computation and can effectively overcome the fault that mean shift is easy to fall into local extreme value instead of global maximum value.Last because of the gray and fusion target motion information this approach also inhibit interference from the background ultimately improve the stability and the real-time of the target track. 2011 Copyright Society of Photo-Optical Instrumentation Engineers (SPIE).

Approach for detecting crowd panic behavior based on fluid kinematic features and entropy (EI CONFERENCE) 会议论文 OAI收割
International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2011, November 19, 2011 - November 23, 2011, Suzhou, China
作者: Li Y.; Li Y.; Li Y.; Zhang X.; Zhang X.

收藏 | 浏览/下载：25/0 | 提交时间：2013/03/25

Crowd panic behavior detection is an important task in video analysis and event recognition whose purpose is to detect when the panic behavior happened and alarming the abnormal event timely. In this paper the crowd is regard as a fluid and the crowd motion is described by four fluid kinematic features (divergence vorticity gradient tensor invariant and rotation tensor invariant). To discriminate the panic event from normal crowd behavior an information entropy is calculated as a high level feature based on the fluid kinematic features. Experimental results show that the entropy raised dramatically once a panic event happened.

广播体育视频中的战术分析研究 学位论文 OAI收割
工学博士, 中国科学院自动化研究所: 中国科学院研究生院, 2010
作者: 张奕

收藏 | 浏览/下载：35/0 | 提交时间：2015/09/02

体育视频分析语义理解球和球员轨迹提取战术分析 sports video analysis semantics ball and player trajectory extraction tactic analysis