中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 多媒体计算与图形学团队
Knowledge-driven Egocentric Multimodal Activity Recognition

文献类型：期刊论文

作者Huang, Yi1,2,3; Yang, Xiaoshan1,2,3; Gao, Junyu1,2,3; Sang, Jitao1,4,5; Xu, Changsheng1,2,3
刊名ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
出版日期2020-12-01
卷号16期号:4页码:21
ISSN号1551-6857
关键词Egocentric videos wearable sensors graph neural networks
DOI10.1145/3409332
通讯作者Huang, Yi(yi.huang@nlpria.ac.cn)
英文摘要Recognizing activities from egocentric multimodal data collected by wearable cameras and sensors, is gaining interest, as multimodal methods always benefit from the complementarity of different modalities. However, since high-dimensional videos contain rich high-level semantic information while low-dimensional sensor signals describe simple motion patterns of the wearer, the large modality gap between the videos and the sensor signals raises a challenge for fusing the raw data. Moreover, the lack of large-scale egocentric multimodal datasets due to the cost of data collection and annotation processes makes another challenge for employing complex deep learning models. To jointly deal with the above two challenges, we propose a knowledge-driven multimodal activity recognition framework that exploits external knowledge to fuse multimodal data and reduce the dependence on large-scale training samples. Specifically, we design a dual-GCLSTM (Graph Convolutional LSTM) and a multi-layer GCN (Graph Convolutional Network) to collectively model the relations among activities and intermediate objects. The dual-GCLSTM is designed to fuse temporal multimodal features with top-down relation-aware guidance. In addition, we apply a co-attention mechanism to adaptively attend to the features of different modalities at different timesteps. The multi-layer GCN aims to learn relation-aware classifiers of activity categories. Experimental results on three publicly available egocentric multimodal datasets show the effectiveness of the proposed model.
WOS关键词1ST-PERSON VISION ; VIDEOS
资助项目National Key Research and Development Program of China[2018AAA0100604] ; National Natural Science Foundation of China[61720106006] ; National Natural Science Foundation of China[62072455] ; National Natural Science Foundation of China[61702511] ; National Natural Science Foundation of China[61751211] ; National Natural Science Foundation of China[61620106003] ; National Natural Science Foundation of China[61532009] ; National Natural Science Foundation of China[U1836220] ; National Natural Science Foundation of China[U1705262] ; National Natural Science Foundation of China[61872424] ; Key Research Program of Frontier Sciences of CAS[QYZDJSSWJSC039] ; Research Program of National Laboratory of Pattern Recognition[Z-2018007]
WOS研究方向Computer Science
语种英语
出版者ASSOC COMPUTING MACHINERY
WOS记录号WOS:000614096700017
资助机构National Key Research and Development Program of China ; National Natural Science Foundation of China ; Key Research Program of Frontier Sciences of CAS ; Research Program of National Laboratory of Pattern Recognition
源URL[http://ir.ia.ac.cn/handle/173211/42873]  
专题自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
通讯作者Huang, Yi
作者单位1.Peng Cheng Lab, Shenzhen, Peoples R China
2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, 95 Zhongguancun East Rd, Beijing, Peoples R China
3.Univ Chinese Acad Sci, Sch Artificial Intelligence, 95 Zhongguancun East Rd, Beijing, Peoples R China
4.Beijing Jiaotong Univ, Beijing Key Lab Traff Data Anal & Min, 506 Room 9 Teaching Bldg, Beijing, Peoples R China
5.Beijing Jiaotong Univ, Sch Comp & Informat Technol, 506 Room 9 Teaching Bldg, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Huang, Yi,Yang, Xiaoshan,Gao, Junyu,et al. Knowledge-driven Egocentric Multimodal Activity Recognition[J]. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,2020,16(4):21.
APA Huang, Yi,Yang, Xiaoshan,Gao, Junyu,Sang, Jitao,&Xu, Changsheng.(2020).Knowledge-driven Egocentric Multimodal Activity Recognition.ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,16(4),21.
MLA Huang, Yi,et al."Knowledge-driven Egocentric Multimodal Activity Recognition".ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 16.4(2020):21.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。