EXPLORING SYNONYMS AS CONTEXT IN ZERO-SHOT ACTION RECOGNITION

被引:0
作者
Alexiou, Ioannis [1 ]
Xiang, Tao [2 ]
Gong, Shaogang [1 ]
机构
[1] Queen Mary Univ London, London, England
[2] Vis Semant Ltd, London, England
来源
2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2016年
关键词
zero-shot learning; action recognition; semantic embedding;
D O I
暂无
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Zero shot learning (ZSL) provides a solution to recognising unseen classes without class labelled data for model learning. Most ZSL methods aim to learn a mapping from a visual feature space to a semantic embedding space, e.g. attribute or word vector spaces. The use of word vector space is particularly attractive as compared to attribute, it offers vast auxiliary classes with free parts embedding without human annotation. However, using the word vector embedding often provides weaker discriminative power than manually labelled attributes of the auxiliary classes. This is compounded further in zero-shot action recognition due to richer content variations among action classes. In this work we propose to explore a broader semantic contextual information in the text domain to enrich the word vector representation of action classes. We show through extensive experiments that this method improves significantly the performance of a number of existing word vector embedding ZSL methods. Moreover, it also outperforms attribute embedding ZSL with human annotation.
引用
收藏
页码:4190 / 4194
页数:5
相关论文
共 50 条
[21]   Zero-Shot Action Recognition with Knowledge Enhanced Generative Adversarial Networks [J].
Huang, Kaiqiang ;
Miralles-Pechuan, Luis ;
Mckeever, Susan .
PROCEEDINGS OF THE 13TH INTERNATIONAL JOINT CONFERENCE ON COMPUTATIONAL INTELLIGENCE (IJCCI), 2021, :254-264
[22]   Zero-Shot Learning for Skeleton-based Classroom Action Recognition [J].
Shi, Bin ;
Wang, Luyang ;
Yu, Zefang ;
Xiang, Suncheng ;
Liu, Ting ;
Fu, Yuzhuo .
2021 INTERNATIONAL SYMPOSIUM ON COMPUTER SCIENCE AND INTELLIGENT CONTROLS (ISCSIC 2021), 2021, :82-86
[23]   Learning Spatio-Temporal Semantics and Cluster Relation for Zero-Shot Action Recognition [J].
Gao, Jiajun ;
Hou, Yonghong ;
Guo, Zihui ;
Zheng, Haochun .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 33 (11) :6519-6530
[24]   Learning temporal information and object relation for zero-shot action recognition [J].
Qi, Qiuping ;
Wang, Hanli ;
Su, Taiyi ;
Liu, Xianhui .
DISPLAYS, 2022, 73
[25]   Manifold embedding for zero-shot recognition [J].
Ji, Zhong ;
Yu, Xuejie ;
Yu, Yunlong ;
He, Yuqing .
COGNITIVE SYSTEMS RESEARCH, 2019, 55 :34-43
[26]   GAN for vision, KG for relation: A two-stage network for zero-shot action recognition [J].
Sun, Bin ;
Kong, Dehui ;
Wang, Shaofan ;
Li, Jinghua ;
Yin, Baocai ;
Luo, Xiaonan .
PATTERN RECOGNITION, 2022, 126
[27]   Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization [J].
Zhou, Yujie ;
Qiang, Wenwen ;
Rao, Anyi ;
Lin, Ning ;
Su, Bing ;
Wang, Jiaqi .
PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, :5302-5310
[28]   Sequence feature generation with temporal unrolling network for zero-shot action recognition [J].
Lee, Jewook ;
Kim, Hoseong ;
Byun, Hyeran .
NEUROCOMPUTING, 2021, 448 :313-323
[29]   Combining Text and Image Knowledge with GANs for Zero-Shot Action Recognition in Videos [J].
Huang, Kaiqiang ;
Miralles-Pechuan, Luis ;
Mckeever, Susan .
PROCEEDINGS OF THE 17TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS (VISAPP), VOL 5, 2022, :623-631
[30]   Fine-grained Human Action Recognition Based on Zero-Shot Learning [J].
Zhao, Yahui ;
Shi, Ping ;
You, Jian .
PROCEEDINGS OF 2019 IEEE 10TH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING AND SERVICE SCIENCE (ICSESS 2019), 2019, :294-297