Research on Volleyball Video Intelligent Description Technology Combining the Long-Term and Short-Term Memory Network and Attention Mechanism

被引:3
|
作者
Gao, Yuhua [1 ]
Mo, Yong [2 ]
Zhang, Heng [3 ]
Huang, Ruiyin [1 ]
Chen, Zilong [1 ]
机构
[1] Guangzhou Sport Univ, Guangzhou 510500, Guangdong, Peoples R China
[2] Guangdong Baiyun Univ, Guangzhou 510450, Guangdong, Peoples R China
[3] Yingshan Cty 1 Middle Sch, Yingshan 438700, Hubei, Peoples R China
关键词
D O I
10.1155/2021/7088837
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
With the development of computer technology, video description, which combines the key technologies in the field of natural language processing and computer vision, has attracted more and more researchers' attention. Among them, how to objectively and efficiently describe high-speed and detailed sports videos is the key to the development of the video description field. In view of the problems of sentence errors and loss of visual information in the generation of the video description text due to the lack of language learning information in the existing video description methods, a multihead model combining the long-term and short-term memory network and attention mechanism is proposed for the intelligent description of the volleyball video. Through the introduction of the attention mechanism, the model pays much attention to the significant areas in the video when generating sentences. Through the comparative experiment with different models, the results show that the model with the attention mechanism can effectively solve the loss of visual information. Compared with the LSTM and base model, the multihead model proposed in this paper, which combines the long-term and short-term memory network and attention mechanism, has higher scores in all evaluation indexes and significantly improved the quality of the intelligent text description of the volleyball video.
引用
收藏
页数:11
相关论文
共 50 条
  • [41] Optimized Deep Stacked Long Short-Term Memory Network for Long-Term Load Forecasting
    Farrag, Tamer Ahmed
    Elattar, Ehab E.
    IEEE ACCESS, 2021, 9 : 68511 - 68522
  • [42] MALICIOUS LOGIN DETECTION USING LONG SHORT-TERM MEMORY WITH AN ATTENTION MECHANISM
    Wu, Yanna
    Liu, Fucheng
    Wen, Yu
    ADVANCES IN DIGITAL FORENSICS XVII, 2021, 612 : 157 - 173
  • [43] Intrusion Detection Based on Bidirectional Long Short-Term Memory with Attention Mechanism
    Yang, Yongjie
    Tu, Shanshan
    Ali, Raja Hashim
    Alasmary, Hisham
    Waqas, Muhammad
    Amjad, Muhammad Nouman
    CMC-COMPUTERS MATERIALS & CONTINUA, 2023, 74 (01): : 801 - 815
  • [44] EEG-Based Emotion Classification Using Long Short-Term Memory Network with Attention Mechanism
    Kim, Youmin
    Choi, Ahyoung
    SENSORS, 2020, 20 (23) : 1 - 22
  • [45] Water Flow Prediction Based on Improved Spatiotemporal Attention Mechanism of Long Short-Term Memory Network
    Hu, Wenwen
    Yu, Yongchuan
    Yan, Jianzhuo
    Zhao, Zhe
    Sun, Wenxue
    Shen, Xumeng
    WATER, 2024, 16 (11)
  • [46] Short-Term Memory to Long-Term Memory Transition in a Nanoscale Memristor
    Chang, Ting
    Jo, Sung-Hyun
    Lu, Wei
    ACS NANO, 2011, 5 (09) : 7669 - 7676
  • [47] The time needed to consolidate short-term memory to long-term memory
    Takeyama, E
    Takenoshita, M
    Nishimura, S
    Yoshiya, I
    ANESTHESIOLOGY, 1998, 89 (3A) : U317 - U317
  • [48] Two circuits to convert short-term memory into long-term memory
    Wong, CW
    MEDICAL HYPOTHESES, 1997, 49 (05) : 375 - 378
  • [49] RETRACTED: Research on Action Recognition Based on Deep Learning with Long Short-Term Memory Network and Attention Mechanism (Retracted Article)
    Feng, Wei
    Feng, Yanshun
    WIRELESS COMMUNICATIONS & MOBILE COMPUTING, 2022, 2022
  • [50] APPLICATION RESEARCH ON LONG SHORT-TERM MEMORY NETWORK IN FAULT DIAGNOSIS
    Wang, Wei-Feng
    Qiu, Xue-Huan
    Chen, Cai-Sen
    Lin, Bo
    Zhang, Hui-Min
    PROCEEDINGS OF 2018 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS (ICMLC), VOL 2, 2018, : 360 - 365