Action Recognition and State Change Prediction in a Recipe Understanding Task Using a Lightweight Neural Network Model

被引:0
|
作者
Wan, Qing [1 ]
Choe, Yoonsuck [1 ]
机构
[1] Texas A&M Univ, Dept Comp Sci & Engn, College Stn, TX 77843 USA
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Consider a natural language sentence describing a specific step in a food recipe. In such instructions, recognizing actions (such as press, bake, etc.) and the resulting changes in the state of the ingredients (shape molded, custard cooked, temperature hot, etc.) is a challenging task. One way to cope with this challenge is to explicitly model a simulator module that applies actions to entities and predicts the resulting outcome (Bosselut et al. 2018). However, such a model can be unnecessarily complex. In this paper, we propose a simplified neural network model that separates action recognition and state change prediction, while coupling the two through a novel loss function. This allows learning to indirectly influence each other. Our model, although simpler, achieves higher state change prediction performance (67% average accuracy for ours vs. 55% in (Bosselut et al. 2018)) and takes fewer samples to train (10K ours vs. 65K+ by (Bosselut et al. 2018)).
引用
收藏
页码:13945 / 13946
页数:2
相关论文
共 50 条
  • [31] IIRNet: A lightweight deep neural network using intensely inverted residuals for image recognition
    Li, Yuyuan
    Zhang, Dong
    Lee, Dah-Jye
    IMAGE AND VISION COMPUTING, 2019, 92
  • [32] Throughput Prediction Using Recurrent Neural Network Model
    Wei, Bo
    Okano, Mayuko
    Kanai, Kenji
    Kawakami, Wataru
    Katto, Jiro
    2018 IEEE 7TH GLOBAL CONFERENCE ON CONSUMER ELECTRONICS (GCCE 2018), 2018, : 107 - 108
  • [33] Breast cancer prediction using a neural network model
    Nastac, I
    Jalava, P
    Collan, M
    Collan, Y
    Kuopio, T
    Back, B
    Soft Computing with Industrial Applications, Vol 17, 2004, 17 : 423 - 428
  • [34] Prediction Model Development using Neural Network Approach
    Chavan, Sumit
    Dorle, Avanti
    Kulkarni, Siddhivinayak
    Venkatraman, Sitalakshmi
    2019 IEEE PUNE SECTION INTERNATIONAL CONFERENCE (PUNECON), 2019,
  • [35] The milling moments prediction using a neural network model
    Olteanu, Elena Luminiţa
    Ghencea, Daniel Petru
    Bîşu, Claudiu Florinel
    UPB Scientific Bulletin, Series D: Mechanical Engineering, 2015, 77 (04): : 141 - 150
  • [36] Traffic Sign Recognition Using a Multi-Task Convolutional Neural Network
    Luo, Hengliang
    Yang, Yi
    Tong, Bei
    Wu, Fuchao
    Fan, Bin
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2018, 19 (04) : 1100 - 1111
  • [37] Multi-task Deep Neural Network for Joint Face Recognition and Facial Attribute Prediction
    Wang, Zhanxiong
    He, Keke
    Fu, Yanwei
    Feng, Rui
    Jiang, Yu-Gang
    Xue, Xiangyang
    PROCEEDINGS OF THE 2017 ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL (ICMR'17), 2017, : 370 - 379
  • [38] Handwriting Prediction Based Character Recognition using Recurrent Neural Network
    Nishide, Shun
    Okuno, Hiroshi G.
    Ogata, Tetsuya
    Tani, Jun
    2011 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2011, : 2549 - 2554
  • [39] Multi-model Lightweight Action Recognition with Group-Shuffle Graph Convolutional Network
    Zhu, Suguo
    Zhan, Yibing
    Zhao, Guo
    ARTIFICIAL INTELLIGENCE, CICAI 2022, PT I, 2022, 13604 : 609 - 621
  • [40] The Prediction of Enterprise Stock Change Trend by Deep Neural Network Model
    Ma, Guifen
    Chen, Ping
    Liu, Zhaoshan
    Liu, Jia
    COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2022, 2022