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
  • [21] Recognition Method and Application of Wild Vegetables based on Lightweight Convolutional Neural Network Model
    Wang, Bingbing
    Gao, Wanlin
    Yang, Bangjie
    Journal of Network Intelligence, 2022, 7 (02): : 347 - 364
  • [22] Lane Change Prediction With an Echo State Network and Recurrent Neural Network in the Urban Area
    Griesbach, Karoline
    Beggiato, Matthias
    Hoffmann, Karl Heinz
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 23 (07) : 6473 - 6479
  • [23] Finger spelling recognition using neural network with pattern recognition model
    Shimada, M
    Iwasaki, S
    Asakura, T
    SICE 2003 ANNUAL CONFERENCE, VOLS 1-3, 2003, : 2458 - 2463
  • [24] Colour recipe prediction in dyeing acrylic fabrics with fluorescent dyes using artificial neural network
    Sennaroglu, Bahar
    Oner, Erhan
    Senvar, Ozlem
    INDUSTRIA TEXTILA, 2014, 65 (01): : 22 - 28
  • [25] Lane change trajectory prediction using artificial neural network
    Tomar, R.S. (rs63@iiita.ac.in), 1600, Inderscience Enterprises Ltd., 29, route de Pre-Bois, Case Postale 856, CH-1215 Geneva 15, CH-1215, Switzerland (06):
  • [26] Action Recognition in Still Images using Residual Neural Network Features
    Sreela, S. R.
    Idicula, Sumam Mary
    8TH INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING & COMMUNICATIONS (ICACC-2018), 2018, 143 : 563 - 569
  • [27] Neural activity and network analysis for understanding reasoning using the matrix reasoning task
    M. M. Caudle
    A. D. Spadoni
    D. M. Schiehser
    A. N. Simmons
    J. Bomyea
    Cognitive Processing, 2023, 24 : 585 - 594
  • [28] Neural activity and network analysis for understanding reasoning using the matrix reasoning task
    Caudle, M. M.
    Spadoni, A. D.
    Schiehser, D. M.
    Simmons, A. N.
    Bomyea, J.
    COGNITIVE PROCESSING, 2023, 24 (04) : 585 - 594
  • [29] A Lightweight Neural Network Model for Disease Risk Prediction in Edge Intelligent Computing Architecture
    Zhou, Feng
    Hu, Shijing
    Du, Xin
    Wan, Xiaoli
    Wu, Jie
    FUTURE INTERNET, 2024, 16 (03)
  • [30] Basic Activity Recognition from Wearable Sensors Using a Lightweight Deep Neural Network
    Benhaili Z.
    Abouqora Y.
    Balouki Y.
    Moumoun L.
    Journal of ICT Standardization, 2022, 10 (02): : 241 - 260