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
  • [1] Pedestrian Attributes Recognition in Surveillance Scenarios Using Multi-Task Lightweight Convolutional Neural Network
    Yan, Pu
    Zhuo, Li
    Li, Jiafeng
    Zhang, Hui
    Zhang, Jing
    APPLIED SCIENCES-BASEL, 2019, 9 (19):
  • [2] Recipe prediction of melange yarn using modular artificial neural network
    Yang, Ying
    Ma, Hui
    Yang, Qun
    Zhang, Chi
    Shen, Jiajia
    JOURNAL OF THE TEXTILE INSTITUTE, 2018, 109 (05) : 629 - 635
  • [3] Prediction Model for Mechanical Properties of Lightweight Aggregate Concrete Using Artificial Neural Network
    Yoon, Jin Young
    Kim, Hyunjun
    Lee, Young-Joo
    Sim, Sung-Han
    MATERIALS, 2019, 12 (17)
  • [4] Brain Age Prediction Using a Lightweight Convolutional Neural Network
    Eltashani, Fatma
    Parreno-Centeno, Mario
    Cole, James H.
    Papa, Joao Paulo
    Costen, Fumie
    IEEE ACCESS, 2025, 13 : 6750 - 6763
  • [5] Recipe prediction in textile coloration using artificial neural network and fuzzy logic
    Chakraborty, J.N.
    Ravi
    Shivangi
    Vanshika
    Vishal
    Asian Textile Journal, 2019, 28 (03): : 62 - 66
  • [6] Fast and Lightweight Automatic Modulation Recognition using Spiking Neural Network
    Lin, Canghai
    Zhang, ZhiJiao
    Wang, Lei
    Wang, Yao
    Zhao, Jingyue
    Yang, Zhijie
    Xiao, Xun
    2024 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, ISCAS 2024, 2024,
  • [7] LIMUNet: A Lightweight Neural Network for Human Activity Recognition Using Smartwatches
    Lin, Liangliang
    Wu, Junjie
    An, Ran
    Ma, Song
    Zhao, Kun
    Ding, Han
    APPLIED SCIENCES-BASEL, 2024, 14 (22):
  • [8] A Lightweight Graph Neural Network Algorithm for Action Recognition Based on Self-Distillation
    Feng, Miao
    Meunier, Jean
    ALGORITHMS, 2023, 16 (12)
  • [9] Underwater target recognition using a lightweight asymmetric convolutional neural network
    Yan, Chenhong
    Yao, Tianyi
    Yu, Yang
    Yang, Changsheng
    Liu, Lu
    Pan, Guang
    Yan, Shefeng
    17TH ACM INTERNATIONAL CONFERENCE ON UNDERWATER NETWORKS & SYSTEMS, WUWNET 2023, 2024,
  • [10] Hybrid deep neural network model for human action recognition
    Ijjina, Earnest Paul
    Mohan, Chalavadi Krishna
    APPLIED SOFT COMPUTING, 2016, 46 : 936 - 952