Dual Convolutional LSTM Network for Referring Image Segmentation

被引:35
|
作者
Ye, Linwei [1 ]
Liu, Zhi [2 ,3 ]
Wang, Yang [1 ]
机构
[1] Univ Manitoba, Dept Comp Sci, Winnipeg, MB R3T 2N2, Canada
[2] Shanghai Univ, Shanghai Inst Adv Commun & Data Sci, Shanghai 200444, Peoples R China
[3] Shanghai Univ, Sch Commun & Informat Engn, Shanghai 200444, Peoples R China
基金
中国国家自然科学基金; 加拿大自然科学与工程研究理事会;
关键词
Image segmentation; Visualization; Decoding; Linguistics; Task analysis; Logic gates; Computer vision; Referring image segmentation; encoder-decoder; vision and language; deep learning;
D O I
10.1109/TMM.2020.2971171
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We consider referring image segmentation. It is a problem at the intersection of computer vision and natural language understanding. Given an input image and a referring expression in the form of a natural language sentence, the goal is to segment the object of interest in the image referred by the linguistic query. To this end, we propose a dual convolutional LSTM (ConvLSTM) network to tackle this problem. Our model consists of an encoder network and a decoder network, where ConvLSTM is used in both encoder and decoder networks to capture spatial and sequential information. The encoder network extracts visual and linguistic features for each word in the expression sentence, and adopts an attention mechanism to focus on words that are more informative in the multimodal interaction. The decoder network integrates the features generated by the encoder network at multiple levels as its input and produces the final precise segmentation mask. Experimental results on four challenging datasets demonstrate that the proposed network achieves superior segmentation performance compared with other state-of-the-art methods.
引用
收藏
页码:3224 / 3235
页数:12
相关论文
共 50 条
  • [1] Dual-graph hierarchical interaction network for referring image segmentation
    Shi, Zhaofeng
    Wu, Qingbo
    Li, Hongliang
    Meng, Fanman
    Ngan, King Ngi
    DISPLAYS, 2023, 80
  • [2] Structured Attention Network for Referring Image Segmentation
    Lin, Liang
    Yan, Pengxiang
    Xu, Xiaoqian
    Yang, Sibei
    Zeng, Kun
    Li, Guanbin
    IEEE TRANSACTIONS ON MULTIMEDIA, 2022, 24 : 1922 - 1932
  • [3] Dual Context Perception Transformer for Referring Image Segmentation
    Kong, Yuqiu
    Liu, Junhua
    Yao, Cuili
    PATTERN RECOGNITION AND COMPUTER VISION, PT V, PRCV 2024, 2025, 15035 : 216 - 230
  • [4] Cell image segmentation by using feedback and convolutional LSTM
    Shibuya, Eisuke
    Hotta, Kazuhiro
    VISUAL COMPUTER, 2022, 38 (11): : 3791 - 3801
  • [5] Cell image segmentation by using feedback and convolutional LSTM
    Eisuke Shibuya
    Kazuhiro Hotta
    The Visual Computer, 2022, 38 : 3791 - 3801
  • [6] Structured Multimodal Fusion Network for Referring Image Segmentation
    Xue, Mingcheng
    Liu, Yu
    Xu, Kaiping
    Zhang, Haiyang
    Yu, Chengyang
    PROCEEDINGS OF THE 2022 INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION, ICMI 2022, 2022, : 36 - 47
  • [7] Query Reconstruction Network for Referring Expression Image Segmentation
    Shi, Hengcan
    Li, Hongliang
    Wu, Qingbo
    Ngan, King Ngi
    IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 23 : 995 - 1007
  • [8] PRNet: A Progressive Refinement Network for referring image segmentation
    Liu, Jing
    Jiang, Huajie
    Hu, Yongli
    Yin, Baocai
    NEUROCOMPUTING, 2025, 630
  • [9] A CONTEXT-BASED NETWORK FOR REFERRING IMAGE SEGMENTATION
    Li, Xinyu
    Liu, Yu
    Xu, Kaiping
    Zhao, Zhehuan
    Liu, Sipei
    2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2020, : 1436 - 1440
  • [10] Bilateral Knowledge Interaction Network for Referring Image Segmentation
    Ding, Haixin
    Zhang, Shengchuan
    Wu, Qiong
    Yu, Songlin
    Hu, Jie
    Cao, Liujuan
    Ji, Rongrong
    IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 26 : 2966 - 2977