/awesome-image-tagging

A paper list of awesome Image Tagging

Awesome-Image-Tagging

A paper list of awesome Image Tagging I've read

Image Tagging (Multi-label Image Classification)

Describe an image using tags. Tags can be objects, situation, and user generated tags.

  • WARP

    • Deep Convolutional Ranking for Multilabel Image Annotation [paper]
      Y Gong, Y Jia, T Leung, A Toshev, S loffe
      arXiv:1312.4894
    • propose WARP loss for multi-label image annotation.

  • CNN-RNN

    • CNN-RNN: A Unified Framework for Multi-Label Image Classification [paper]
      J Wang, Y Yang, J Mao, Z Huang, C Huang, W Xu
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
    • utilize RNN combined with CNN to learn a joint image-label embedding to characterize the semantic label dependency as well as the image-label relevance.

  • S-CNN-RNN

    • Semantic Regularisation for Recurrent Image Annotation [paper]
      F Liu, T Xiang, TM Hospedales, W Yang, C Sun
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
    • using a semantically regularised embedding layer as the interface between the CNN and RNN. simple modification to CNN-RNN?

  • Multi-label Triplet Embeddings

    • Multi-label Triplet Embeddings for Image Annotation from User-Generated Tags [paper]
      Z Seymour, ZM Zhang
      ACM International Conference on Multimedia Retrieval (ICMR), 2018

  • Knowledge Distillation from Weakly-Supervised Detection

    • Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection [paper]
      Yongcheng Liu, Lu Sheng, Jing Shao, Junjie Yan, Shiming Xiang, Chunhong Pan
      ACM International Conference on Multimedia (ACM MM), 2018

  • Multi-Modal Multi-Scale Deep Learning for Large-Scale Image Annotation

    • Multi-Modal Multi-Scale Deep Learning for Large-Scale Image Annotation [paper]
      Yulei Niu, Zhiwu Lu, Ji-Rong Wen, Tao Xiang, Shih-Fu Chang
      IEEE Transactions on Image Processing (TIP), 2019
    • using noisy tags + label quantity prediction network

  • Attend and Imagine

    • Attend and Imagine: Multi-label Image Classification with Visual Attention and Recurrent Neural Networks [paper]
      Fan Lyu, Qi Wu, Fuyuan Hu, Qingyao Wu, Mingkui Tan
      IEEE Transactions on Multimedia, 2019
    • Attention + RNN

Zero-shot Image Tagging

Annotate an image by unseen tags. It means 'unseen at the training stage'.

  • HierSE

    • Zero-shot Image Tagging by Hierarchical Semantic Embedding [paper]
      X Li, S Liao, W Lan, X Du, G Yang
      38th Annual ACM SIGIR Conference on Research & Development on Information Retrieval (SIGIR), 2015

  • Fast0Tag

    • Fast Zero-shot Image Tagging [paper]
      Y Zhang, B Gong, M Shah
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016

  • Deep Multiple Instance Learning

    • Deep Multiple Instance Learning for Zero-shot Image Tagging [paper]
      S Rahman, S Khan
      15th European Conference on Computer Vision (ECCV), 2018

Diverse Image Annotation

Describe an image using a limited numbers of tags, whereby the retrieved tags need to cover as much useful information about the image as possible. (by Diverse Image Annotation, CVPR 2017)

  • DIA
    • Diverse Image Annotation [paper]
      B Wu, F Jia, W Liu, B Ghanem
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
  • D2IA-GAN
    • Tagging like humans : Diverse and Distinct Image Annotation [paper]
      B Wu, W Chen, P Sun, W Liu, B Ghanem, S Lyu
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018

CVPR 2019 Accepted Paper List

I am so excited to read awesome CVPR 2019 aceepted papers about Image Tagging. Also, it is surprising that many papers on Image Tagging has accepted this year.

  • Weakly Supverised Deep Image Hashing through Tag Embeddings

    • Weakly Supervised Deep Image Hashing through Tag Embeddings [paper]
      Vijetha Gattupalli, Yaoxin Zhuo, Baoxin Li
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019

  • Metatdata Neighbourhood Graph Co-Attention Networks

  • Graph Convolutional Networks (GCN)

    • Multi-Label Image Recognition with Graph Convolutional Networks [paper]
      Zhao-Min Chen, Xiu-Shen Wei, Peng Wang, Yanwen Guo
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019

  • Learning with Partial Labels + Graph Neural Network (GNN)

    • Learning a Deep ConvNet for Multi-label Classification with Partial Labels [paper]
      Thibaut Durand, Nazanin Mehrasa, Greg Mori
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019

  • Visual Attention Consistency under Image Transforms

    • Visual Attention Consistency under Image Transforms for Multi-label Image Classification [paper]
      Hao Guo, Kang Zheng, Xiaochuan Fan, Hongkai Yu, Song Wang
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019

  • LaSO(Label-Set Operations networks) : few-shot learning (oral paper)

    • LaSO: Label-Set Operations networks for multi-label few-shot learning [paper]
      Amit Alfassy, Leonid Karlinsky, Ami Aides, Joseph Shtok, Sivan Harary, Rogerio Feris, Raja Giryes, Alex M. Bronstein
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019

ICCV 2019 Accepted Paper List

[accepted paper list]

  • Learning Semantic-Specific Graph Representation
    • Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition [paper]
      Tianshui Chen, Muxin Xu, Xiaolu Hui, Hefeng Wu, Liang Lin
      In Proceedings of IEEE International Conference on Computer Vision (ICCV), 2019

Notice

This repository is just made for my own studying, so there may be incorrect information.
Also, I regard 'image tagging', 'image annotation', 'multi-label image classification' as same task (actually may be little bit different) in this repository.

I'd appreciate it if everybody could reccommend me image tagging paper that I can read.
 현재는 이 쪽 분야의 paper를 read up 하고 있지는 않지만, ICCV 2019 paper까지는 올려보고자 합니다.
Thank you!

Email: kabbi159@gmail.com