Collaborative Image Understanding

被引:0
|
作者
Bibas, Koby [1 ]
Shalom, Oren Sar [2 ]
Jannach, Dietmar [3 ]
机构
[1] Meta, Tel Aviv, Israel
[2] Amazon, Tel Aviv, Israel
[3] Univ Klagenfurt, Klagenfurt, Austria
关键词
Information Extraction; Image Categorization; Collaborative Filtering; Multitask Learning; AUTOENCODER;
D O I
10.1145/3511808.3557260
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Automatically understanding the contents of an image is a highly relevant problem in practice. In e-commerce and social media settings, for example, a common problem is to automatically categorize user-provided pictures. Nowadays, a standard approach is to fine-tune pre-trained image models with application-specific data. Besides images, organizations however often also collect collaborative signals in the context of their application, in particular how users interacted with the provided online content, e.g., in forms of viewing, rating, or tagging. Such signals are commonly used for item recommendation, typically by deriving latent user and item representations from the data. In this work, we show that such collaborative information can be leveraged to improve the classification process of new images. Specifically, we propose a multitask learning framework, where the auxiliary task is to reconstruct collaborative latent item representations. A series of experiments on datasets from e-commerce and social media demonstrates that considering collaborative signals helps to significantly improve the performance of the main task of image classification by up to 9.1%.
引用
收藏
页码:77 / 87
页数:11
相关论文
共 50 条
  • [1] Deep Collaborative Embedding for Social Image Understanding
    Li, Zechao
    Tang, Jinhui
    Mei, Tao
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2019, 41 (09) : 2070 - 2083
  • [2] Understanding the image in the digital culture: The quest for an interdisciplinary and collaborative education
    Madrazo, L
    ED-MEDIA 2004: WORLD CONFERENCE ON EDUCATIONAL MULTIMEDIA, HYPERMEDIA & TELECOMMUNICATIONS, VOLS. 1-7, 2004, : 1487 - 1494
  • [3] Understanding the collaborative workspaces
    Gautier, Gilles
    Piddington, Colin
    Fernando, Terrence
    ENTERPRISE INTEROPERABILITY III: NEW CHALLENGES AND INDUSTRIAL APPROACHES, 2008, : 99 - 111
  • [4] Shared understanding for collaborative control
    Bruemmer, DJ
    Few, DA
    Boring, RL
    Marble, JL
    Walton, MC
    Nielsen, CW
    IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART A-SYSTEMS AND HUMANS, 2005, 35 (04): : 494 - 504
  • [5] Image Understanding
    Haindl, Michal
    Kittler, Josef
    ERCIM NEWS, 2013, (95): : 9 - 9
  • [6] Collaborative Personalization of Image Enhancement
    Kapoor, Ashish
    Caicedo, Juan C.
    Lischinski, Dani
    Kang, Sing Bing
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2014, 108 (1-2) : 148 - 164
  • [7] Collaborative Personalization of Image Enhancement
    Caicedo, Juan C.
    Kapoor, Ashish
    Kang, Sing Bing
    2011 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2011, : 249 - 256
  • [8] Collaborative Personalization of Image Enhancement
    Ashish Kapoor
    Juan C. Caicedo
    Dani Lischinski
    Sing Bing Kang
    International Journal of Computer Vision, 2014, 108 : 148 - 164
  • [9] Solving diverse image understanding problems using the image understanding environment
    Dolan, J
    Kohl, C
    Lerner, R
    Mundy, J
    Boult, T
    Beveridge, JR
    IMAGE UNDERSTANDING WORKSHOP, 1996 PROCEEDINGS, VOLS I AND II, 1996, : 1481 - 1504
  • [10] DRIVER - A platform for collaborative framework understanding
    Flores, Nuno
    Aguiar, Ademar
    2015 30TH IEEE/ACM INTERNATIONAL CONFERENCE ON AUTOMATED SOFTWARE ENGINEERING (ASE), 2015, : 783 - 788