About This Special Issue

The big data era has brought with it new challenges to computer vision and image understanding. More scalable and robust methods are required to efficiently index, retrieve, organize and interact with big visual data. One can only think to the amount of image/video data downloaded every minute in social media or to the number of surveillance cameras installed in our cities nowadays. Both cases are not manageable without automatic or semi-automatic (e.g., human-in-the-loop) approaches capable of distill useful information from a large quantity of raw data. This special issue covers a wide range of topics, with a common denominator devoted to the analysis for understanding of images and videos. Some of these papers are extended versions of the best works presented at the International Conference on Image Analysis and Processing ICIAP 2015, held in Genova in September 2015

Computer Vision and Image Understanding
Volume 156, Pages 1-186 (March 2017)
Image and Video Understanding in Big Data
Edited by Vittorio Murino, Shaogang Gong, Chen Change Loy and Loris Bazzani


The issue is available electronically on Science Direct at the following link: http://www.sciencedirect.com/science/journal/10773142/156
The printed special issue will appear in Mar 2017.

Table of Contents

  1. Image and Video Understanding in Big Data
    Vittorio Murino, Shaogang Gong, Chen Change Loy, Loris Bazzani

  2. MEG: Texture Operators for Multi-Expert Gender Classification
    Modesto CastrilloĢn Santana, Maria De Marsico, Michele Nappi, Daniel Riccio

  3. Boosting Hankel Matrices for Face Emotion Recognition and Pain Detection
    Liliana Lo Presti, Marco La Cascia

  4. Social Profiling through Image Understanding: Personality Inference using Convolutional Neural Networks
    Cristina Segalin, Dong Seon Cheng, Marco Cristani

  5. Structured Learning of Metric Ensembles with Application to Person Re-Identification
    Sakrapee Paisitkriangkrai, Lin Wu, Chunhua Shen, Anton van den Hengel

  6. Continuous Adaptation of Multi-Camera Person Identification Models through Sparse Non-redundant Representative Selection
    Abir Das, Rameswar Panda, Amit K Roy-Chowdhury

  7. A Bag-of-Words Equivalent Recurrent Neural Network for Action Recognition
    Alexander Richard, Juergen Gall

  8. Improved Scene Identification and Object Detection on Egocentric Vision of Daily Activities
    Gonzalo Vaca-Castano, Samarjit Das, Joao P Sousa, Niels D. Lobo, Mubarak Shah

  9. Fast Action Retrieval from Videos via Feature Disaggregation
    Jie Qin, Li Liu, Mengyang Yu, Yunhong Wang, Ling Shao

  10. Detecting Anomalous Events in Videos by Learning Deep Representations of Appearance and Motion
    Dan Xu, Yan Yan, Elisa Ricci, Nicu Sebe

  11. Deep Active Object Recognition by Joint Label and Action Prediction
    Mohsen Malmir, Karan Sikka, Deborah Forster, Ian Fasel, Javier R Movellan, Garrison W Cottrell

  12. Weak Supervision for Detecting Object Classes from Activities
    Abhilash Srikantha, Juergen Gall

  13. Efficient Large-Scale Multi-Class Image Classification By Learning Balanced Trees
    Tien-Dung Mai, Thanh Duc Ngo, Duy-Dinh Le, Duc Anh Duong, Kiem Hoang, Shin'ichi Satoh

  14. Online Supervised Hashing
    Fatih Cakir, Sarah A Bargal, Stan Sclaroff

  15. Scalable Greedy Algorithms for Transfer Learning
    Ilja Kuzborskij, Francesco Orabona, Barbara Caputo

Guest Editors

Vittorio Murino, Istituto Italiano di Tecnologia, Genova/University of Verona, Verona, Italy
Shaogang Gong, Queen Mary University of London, UK
Chen Change Loy, The Chinese University of Hong Kong, China
Loris Bazzani