Call for Papers: IEEE TPAMI Special Issue

Call for Papers


IEEE Transactions on Pattern Analysis and Machine Intelligence Special Issue on Compact and Efficient Feature Representation and Learning in Computer Vision



Feature representation is at the core of many computer vision problems such as image classification, object detection and recognition, object tracking, image and video retrieval, image matching and many others. The rapidly developing field of feature representation is concerned with questions surrounding how we can best seek meaningful and useful features that can support effective machine learning. In the past two decades we have witnessed remarkable progress in feature representation and learning, starting from Scale Invariant Feature Transform (SIFT) feature entering the scene and evolving to deep learning based features dominating the computer vision field today. For years, milestone handcrafted feature descriptors such as SIFT, Speeded Up Robust Features (SURF), Histogram of Oriented Gradients (HOG) and Local Binary Pattern (LBP) have dominated various domains of computer vision until the turning point in 2012 when Deep Convolutional Neural Networks (DCNN) achieved a record breaking image classification result. Handcrafted features are not data adaptive and usually labor intensive. DCNN is a hierarchical structure that attempts to learn representations of data with multiple levels of abstraction automatically. However, it is a common belief that existing DCNN based features often rely on computationally expensive deep models, which are very slow for numerous applications.


Nowadays, featuring exponentially increasing amount of images and videos, the emerging phenomenon of big dimensionality (millions of dimensions and above) renders the inadequacies of existing approaches, no matter traditional handcrafted features or recent deep learning based ones. There is thus a pressing need for new scalable and efficient approaches that can cope with this explosion of dimensionality. In addition, with the prevalence of social media networks and portable/mobile/wearable devices which have limited computational capabilities and storage space, the demands for sophisticated portable/mobile/wearable device applications in handling large-scale visual data is rising. In such applications, real time performance is of utmost importance to users, since no one is willing to spend any time waiting nowadays. Therefore, there is a growing need for feature descriptors that are fast to compute, memory efficient, and yet exhibiting good discriminability and robustness.


We encourage researchers to study and develop new compact and efficient feature representations that are fast to compute, memory efficient, and yet exhibiting good discriminability and robustness. We also encourage new theories and applications related to features for dealing with these challenges. We invite paper submissions for a special issue on Compact and Efficient Feature Representation and Learning in Computer Vision to be published in IEEE TPAMI. Original research papers as well as overview and survey papers are welcome, on topics including, but not limited to:


·       Large-scale applications oriented new features

·       Hashing/binary codes and its related applications

·       Efficient neural network design

·       Compact and efficient feature selection

·       Fast features that are suitable for wearable/mobile devices

·       Big dimensionality oriented dimension reduction and feature selection

·       Sparse dictionary coding and its related applications

·       Evaluations of current handcrafted descriptors and deep learning based features

·       Methods to make deep networks/features/detectors practical such as network compression/quantization/binarization.

·       Other applications such as robotics and medical image analysis

·       Other novel application domains



Priority will be given to papers with high novelty and originality for research papers, and to papers with high potential impact for survey/overview papers.



Paper submission and review:


Authors need to submit full papers online through the TPAMI site at,

selecting the choice that indicates this special issue. Peer reviewing will follow the standard IEEE review process. Full length manuscripts are expected to follow the TPAMI guidelines in



Time line:


Submission of full papers: January 15, 2018.

First reviews: May 15, 2018. (Most submissions have received their first round comments. Several submissions will receive their decisions as soon as possible.)

Revisions due: July 15, 2018.

Decisions announced: September 15, 2018.

Final manuscripts due: October 15, 2018.



Guest editors


·       Li Liu, National University of Defense Technology, China,

University of Oulu, Finland

·       Matti Pietikäinen, University of Oulu, Finland,

·       Jie Chen, University of Oulu, Finland,

·       Guoying Zhao, University of Oulu, Finland,

·       Xiaogang Wang, The Chinese University of Hong Kong, China,

·       Rama Chellappa, University of Maryland, USA,





Li Liu

Email: ,

National University of Defense Technology, China

Center for Machine Vision and Signal Analysis (CMVS),
University of Oulu, Finland



Any question about this page? Turn to its host!

This page is maintained currently by Li Liu. Last modified: 2017 June 4