Search Results

• A trainable RNN based pooling method is proposed.
• CNNs are turned into fully ...

Pooling is an important component in convolutional neural networks (CNNs) for aggregating features and reducing computational burden. Compared with other components such as convolutional layers and fully connected layers which are ...

This article takes a problem-oriented perspective and presents a comprehensive review of transfer-learning methods, both shallow and deep, for cross-dataset visual recognition. Specifically, it categorises the cross-dataset recognition into 17 problems ...

Convolutional Neural Networks (ConvNets) have recently shown promising performance in many computer vision tasks, especially image-based recognition. How to effectively apply ConvNets to sequence-based data is still an open problem. ...

Human activity recognition based on the smartphone sensors has the potential to impact a wide range of applications such as healthcare, smart home, and remote monitoring. For simple activities like "Sit" and "Walk", it can be distinguished relatively ...

Unsupervised feature selection has become an important and challenging pre-processing step in machine learning and data mining since large amount of unlabelled high dimensional data are often required to be processed. In this paper, we ...

A novel deep neural network training paradigm that exploits the conjoint information in multiple heterogeneous sources is proposed. Specifically, in a RGB-D based action recognition task, it cooperatively trains a single convolutional neural network (...

A novel semantic representation, pose lexicon, is proposed for action recognition.An extended hidden Markov alignment model is developed to learn a pose lexicon.A semantic action recognition method that is capable of zero-shot recognition is developed ...

Foreground detection has been widely studied for decades due to its importance in many practical applications. Most of the existing methods assume foreground and background show visually distinct characteristics and thus the foreground can be detected ...

Stereo matching algorithms attempt to estimate depth from the images obtained by two cameras. In most cases, the arrangement of cameras (their locations and orientations with respect to the scene) is determined based on human experience. In this paper, ...

This paper presents a novel and effective edge-preserving image smoothing method for edge-aware image manipulation. The method formulates the smoothing as a problem of minimizing a convex object function with a constraint and an efficient solution to ...

Human action recognition from RGB-D (Red, Green, Blue and Depth) data has attracted increasing attention since the first work reported in 2010. Over this period, many benchmark datasets have been created to facilitate the development and evaluation of ...

Project-based learning is a widely used pedagogical strategy in engineering education shown to be effective in fostering problem-solving, design, and teamwork skills. There are distinct benefits to be gained from giving students autonomy in determining ...

Recently, Convolutional Neural Networks (ConvNets) have shown promising performances in many computer vision tasks, especially image-based recognition. How to effectively use ConvNets for video-based recognition is still an open problem. In this paper, ...

The ability to recognize human actions using a single viewpoint is affected by phenomena such as self-occlusions or occlusions by other objects. Incorporating multiple cameras can help overcome these issues. However, the question remains how to ...

We consider the problem of learning a structured and discriminative dictionary based on sparse representation for classification task. The structure comprises class-shared and class-specific partitions which allows the separation of common and class-...

The problem of human detection is to automatically locate people in an image or video sequence and has been actively researched in the past decade. This paper aims to provide a comprehensive survey on the recent development and challenges of human ...

Covariance matrix has recently received increasing attention in computer vision by leveraging Riemannian geometry of symmetric positive-definite (SPD) matrices. Originally proposed as a region descriptor, it has now been used as a generic representation ...

In this paper, we propose to adopt ConvNets to recognize human actions from depth maps on relatively small datasets based on Depth Motion Maps (DMMs). In particular, three strategies are developed to effectively leverage the capability of ConvNets in ...

In a light field-based free viewpoint video (LF-based FVV) system, effective sampling density (ESD) is defined as the number of rays per unit area of the scene that has been acquired and is selected in the rendering process for reconstructing an unknown ...