Computer vision has become increasingly important and effective in recent years due to its wide-ranging applications in areas as diverse as smart surveillance and monitoring, health and medicine, sports and recreation, robotics, drones, and self-driving cars. Visual recognition tasks, such as image classification, localization, and detection, are the core building blocks of many of these applications, and recent developments in Convolutional Neural Networks (CNNs) have led to outstanding performance in these state-of-the-art visual recognition tasks and systems. As a result, CNNs now form the crux of deep learning algorithms in computer vision. This self-contained guide will benefit those who seek to both understand the theory behind CNNs and to gain hands-on experience on the application of CNNs in computer vision. It provides a comprehensive introduction to CNNs starting with the essential concepts behind neural networks: training, regularization, and optimization of CNNs. The book also discuss...

Existing techniques for 3D action recognition are sensitive to viewpoint variations because they extract features from depth images which are viewpoint dependent. In contrast, we directly process point clouds for cross-view action recognition from unknown and unseen views. We propose the histogram of oriented principal components (HOPC) descriptor that is robust to noise, viewpoint, scale and action speed variations. At a 3D point, HOPC is computed by projecting the three scaled eigenvectors of the pointcloud within its local spatio-temporal support volume onto the vertices of a regular dodecahedron. HOPC is also used for the detection of spatiotemporal keypoints (STK) in 3D pointcloud sequences so that view-invariant STK descriptors (or Local HOPC descriptors) at these key locations only are used for action recognition. We also propose a global descriptor computed from the normalized spatio-temporal distribution of STKs in 4-D, which we refer to as STK-D. We have evaluated the performance of our proposed descriptors against nine existing techniques on two cross-view and three single-view human action recognition datasets. The experimental results show that our techniques provide significant improvement over state-of-the-art methods.

Recognizing human actions from unknown and unseen (novel) views is a challenging problem. We propose a Robust Non-Linear Knowledge Transfer Model (R-NKTM) for human action recognition from novel views. The proposed R-NKTM is a deep fully-connected neural network that transfers knowledge of human actions from any unknown view to a shared high-level virtual view by finding a set of non-linear transformations that connects the views. The R-NKTM is learned from 2D projections of dense trajectories of synthetic 3D human models fitted to real motion capture data and generalizes to real videos of human actions. The strength of our technique is that we learn a single R-NKTM for all actions and all viewpoints for knowledge transfer of any real human action video without the need for re-training or fine-tuning the model. Thus, R-NKTM can efficiently scale to incorporate new action classes. R-NKTM is learned with dummy labels and does not require knowledge of the camera viewpoint at any stage. Experiments on three benchmark cross-view human action datasets show that our method outperforms existing state-of-the-art.

We propose a human pose representation model that transfers human poses acquired from different unknown views to a view-invariant high-level space. The model is a deep convolutional neural network and requires a large corpus of multiview training data which is very expensive to acquire. Therefore, we propose a method to generate this data by fitting synthetic 3D human models to real motion capture data and rendering the human poses from numerous viewpoints. While learning the CNN model, we do not use action labels but only the pose labels after clustering all training poses into k clusters. The proposed model is able to generalize to real depth images of unseen poses without the need for re-training or fine-tuning. Real depth videos are passed through the model frame-wise to extract view-invariant features. For spatio-temporal representation, we propose group sparse Fourier Temporal Pyramid which robustly encodes the action specific most discriminative output features of the proposed human pose model. Experiments on two multiview and three single-view benchmark datasets show that the proposed method dramatically outperforms existing state-of-the-art in action recognition.

This paper concerns action recognition from unseen and unknown views. We propose unsupervised learning of a non-linear model that transfers knowledge from multiple views to a canonical view. The proposed Non-linear Knowledge Transfer Model (NKTM) is a deep network, with weight decay and sparsity constraints, which finds a shared high-level virtual path from videos captured from different unknown viewpoints to the same canonical view. The strength of our technique is that we learn a single NKTM for all actions and all camera viewing directions. Thus, NKTM does not require action labels during learning and knowledge of the camera viewpoints during training or testing. NKTM is learned once only from dense trajectories of synthetic points fitted to mocap data and then applied to real video data. Trajectories are coded with a general codebook learned from the same mocap data. NKTM is scalable to new action classes and training data as it does not require re-learning. Experiments on the IXMAS and N-UCLA datasets show that NKTM outperforms existing state-of-the-art methods for cross-view action recognition.