We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background. Finally, YOLO learns very general representations of objects. It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.

/pdf/you-only-look-once-unified-real-time-object-detection-3gan6roe1o.pdf

You Only Look Once: Unified, Real-Time Object Detection

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

We consider the problem of automatically recognizing human faces from frontal views with varying expression and illumination, as well as occlusion and disguise. We cast the recognition problem as one of classifying among multiple linear regression models and argue that new theory from sparse signal representation offers the key to addressing this problem. Based on a sparse representation computed by C1-minimization, we propose a general classification algorithm for (image-based) object recognition. This new framework provides new insights into two crucial issues in face recognition: feature extraction and robustness to occlusion. For feature extraction, we show that if sparsity in the recognition problem is properly harnessed, the choice of features is no longer critical. What is critical, however, is whether the number of features is sufficiently large and whether the sparse representation is correctly computed. Unconventional features such as downsampled images and random projections perform just as well as conventional features such as eigenfaces and Laplacianfaces, as long as the dimension of the feature space surpasses certain threshold, predicted by the theory of sparse representation. This framework can handle errors due to occlusion and corruption uniformly by exploiting the fact that these errors are often sparse with respect to the standard (pixel) basis. The theory of sparse representation helps predict how much occlusion the recognition algorithm can handle and how to choose the training images to maximize robustness to occlusion. We conduct extensive experiments on publicly available databases to verify the efficacy of the proposed algorithm and corroborate the above claims.

/pdf/robust-face-recognition-via-sparse-representation-4bfqv6y74o.pdf

Robust Face Recognition via Sparse Representation

Computational single-cell RNA-seq (scRNA-seq) methods have been successfully applied to experiments representing a single condition, technology, or species to discover and define cellular phenotypes. However, identifying subpopulations of cells that are present across multiple data sets remains challenging. Here, we introduce an analytical strategy for integrating scRNA-seq data sets based on common sources of variation, enabling the identification of shared populations across data sets and downstream comparative analysis. We apply this approach, implemented in our R toolkit Seurat (http://satijalab.org/seurat/), to align scRNA-seq data sets of peripheral blood mononuclear cells under resting and stimulated conditions, hematopoietic progenitors sequenced using two profiling technologies, and pancreatic cell 'atlases' generated from human and mouse islets. In each case, we learn distinct or transitional cell states jointly across data sets, while boosting statistical power through integrated analysis. Our approach facilitates general comparisons of scRNA-seq data sets, potentially deepening our understanding of how distinct cell states respond to perturbation, disease, and evolution.

/pdf/integrating-single-cell-transcriptomic-data-across-different-3dtsi5w7ob.pdf

Integrating single-cell transcriptomic data across different conditions, technologies, and species.

With the wide applications of face recognition, spoofing attack is becoming a big threat to their security Conventional face recognition systems usually adopt behavioral challenge-response or texture analysis methods to resist spoofing attacks, however, these methods require high user cooperation and are sensitive to the imaging quality and environments In this chapter, we present a multi-spectral face recognition system working in VIS (Visible) and NIR (Near Infrared) spectrums, which is robust to various spoofing attacks and user cooperation free First, we introduce the structure of the system from several aspects including: imaging device, face landmarking, feature extraction, matching, VIS, and NIR sub-systems Then the performance of the multi-spectral system and each subsystem is evaluated and analyzed Finally, we describe the multi-spectral image-based anti-spoofing module, and report its performance under photo attacks Experiments on a spoofing database show the excellent performance of the proposed system both in recognition rate and anti-spoofing ability Compared with conventional VIS face recognition system, the multi-spectral system has two advantages: (1) By combining the VIS and NIR spectrums, the system can resist VIS photo and NIR photo attacks easily And users’ cooperation is no longer needed, making the system user friendly and fast (2) Due to the precise key-point localization, Gabor feature extraction and unsupervised learning, the system is robust to pose, illumination and expression variations Generally, its recognition rate is higher than the VIS subsystem

Face Anti-spoofing: Multi-spectral Approach

Faces under varying illumination, pose and non-rigid deformation are empirically thought of as a highly nonlinear manifold in the observation space. How to discover intrinsic low-dimensional manifold is important to characterize meaningful face distributions and classify them using a simpler, such as linear or Gaussian based, classifier. In this paper, we present a manifold learning algorithm (MLA) for learning a mapping from highly-dimensional manifold into the intrinsic low-dimensional linear manifold. We also propose the nearest manifold (NM) criterion for the classification and present an algorithm for computing the distance from the sample to be classified to the nearest face manifolds in light of local linearity of manifold. Based on these works, face recognition is achieved with the combination of MLA and NM. Experiments on several face databases show that the advantages of our proposed combinational approach.

/pdf/nearest-manifold-approach-for-face-recognition-4kc7hsjy5n.pdf

Nearest manifold approach for face recognition

Fast and accurate segmentation of moving objects in video sequences is a basic task in many computer vision and video analysis applications. It has a critical impact on the performance of object tracking and classification and activity analysis. This paper presents effective methods for solving this problem. Firstly, a fast and efficient algorithm is presented for background update to handle various sources of scene changes, including ghosts, left objects, camera shaking, and abrupt illumination changes. This is done by analyzing properties of object motion in image pixels and temporal frames, and combining both levels of constraints. Moreover, the algorithm does not need training sequence. Secondly, a real-time and accurate moving object segmentation algorithm is presented for moving object localization. Here, a novel filtering method is presented based on multiple scale and fast connected blob extraction. An intelligent video surveillance system is developed to test the performance of the algorithms. Experiments are performed using long video sequences under different conditions indoor and outdoor. The results show that the proposed algorithm is effective and efficient in real-time and accurate background update and moving object segmentation.

http://www.cbsr.ia.ac.cn/Li%20Group/papers/YangTao-VSSN2004.pdf

Real-time and accurate segmentation of moving objects in dynamic scene

Robust descriptor-based subspace learning with complex data is an active topic in pattern analysis and machine intelligence. A few researches concentrate the optimal design on feature representation and metric learning. However, traditionally used features of single-type, e.g., image gradient orientations (IGOs), are deficient to characterize the complete variations in robust and discriminant subspace learning. Meanwhile, discontinuity in edge alignment and feature match are not been carefully treated in the literature. In this paper, local order constrained IGOs are exploited to generate robust features. As the difference-based filters explicitly consider the local contrasts within neighboring pixel points, the proposed features enhance the local textures and the order-based coding ability, thus discover intrinsic structure of facial images further. The multimodal features are automatically fused in the most discriminant subspace. The utilization of adaptive interaction function suppresses outliers in each dimension for robust similarity measurement and discriminant analysis. The sparsity-driven regression model is modified to adapt the classification issue of the compact feature representation. Extensive experiments are conducted by using some benchmark face data sets, e.g., of controlled and uncontrolled environments, to evaluate our new algorithm.

Enhanced Local Gradient Order Features and Discriminant Analysis for Face Recognition

We present a novel approach for human gait recognition that inherently combines appearance and motion. Dynamic texture descriptors, Local Binary Patterns from Three Orthogonal Planes (LBP-TOP), are used to describe human gait in a spatiotemporal way. We also propose a new coding of multiresolution uniform Local Binary Patterns and use it in the construction of spatiotemporal LBP histograms. We show the suitability of the representation for gait recognition and test our method on a popular CMU MoBo dataset. We then compare our result to the state of the art methods.

/pdf/dynamic-texture-based-gait-recognition-45skjwbkrb.pdf

Stan Z. Li

Papers

Face Anti-spoofing: Multi-spectral Approach

Nearest manifold approach for face recognition

Real-time and accurate segmentation of moving objects in dynamic scene

Enhanced Local Gradient Order Features and Discriminant Analysis for Face Recognition

Dynamic Texture Based Gait Recognition