Stan Z. Li

Bio: Stan Z. Li is an academic researcher from Westlake University. The author has contributed to research in topics: Facial recognition system & Face detection. The author has an hindex of 97, co-authored 532 publications receiving 41793 citations. Previous affiliations of Stan Z. Li include Microsoft & Macau University of Science and Technology.

Facial expression recognition from near-infrared video sequences

Abstract: Facial expressions can be thought as specific dynamic textures where local appearance and motion information need to be taken into account. We utilize local spatiotemporal operators to describe facial expressions. All current facial expression recognition databases are captured in visible light spectrum. Visual light usually changes with locations, and can also vary with time, which can cause significant variations in image appearance and texture. In this paper, we present a novel research on a dynamic facial expression recognition from near-infrared (NIR) video sequences. NIR imaging is robust with respect to illumination changes. Experiments on a new NIR database show promising and robust results against illumination variations.

Exploring Structural Information and Fusing Multiple Features for Person Re-identification

Abstract: Recently, methods with learning procedure have been widely used to solve person re-identification (re-id) problem. However, most existing databases for re-id are smallscale, therefore, over-fitting is likely to occur. To further improve the performance, we propose a novel method by fusing multiple local features and exploring their structural information on different levels. The proposed method is called Structural Constraints Enhanced Feature Accumulation (SCEFA). Three local features (i.e., Hierarchical Weighted Histograms (HWH), Gabor Ternary Pattern HSV (GTP-HSV), Maximally Stable Color Regions (MSCR)) are used. Structural information of these features are deeply explored in three levels: pixel, blob, and part. The matching algorithms corresponding to the features are also discussed. Extensive experiments conducted on three datasets: VIPeR, ETHZ and our own challenging dataset MCSSH, show that our approach outperforms stat-of-the-art methods significantly.

Face Image Quality Evaluation for ISO/IEC Standards 19794-5 and 29794-5

Abstract: Face recognition performance can be significantly influenced by face image quality. The approved ISO/IEC standard 19794-5 has specified recommendations for face photo taking for E-passport and related applications. Standardization of face image quality, ISO/IEC 29794-5, is in progress. Bad illumination, facial pose and out-of-focus are among main reasons that disqualify a face image sample. This paper presents several algorithms for face image quality assessment. Illumination conditions and facial pose are evaluated in terms of facial symmetry, and implemented based on Gabor wavelet features. Assessment of camera focus is done based on discrete cosine transform (DCT). These methods are validated by experiments.

Structured visual tracking with dynamic graph

Abstract: Structure information has been increasingly incorporated into computer vision field, whereas only a few tracking methods have employed the inner structure of the target. In this paper, we introduce a dynamic graph with pairwise Markov property to model the structure information between the inner parts of the target. The target tracking is viewed as tracking a dynamic undirected graph whose nodes are the target parts and edges are the interactions between parts. These target parts within the graph waiting for matching are separated from the background with graph cut, and a spectral matching technique is exploited to accomplish the graph tracking. With the help of an intuitive updating mechanism, our dynamic graph can robustly adapt to the variations of target structure. Experimental results demonstrate that our structured tracker outperforms several state-of-the-art trackers in occlusion and structure deformations.

Real-time face detection using boosting in hierarchical feature spaces

Abstract: Boosting-based methods have recently led to the state-of-the-art-face detection systems. In these systems, weak classifiers to be boosted are based on simple, local, Haar-like features. However, it can be empirically observed that in later stages of the boosting process, the non-face examples collected by bootstrapping become very similar to the face examples, and the classification error of Haar-like feature based weak classifiers is thus very close to 50%. As a result, the performance of a face detector cannot be further improved. This paper proposed a solution to this problem, introducing a face detection method based on boosting in hierarchical feature spaces (both local and global). We argue that global features, like those derived from principal component analysis, can be advantageously used in the later stages of boosting, when local features do not provide any further benefit. We show that weak classifiers learned in hierarchical feature spaces are better boosted. Our methodology leads to a face detection system that achieves higher performance than a current state-of-the-art system, at a comparable speed.

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

Abstract: 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.

Machine learning

Abstract: 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.).

Pattern Recognition and Machine Learning

Abstract: 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.

Robust Face Recognition via Sparse Representation

Abstract: 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.

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

Abstract: 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.