Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also present experiments that provide insight into what the network learns, revealing a rich hierarchy of image features. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn.

/pdf/rich-feature-hierarchies-for-accurate-object-detection-and-22fvjlggyg.pdf

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

抗原变异可使得多种致病微生物易于逃避宿主免疫应答。表达在感染红细胞表面的恶性疟原虫红细胞表面蛋白1（PfPMP1）与感染红细胞、内皮细胞、树突状细胞以及胎盘的单个或多个受体作用，在黏附及免疫逃避中起关键的作用。每个单倍体基因组var基因家族编码约60种成员，通过启动转录不同的var基因变异体为抗原变异提供了分子基础。

疟原虫var基因转换速率变化导致抗原变异[英]／Paul H, Robert P, Christodoulou Z, et al//Proc Natl Acad Sci U S A

Presents a theoretically very simple, yet efficient, multiresolution approach to gray-scale and rotation invariant texture classification based on local binary patterns and nonparametric discrimination of sample and prototype distributions. The method is based on recognizing that certain local binary patterns, termed "uniform," are fundamental properties of local image texture and their occurrence histogram is proven to be a very powerful texture feature. We derive a generalized gray-scale and rotation invariant operator presentation that allows for detecting the "uniform" patterns for any quantization of the angular space and for any spatial resolution and presents a method for combining multiple operators for multiresolution analysis. The proposed approach is very robust in terms of gray-scale variations since the operator is, by definition, invariant against any monotonic transformation of the gray scale. Another advantage is computational simplicity as the operator can be realized with a few operations in a small neighborhood and a lookup table. Experimental results demonstrate that good discrimination can be achieved with the occurrence statistics of simple rotation invariant local binary patterns.

/pdf/multiresolution-gray-scale-and-rotation-invariant-texture-1b1y2fta4g.pdf

Multiresolution gray-scale and rotation invariant texture classification with local binary patterns

Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012---achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also compare R-CNN to OverFeat, a recently proposed sliding-window detector based on a similar CNN architecture. We find that R-CNN outperforms OverFeat by a large margin on the 200-class ILSVRC2013 detection dataset. Source code for the complete system is available at this http URL.

Rich feature hierarchies for accurate object detection and semantic segmentation

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

Human Identification Based on Gait (The Kluwer International Series on Biometrics)

Training with more data has always been the most stable and effective way of improving performance in deep learn-ing era. As the largest object detection dataset so far, OpenImages brings great opportunities and challenges for object detection in general and sophisticated scenarios. However, owing to its semi-automatic collecting and labeling pipeline to deal with the huge data scale, Open Images dataset suffers from label-related problems that objects may explicitly or implicitly have multiple labels and the label distribution is extremely imbalanced. In this work, we quantitatively analyze these label problems and provide a simple but effective solution. We design a concurrent softmax to handle the multi-label problems in object detection and propose a soft-sampling methods with hybrid training scheduler to deal with the label imbalance. Overall, our method yields a dramatic improvement of 3.34 points, leading to the best single model with 60.90 mAP on the public object detection test set of Open Images. And our ensembling result achieves 67.17mAP, which is 4.29 points higher than the first place method last year.

/pdf/large-scale-object-detection-in-the-wild-from-imbalanced-1l809yrc5n.pdf

Large-Scale Object Detection in the Wild From Imbalanced Multi-Labels

In people tracking, one of the most challenging issues is occlusion handling. To cope with it, we introduce a Bayesian network, which involves human 2D ellipse models and an extra hidden process for occlusion relation. The 2D ellipse model combines color and spatial information simultaneously by creating color histograms for serval sub-regions. The extra hidden process for occlusion indicates the depth information of people through occlusions. The tracking process is performed using a condensation algorithm. Experiments show the effectiveness of the proposed method.

Tracking people through occlusions

In this paper, we present a novel method for shadow removal using Markov random fields (MRF). In our method, we first construct the shadow model in a hierarchical manner. At the pixel level, we use the Gaussian mixture model to model the behavior of cast shadows for every pixel in the HSV color space. The samples which are used to update the shadow model should satisfy a pre-classifier. This pre-classifier indicates the color feature of shadow in current frame. At the global level, we exploit the statistical features of shadow in the whole scene over several consecutive frames to make this pre-classifier accurate and adaptive to the change of shadow. Then, based on the shadow model, an MRF model is constructed for shadow removal. The main contribution of this paper is twofold. First, although our method is a chroma-based method, we make the pre-classifier accurate and adaptive to the change of shadow by using the statistical features of shadow at the global level. Moreover, tracking information can make this global-level statistical information more robust. Second, we construct an MRF model to represent the dependencies between the label of a pixel and the shadow models of its neighbors. Experimental results show that the proposed method is efficient and robust.

/pdf/cast-shadow-removal-in-a-hierarchical-manner-using-mrf-230ijmvdx3.pdf

Cast Shadow Removal in a Hierarchical Manner Using MRF

Combining multiple biometrics may enhance the performance of personal authentication system in accuracy and reliability. In this paper, we compare 13 combination methods in the context of combining the voiceprint and fingerprint recognition system in two different modes: verification and identification. The experimental results show that Support Vector Machine and the Dempster-Shafer method are superior to other schemes.

/pdf/combining-fingerprint-and-voiceprint-biometrics-for-identity-39zmgjf7kk.pdf

Tieniu Tan

Papers

Human Identification Based on Gait (The Kluwer International Series on Biometrics)

Large-Scale Object Detection in the Wild From Imbalanced Multi-Labels

Tracking people through occlusions

Cast Shadow Removal in a Hierarchical Manner Using MRF

Combining fingerprint and voiceprint biometrics for identity verification: An experimental comparison