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

3D image data provide several advantages than 2D data for face recognition and overcome many problems with 2D intensity images based methods. In this paper, we propose a novel approach to 3D-based face recognition. First, a novel representation, called intrinsic features, is presented to encode local 3D shapes. It describes complementary non-relational features to provide an intrinsic representation of faces. This representation is extracted after alignment, and is invariant to translation, rotation and scale. Without reduction, tens of thousands of intrinsic features can be produced for a face, but not all of them are useful and equally important. Therefore, in the second part of the work, we introduce a learning method for learning most effective local features and combining them into a strong classifier using an AdaBoost learning procedure. Experimental results are performed on a large 3D face database obtained with complex illumination, pose and expression variations. The results demonstrate that the proposed approach produces consistently better results than existing methods.

/pdf/learning-effective-intrinsic-features-to-boost-3d-based-face-179tuu0l0g.pdf

Learning effective intrinsic features to boost 3d-based face recognition

This paper focuses on acquisition of human motion data such as joint angles and velocity for applications of virtual reality, using both articulated body model and motion model in the CONDENSATION framework. Firstly, we learn a motion model represented by Gaussian distributions, and explore motion constraints by considering the dependency of motion parameters and represent them as conditional distributions. Then both of them are integrated into the dynamic model to concentrate factored sampling in the areas of state-space with mostposterior information. To measure the observing density with accuracy and robustness, a PEF (Pose Evaluation Function) modeled with a radial term is proposed. We also address the issue of automatic acquisition of initial model posture and recovery from severe failures. A large number of experiments on several persons demonstrate that our approach works well.

http://www.ifp.illinois.edu/~hning2/papers/ICMI02_ning&wang.pdf

Articulated model based people tracking using motion models

MAPNet: Multi-modal attentive pooling network for RGB-D indoor scene classification

We address the problem of automatic object classification for traffic scene surveillance, which is very challenging for the low resolution videos, large intra-class variations and real-time requirement. In this paper, we propose a new strategy for object classification by boosting different local feature descriptors in motion blobs. We not only evaluate the performance of each local feature descriptor, but also fuse these descriptors to achieve better performance. Numerous experiments are conducted and experimental results demonstrate the effectiveness and efficiency of our approach with robustness to noise and variance of view angles, lighting conditions and environments.

/pdf/boosting-local-feature-descriptors-for-automatic-objects-2w6ynafscj.pdf

Boosting local feature descriptors for automatic objects classification in traffic scene surveillance

The problem of detecting the feature points arises in many fields of science and engineering. In this paper, we focus on the 3D face range data and propose a robust scheme to solve a specific problem, i.e. locating the nose lip and nose ridge using the local statistic features and included angle curve. This work is very significant to 3D face modelling, recognition and registration. The key features of our method are the fully automated processing, the ability to deal with noisy and incomplete input data, the immunity to the rotation and translation and the adaptability to the different resolution. The experimental results in different databases fully show the robust and feasibility of the proposed method.

Tieniu Tan

Papers

Learning effective intrinsic features to boost 3d-based face recognition

Articulated model based people tracking using motion models

MAPNet: Multi-modal attentive pooling network for RGB-D indoor scene classification

Boosting local feature descriptors for automatic objects classification in traffic scene surveillance

Robust nose detection in 3D facial data using local characteristics