In this paper, we report on experiments with the use of local measures for depth motion for visual action recognition from MPEG encoded RGBD video sequences. We show that such measures can be combined with local space-time video descriptors for appearance to provide a computationally efficient method for recognition of actions. Fisher vectors are used for encoding and concatenating a depth descriptor with existing RGB local descriptors. We then employ a linear SVM for recognizing manipulation actions using such vectors. We evaluate the effectiveness of such measures by comparison to the state-of-the-art using two recent datasets for action recognition in kitchen environments.
School of Electrical Engineering and Computer Science（电气工程与计算机科学学院）；University of Ottawa（渥太华大学）
This paper introduces a high efficient local spatiotemporal descriptor, called gradient boundary histograms (GBH). The proposed GBH descriptor is built on simple spatio-temporal gradients, which are fast to compute. We demonstrate that it can better represent local structure and motion than other gradient-based descriptors, and significantly outperforms them on large realistic datasets. A comprehensive evaluation shows that the recognition accuracy is preserved while the spatial resolution is greatly reduced, which yields both high efficiency and low memory usage.
Despite the recent developments in spatiotemporal local features for action recognition in video sequences, local color information has so far been ignored. However, color has been proved an important element to the success of automated recognition of objects and scenes. In this paper we extend the space-time interest point descriptor STIP to take into account the color information on the features' neighborhood. We compare the performance of our color-aware version of STIP (which we have called HueSTIP) with the original one.
Existing techniques for 3D action recognition are sensitive to viewpoint variations because they extract features from depth images which change significantly with viewpoint. In contrast, we directly process the pointclouds and propose a new technique for action recognition which is more robust to noise, action speed and viewpoint variations. Our technique consists of a novel descriptor and keypoint detection algorithm. The proposed descriptor is extracted at a point by encoding the Histogram of Oriented Principal Components (HOPC) within an adaptive spatio-temporal support volume around that …
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 pointclouds 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 dodecah…
University of Moratuwa（莫勒图沃大学）；University of Malaya（马来亚大学）
Visual feature clustering is one of the cost-effective approaches to segment objects in videos. However, the assumptions made for developing the existing algorithms prevent them from being used in situations like segmenting an unknown number of static and moving objects under heavy camera movements. This paper addresses the problem by introducing a clustering approach based on superpixels and short-term Histogram of Oriented Optical Flow (HOOF). Salient Dither Pattern Feature (SDPF) is used as the visual feature to track the flow and Simple Linear Iterative Clustering (SLIC) is used for obtain…
CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System（中国科学院地理空间信息处理与应用系统技术重点实验室）；University of Science and Technology of China（中国科学技术大学）
We study the video super-resolution (SR) problem for facilitating video analytics tasks, e.g. action recognition, instead of for visual quality. The popular action recognition methods based on convolutional networks, exemplified by two-stream networks, are not directly applicable on video of low spatial resolution. This can be remedied by performing video SR prior to recognition, which motivates us to improve the SR procedure for recognition accuracy. Tailored for two-stream action recognition networks, we propose two video SR methods for the spatial and temporal streams respectively. On the o…
Despite the notable progress made in action recognition tasks, not much work has been done in action recognition specifically for human-robot interaction. In this paper, we deeply explore the characteristics of the action recognition task in interaction scenarios and propose an attention-oriented multi-level network framework to meet the need for real-time interaction. Specifically, a Pre-Attention network is employed to roughly focus on the interactor in the scene at low resolution firstly and then perform fine-grained pose estimation at high resolution. The other compact CNN receives the ext…
Isfahan University of Technology（伊斯法罕理工大学）；Australian National University（澳大利亚国立大学）；University of Queensland（昆士兰大学）；NICTA
Representing videos by densely extracted local space-time features has recently become a popular approach for analysing actions. In this paper, we tackle the problem of categorising human actions by devising Bag of Words (BoW) models based on covariance matrices of spatio-temporal features, with the features formed from histograms of optical flow. Since covariance matrices form a special type of Riemannian manifold, the space of Symmetric Positive Definite (SPD) matrices, non-Euclidean geometry should be taken into account while discriminating between covariance matrices. To this end, we propo…
Tel Aviv University（特拉维夫大学）；Geha Mental Health Center（格哈心理健康中心）
Automatic recognition of facial gestures is becoming increasingly important as real world AI agents become a reality. In this paper, we present an automated system that recognizes facial gestures by capturing local changes and encoding the motion into a histogram of frequencies. We evaluate the proposed method by demonstrating its effectiveness on spontaneous face action benchmarks: the FEEDTUM dataset, the Pain dataset and the HMDB51 dataset. The results show that, compared to known methods, the new encoding methods significantly improve the recognition accuracy and the robustness of analysis…
Vision-based activity recognition is essential for security, monitoring and surveillance applications. Further, real-time analysis having low-quality video and contain less information about surrounding due to poor illumination, and occlusions. Therefore, it needs a more robust and integrated model for low quality and night security operations. In this context, we proposed a hybrid model for illumination invariant human activity recognition based on sub-image histogram equalization enhancement and k-key pose human silhouettes. This feature vector gives good average recognition accuracy on thre…
University of Zagreb（萨格勒布大学）；Graz University of Technology（格拉茨技术大学）
This paper proposes combining spatio-temporal appearance (STA) descriptors with optical flow for human action recognition. The STA descriptors are local histogram-based descriptors of space-time, suitable for building a partial representation of arbitrary spatio-temporal phenomena. Because of the possibility of iterative refinement, they are interesting in the context of online human action recognition. We investigate the use of dense optical flow as the image function of the STA descriptor for human action recognition, using two different algorithms for computing the flow: the Farnebäck algor…
University of Wollongong（伍伦贡大学）；Tianjin University（天津大学）
This paper proposes a new framework for RGB-D-based action recognition that takes advantages of hand-designed features from skeleton data and deeply learned features from depth maps, and exploits effectively both the local and global temporal information. Specifically, depth and skeleton data are firstly augmented for deep learning and making the recognition insensitive to view variance. Secondly, depth sequences are segmented using the hand-crafted features based on skeleton joints motion histogram to exploit the local temporal information. All training se gments are clustered using an Infini…
Zhejiang University – University of Illinois at Urbana-Champaign Institute, ZJUI（浙江大学伊利诺伊大学厄巴纳香槟校区联合学院（ZJUI））
Action recognition and pose estimation from videos are closely related to understand human motions, but more literature focuses on how to solve pose estimation tasks alone from action recognition. This research shows a faster and more flexible training method for VideoPose3D which is based on action recognition. This model is fed with the same type of action as the type that will be estimated, and different types of actions can be trained separately. Evidence has shown that, for common pose-estimation tasks, this model requires a relatively small amount of data to carry out similar results wit…
Traditionally, only experts who are equipped with professional knowledge and rich experience are able to recognize different species of wood. Applying image processing techniques for wood species recognition can not only reduce the expense to train qualified identifiers, but also increase the recognition accuracy. In this paper, a wood species recognition technique base on Scale Invariant Feature Transformation (SIFT) keypoint histogram is proposed. We use first the SIFT algorithm to extract keypoints from wood cross section images, and then k-means and k-means++ algorithms are used for cluste…
This paper addresses the problem of selecting appearance features for multiple object tracking (MOT) in urban scenes. Over the years, a large number of features has been used for MOT. However, it is not clear whether some of them are better than others. Commonly used features are color histograms, histograms of oriented gradients, deep features from convolutional neural networks and re-identification (ReID) features. In this study, we assess how good these features are at discriminating objects enclosed by a bounding box in urban scene tracking scenarios. Several affinity measures, namely the …
Substantial research has been devoted to the development of algorithms that automate buried threat detection (BTD) with ground penetrating radar (GPR) data, resulting in a large number of proposed algorithms. One popular algorithm GPR-based BTD, originally applied by Torrione et al., 2012, is the Histogram of Oriented Gradients (HOG) feature. In a recent large-scale comparison among five veteran institutions, a modified version of HOG referred to here as "gprHOG", performed poorly compared to other modern algorithms. In this paper, we provide experimental evidence demonstrating that the modifi…
CONICET（阿根廷国家科学技术研究委员会）；Universidad Argentina de la Empresa (UADE)（阿根廷企业大学）
Address Event Representation is a thriving technology that could change digital image processing paradigm. This paper proposes a methodology to characterize the shape of objects using the streaming of asynchronous events. A new descriptor that enhances spikes connectivity is associated with two oriented histogram based representations. This paper uses these features to develop both a non-supervised and a supervised multi-classification framework to recognize poker symbols from the Poker-DVS public dataset. The aforementioned framework, which uses a very limited number of events and a simple cl…
University Federal of Ouro Preto（奥罗普雷托联邦大学）；Univ. Federal of Minas Gerais（米纳斯吉拉斯联邦大学）
Due to the increasingly need for automatic traffic monitoring, vehicle license plate detection is of high interest to perform automatic toll collection, traffic law enforcement, parking lot access control, among others. In this paper, a sliding window approach based on Histogram of Oriented Gradients (HOG) features is used for Brazilian license plate detection. This approach consists in scanning the whole image in a multiscale fashion such that the license plate is located precisely. The main contribution of this work consists in a deep study of the best setup for HOG descriptors on the detect…
State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School（国家一般人工智能实验室，北京大学深圳研究生院）；Department of Information Engineering and Computer Science (DISI), University of Trento（信息工程与计算机科学系（DISI），特伦托大学）；University at Buffalo, The State University of New York（布法罗大学，纽约州立大学）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学）
The traditional bag-of-words approach has found a wide range of applications in computer vision. The standard pipeline consists of a generation of a visual vocabulary, a quantization of the features into histograms of visual words, and a classification step for which usually a support vector machine in combination with a non-linear kernel is used. Given large amounts of data, however, the model suffers from a lack of discriminative power. This applies particularly for action recognition, where the vast amount of video features needs to be subsampled for unsupervised visual vocabulary generatio…
Growing amount of different practical tasks in a video understanding problem has addressed the great challenge aiming to design an universal solution, which should be available for broad masses and suitable for the demanding edge-oriented inference. In this paper we are focused on designing a network architecture and a training pipeline to tackle the mentioned challenges. Our architecture takes the best from the previous ones and brings the ability to be successful not only in appearance-based action recognition tasks but in motion-based problems too. Furthermore, the induced label noise probl…
Chongqing University（重庆大学）；Beihang University（北京航空航天大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
We further exploit the representational power of Haar wavelet and present a novel low-level face representation named Shape Primitives Histogram (SPH) for face recognition. Since human faces exist abundant shape features, we address the face representation issue from the perspective of the shape feature extraction. In our approach, we divide faces into a number of tiny shape fragments and reduce these shape fragments to several uniform atomic shape patterns called Shape Primitives. A convolution with Haar Wavelet templates is applied to each shape fragment to identify its belonging shape primi…
Despite recent advances in image enhancement, it remains difficult for existing approaches to adaptively improve the brightness and contrast for both low-light and normal-light images. To solve this problem, we propose a novel 2D histogram equalization approach. It assumes intensity occurrence and co-occurrence to be dependent on each other and derives the distribution of intensity occurrence (1D histogram) by marginalizing over the distribution of intensity co-occurrence (2D histogram). This scheme improves global contrast more effectively and reduces noise amplification. The 2D histogram is …
Human face recognition has been a long standing problem in computer vision and pattern recognition. Facial analysis can be viewed as a two-fold problem, namely (i) facial representation, and (ii) classification. So far, many face representations have been proposed, a well-known method is the Local Binary Pattern (LBP), which has witnessed a growing interest. In this respect, we treat in this paper the issues of face representation as well as classification in a novel manner. On the one hand, we use a variant to LBP, so-called Complete Local Binary Pattern (CLBP), which differs from the basic L…
Because the magnitude of inner products with its basis functions are invariant to rotation and scale change, the Fourier-Mellin transform has long been used as a component in Euclidean invariant 2D shape recognition systems. Yet Fourier-Mellin transform magnitudes are only invariant to rotation and scale changes about a known center point, and full Euclidean invariant shape recognition is not possible except when this center point can be consistently and accurately identified. In this paper, we describe a system where a Fourier-Mellin transform is computed at every point in the image. The spat…
Pain assessment through observational pain scales is necessary for special categories of patients such as neonates, patients with dementia, critically ill patients, etc. The recently introduced Prkachin-Solomon score allows pain assessment directly from facial images opening the path for multiple assistive applications. In this paper, we introduce the Histograms of Topographical (HoT) features, which are a generalization of the topographical primal sketch, for the description of the face parts contributing to the mentioned score. We propose a semi-supervised, clustering oriented self--taught l…
In this paper, we present a novel approach for image retrieval based on extraction of low level features using techniques such as Directional Binary Code, Haar Wavelet transform and Histogram of Oriented Gradients. The DBC texture descriptor captures the spatial relationship between any pair of neighbourhood pixels in a local region along a given direction, while Local Binary Patterns descriptor considers the relationship between a given pixel and its surrounding neighbours. Therefore, DBC captures more spatial information than LBP and its variants, also it can extract more edge information th…
fortiss - The Research Institute of the Free State of Bavaria（fortiss - 巴伐利亚自由州研究院）
Distance-based dynamic texture recognition is an important research field in multimedia processing with applications ranging from retrieval to segmentation of video data. Based on the conjecture that the most distinctive characteristic of a dynamic texture is the appearance of its individual frames, this work proposes to describe dynamic textures as kernelized spaces of frame-wise feature vectors computed using the Scattering transform. By combining these spaces with a basis-invariant metric, we get a framework that produces competitive results for nearest neighbor classification and state-of-…
The purpose of this paper is to describe one-shot-learning gesture recognition systems developed on the \textit{ChaLearn Gesture Dataset}. We use RGB and depth images and combine appearance (Histograms of Oriented Gradients) and motion descriptors (Histogram of Optical Flow) for parallel temporal segmentation and recognition. The Quadratic-Chi distance family is used to measure differences between histograms to capture cross-bin relationships. We also propose a new algorithm for trimming videos --- to remove all the unimportant frames from videos. We present two methods that use combination of…
Xiamen University（厦门大学）；University of Waterloo（滑铁卢大学）；The Hong Kong Polytechnic University（香港理工大学）
In this paper, we propose an effective scene text recognition method using sparse coding based features, called Histograms of Sparse Codes (HSC) features. For character detection, we use the HSC features instead of using the Histograms of Oriented Gradients (HOG) features. The HSC features are extracted by computing sparse codes with dictionaries that are learned from data using K-SVD, and aggregating per-pixel sparse codes to form local histograms. For word recognition, we integrate multiple cues including character detection scores and geometric contexts in an objective function. The final r…
University College London（伦敦大学学院）；NAAMII；Redev Technology（Redev科技）
We present our novel deep multi-task learning method for medical image segmentation. Existing multi-task methods demand ground truth annotations for both the primary and auxiliary tasks. Contrary to it, we propose to generate the pseudo-labels of an auxiliary task in an unsupervised manner. To generate the pseudo-labels, we leverage Histogram of Oriented Gradients (HOGs), one of the most widely used and powerful hand-crafted features for detection. Together with the ground truth semantic segmentation masks for the primary task and pseudo-labels for the auxiliary task, we learn the parameters o…
Document segmentation is one of the critical phases in machine recognition of any language. Correct segmentation of individual symbols decides the accuracy of character recognition technique. It is used to decompose image of a sequence of characters into sub images of individual symbols by segmenting lines and words. Devnagari is the most popular script in India. It is used for writing Hindi, Marathi, Sanskrit and Nepali languages. Moreover, Hindi is the third most popular language in the world. Devnagari documents consist of vowels, consonants and various modifiers. Hence proper segmentation …
University of Missouri-Columbia（密苏里大学哥伦比亚分校）；US Naval Research Laboratory（美国海军研究实验室）
Weighting pixel contribution considering its location is a key feature in many fundamental image processing tasks including filtering, object modeling and distance matching. Several techniques have been proposed that incorporate Spatial information to increase the accuracy and boost the performance of detection, tracking and recognition systems at the cost of speed. But, it is still not clear how to efficiently ex- tract weighted local histograms in constant time using integral histogram. This paper presents a novel algorithm to compute accurately multi-scale Spatially weighted local histogram…
The University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）；Texas State University（德克萨斯州立大学）
This research presents an improved real-time face recognition system at a low resolution of 15 pixels with pose and emotion and resolution variations. We have designed our datasets named LRD200 and LRD100, which have been used for training and classification. The face detection part uses the Viola-Jones algorithm, and the face recognition part receives the face image from the face detection part to process it using the Local Binary Pattern Histogram (LBPH) algorithm with preprocessing using contrast limited adaptive histogram equalization (CLAHE) and face alignment. The face database in this s…
The success rates of Optical Character Recognition (OCR) systems for printed Malayalam documents is quite impressive with the state of the art accuracy levels in the range of 85-95% for various. However for real applications, further enhancement of this accuracy levels are required. One of the bottle necks in further enhancement of the accuracy is identified as close-matching characters. In this paper, we delineate the close matching characters in Malayalam and report the development of a specialised classifier for these close-matching characters. The output of a state of the art of OCR is tak…
Hybrid second-order gradient histogram based global low-rank sparse regression for robust face recognition
School of Mathematics, Physics and Statistics, Shanghai University of Engineering Science（数学物理与统计学学院，上海工程技术大学）；School of Mathematical Sciences , Sunway University（数学科学学院，Sunway大学）；School of Law and Criminal Justice, East China University of Political Science and Law（法律与刑事司法学院，中国政法大学）
Oriented histogram-based vector field embedding for characterizing 4D CT data sets in radiotherapy
Institute for Applied Medical Informatics, University Medical Center Hamburg-Eppendorf（汉堡埃彭多夫大学医学中心应用医学信息学研究所）；Institute of Computational Neuroscience, University Medical Center Hamburg-Eppendorf（汉堡埃彭多夫大学医学中心计算神经科学研究所）；Department of Radiotherapy and Radiation Oncology, University Medical Center Hamburg-Eppendorf（汉堡埃彭多夫大学医学中心放射治疗与放射肿瘤学系）
In a broad range of computer vision applications, the purpose of Low-rank matrix approximation (LRMA) models is to recover the underlying low-rank matrix from its degraded observation. The latest LRMA methods - Robust Principal Component Analysis (RPCA) resort to using the nuclear norm minimization (NNM) as a convex relaxation of the non-convex rank minimization. However, NNM tends to over-shrink the rank components and treats the different rank components equally, limiting its flexibility in practical applications. We use a more flexible model, namely the Weighted Schatten p-Norm Minimization…
This study presents an open source method for detecting 3D printing anomalies by comparing images of printed layers from a stationary monocular camera with G-code-based reference images of an ideal process generated with Blender, a physics rendering engine. Recognition of visual deviations was accomplished by analyzing the similarity of histograms of oriented gradients (HOG) of local image areas. The developed technique requires preliminary modeling of the working environment to achieve the best match for orientation, color rendering, lighting, and other parameters of the printed part. The out…
Institute of Semiconductors, Chinese Academy of Sciences（中国科学院半导体研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Wave Group（浪潮集团）
Local feature descriptors exhibit great superiority in finger vein recognition due to their stability and robustness against local changes in images. However, most of these are methods use general-purpose descriptors that do not consider finger vein-specific features. In this work, we propose a finger vein-specific local feature descriptors based physiological characteristic of finger vein patterns, i.e., histogram of oriented physiological Gabor responses (HOPGR), for finger vein recognition. First, prior of directional characteristic of finger vein patterns is obtained in an unsupervised man…
Encoded Local Projections (ELP) is a recently introduced dense sampling image descriptor which uses projections in small neighbourhoods to construct a histogram/descriptor for the entire image. ELP has shown to be as accurate as other state-of-the-art features in searching medical images while being time and resource efficient. This paper attempts for the first time to utilize ELP descriptor as primary features for facial recognition and compare the results with LBP histogram on the Labeled Faces in the Wild dataset. We have evaluated descriptors by comparing the chi-squared distance of each i…
Balancing computational efficiency with recognition accuracy is one of the major challenges in real-world video-based face recognition. A significant design decision for any such system is whether to process and use all possible faces detected over the video frames, or whether to select only a few "best" faces. This paper presents a video face recognition system based on probabilistic Multi-Region Histograms to characterise performance trade-offs in: (i) selecting a subset of faces compared to using all faces, and (ii) combining information from all faces via clustering. Three face selection m…
M.S. University（M.S.大学）；S.T. Hindu College（S.T.印度教学院）
The performance of the Fingerprint recognition system will be more accurate with respect of enhancement for the fingerprint images. In this paper we develop a novel method for Fingerprint image contrast enhancement technique based on the discrete wavelet transform (DWT) and singular value decomposition (SVD) has been proposed. This technique is compared with conventional image equalization techniques such as standard general histogram equalization and local histogram equalization. An automatic histogram threshold approach based on a fuzziness measure is presented. Then, using an index of fuzzi…
School of Automation, Beijing Institute of Technology（北京理工大学自动化学院）
Oriented object detection in remote sensing images has made great progress in recent years. However, most of the current methods only focus on detecting targets, and cannot distinguish fine-grained objects well in complex scenes. In this technical report, we analyzed the key issues of fine-grained object recognition, and use an oriented feature alignment network (OFA-Net) to achieve high-performance fine-grained oriented object recognition in optical remote sensing images. OFA-Net achieves accurate object localization through a rotated bounding boxes refinement module. On this basis, the bound…
Spatial-temporal local binary pattern (STLBP) has been widely used in dynamic texture recognition. STLBP often encounters the high-dimension problem as its dimension increases exponentially, so that STLBP could only utilize a small neighborhood. To tackle this problem, we propose a method for dynamic texture recognition using PDV hashing and dictionary learning on multi-scale volume local binary pattern (PHD-MVLBP). Instead of forming very high-dimensional LBP histogram features, it first uses hash functions to map the pixel difference vectors (PDVs) to binary vectors, then forms a dictionary …
University of Wollongong（伍伦贡大学）；University of Sydney（悉尼大学）
This paper takes a problem-oriented perspective and presents a comprehensive review of transfer learning methods, both shallow and deep, for cross-dataset visual recognition. Specifically, it categorises the cross-dataset recognition into seventeen problems based on a set of carefully chosen data and label attributes. Such a problem-oriented taxonomy has allowed us to examine how different transfer learning approaches tackle each problem and how well each problem has been researched to date. The comprehensive problem-oriented review of the advances in transfer learning with respect to the prob…
Universidad de Vigo（维戈大学）；A. Razmadze Mathematical Institute of Tbilisi State University（第比利斯国立大学拉兹马泽数学研究所）；Tbilisi Centre for Mathematical Sciences（第比利斯数学科学中心）；Universidade de Santiago de Compostela（圣地亚哥德孔波斯特拉大学）；Universidad de A Coruña（拉科鲁尼亚大学）
In this paper, we present a methodology for off-line handwritten character recognition. The proposed methodology relies on a new feature extraction technique based on structural characteristics, histograms and profiles. As novelty, we propose the extraction of new eight histograms and four profiles from the $32\times 32$ matrices that represent the characters, creating 256-dimension feature vectors. These feature vectors are then employed in a classification step that uses a $k$-means algorithm. We performed experiments using the NIST database to evaluate our proposal. Namely, the recognition …
This paper presents a framework for recognition of human activity from egocentric video and eye tracking data obtained from a head-mounted eye tracker. Three channels of information such as eye movement, ego-motion, and visual features are combined for the classification of activities. Image features were extracted using a pre-trained convolutional neural network. Eye and ego-motion are quantized, and the windowed histograms are used as the features. The combination of features obtains better accuracy for activity classification as compared to individual features.
This paper devises a new means of filter diversification, dubbed multi-fold filter convolution (M-FFC), for face recognition. On the assumption that M-FFC receives single-scale Gabor filters of varying orientations as input, these filters are self-cross convolved by M-fold to instantiate a filter offspring set. The M-FFC flexibility also permits cross convolution amongst Gabor filters and other filter banks of profoundly dissimilar traits, e.g., principal component analysis (PCA) filters, and independent component analysis (ICA) filters. The 2-FFC of Gabor, PCA and ICA filters thus yields thre…
Hikvision Research Institute（海康威视研究院）；Tongji University（同济大学）；Fudan University（复旦大学）
Recognizing text from natural images is a hot research topic in computer vision due to its various applications. Despite the enduring research of several decades on optical character recognition (OCR), recognizing texts from natural images is still a challenging task. This is because scene texts are often in irregular (e.g. curved, arbitrarily-oriented or seriously distorted) arrangements, which have not yet been well addressed in the literature. Existing methods on text recognition mainly work with regular (horizontal and frontal) texts and cannot be trivially generalized to handle irregular …
Knowledge distillation (KD) is a widely-used technique that utilizes large networks to improve the performance of compact models. Previous KD approaches usually aim to guide the student to mimic the teacher's behavior completely in the representation space. However, such one-to-one corresponding constraints may lead to inflexible knowledge transfer from the teacher to the student, especially those with low model capacities. Inspired by the ultimate goal of KD methods, we propose a novel Evaluation oriented KD method (EKD) for deep face recognition to directly reduce the performance gap between…
