Gestures are a common form of human communication and important for human computer interfaces (HCI). Recent approaches to gesture recognition use deep learning methods, including multi-channel methods. We show that wh...
详细信息
ISBN:
(纸本)9781538664209
Gestures are a common form of human communication and important for human computer interfaces (HCI). Recent approaches to gesture recognition use deep learning methods, including multi-channel methods. We show that when spatial channels are focused on the hands, gesture recognition improves significantly, particularly when the channels are fused using a sparse network. Using this technique, we improve performance on the ChaLearn IsoGD dataset from a previous best of 67.71% to 82.07%, and on the NVIDIA dataset from 83.8% to 91.28%.
We present Meta Pseudo Labels, a semi-supervised learning method that achieves a new state-of-the-art top-1 accuracy of 90.2% on ImageNet, which is 1.6% better than the existing state-of-the-art [16]. Like Pseudo Labe...
详细信息
ISBN:
(纸本)9781665445092
We present Meta Pseudo Labels, a semi-supervised learning method that achieves a new state-of-the-art top-1 accuracy of 90.2% on ImageNet, which is 1.6% better than the existing state-of-the-art [16]. Like Pseudo Labels, Meta Pseudo Labels has a teacher network to generate pseudo labels on unlabeled data to teach a student network. However, unlike Pseudo Labels where the teacher is fixed, the teacher in Meta Pseudo Labels is constantly adapted by the feedback of the student's performance on the labeled dataset. As a result, the teacher generates better pseudo labels to teach the student.(1)
We propose a novel grayness index forfinding gray pixels and demonstrate its effectiveness and efficiency in illumination estimation. The grayness index, GI in short, is derived using the Dichromatic Reflection Model ...
详细信息
ISBN:
(纸本)9781728132938
We propose a novel grayness index forfinding gray pixels and demonstrate its effectiveness and efficiency in illumination estimation. The grayness index, GI in short, is derived using the Dichromatic Reflection Model and is learning-free. GI allows to estimate one or multiple illuminationsources in color-biasedimages. On standardsingleillumination and multiple-illumination estimation benchmarks, GI outperforms state-of-the-art statisticalmethods and many recent deep methods. GI is simple andfast, written in afew dozen lines of code, processing a 1080p image in - 0.4 seconds with a non-optimized Matlab code.
We address the problem of locating a gray-level pattern in a gray-level image. The pattern can have been transformed formed by an affine transformation, and may have undergone some additional changes. We define a diff...
详细信息
ISBN:
(纸本)0780342364
We address the problem of locating a gray-level pattern in a gray-level image. The pattern can have been transformed formed by an affine transformation, and may have undergone some additional changes. We define a difference function based on comparing each pixel of the pattern with a window: in the image, and search efficiently for transformations that minimise the difference function. The search is guaranteed: it will always find the transformation minimising the difference function, and not get fooled by a local minimum;it is also efficient, in that it does not need to examine every transformation in order to achieve this guarantee. This technique can be applied to object location, motion tracking, optical flow, or block-based motion compensation in video image sequence compression (e.g., MPEG).
We propose a face recognition approach based on hashing. The approach yields comparable recognition rates with the random l(1) approach [18], which is considered the state-of-the-art. But our method is much faster: it...
详细信息
ISBN:
(纸本)9781424469840
We propose a face recognition approach based on hashing. The approach yields comparable recognition rates with the random l(1) approach [18], which is considered the state-of-the-art. But our method is much faster: it is up to 150 times faster than [18] on the YaleB dataset. We show that with hashing, the sparse representation can be recovered with a high probability because hashing preserves the restrictive isometry property. Moreover, we present a theoretical analysis on the recognition rate of the proposed hashing approach. Experiments show a very competitive recognition rate and significant speedup compared with the state-of-the-art.
We show how shadows can be efficiently generated in differentiable rendering of triangle meshes. Our central observation is that pre-filtered shadow mapping, a technique for approximating shadows based on rendering fr...
详细信息
ISBN:
(纸本)9798350301298
We show how shadows can be efficiently generated in differentiable rendering of triangle meshes. Our central observation is that pre-filtered shadow mapping, a technique for approximating shadows based on rendering from the perspective of a light, can be combined with existing differentiable rasterizers to yield differentiable visibility information. We demonstrate at several inverse graphics problems that differentiable shadow maps are orders of magnitude faster than differentiable light transport simulation with similar accuracy - while differentiable rasterization without shadows often fails to converge.
It is often necessary to handle randomness and geometry is computervision, for instance to match and fuse together noisy geometric features such as points, lines or 3D frames, or to estimate a geometric transformatio...
详细信息
ISBN:
(纸本)0818672587
It is often necessary to handle randomness and geometry is computervision, for instance to match and fuse together noisy geometric features such as points, lines or 3D frames, or to estimate a geometric transformation from a set of matched features. However, the proper handling of these geometric features is far more difficult than for points, and a number of paradoxes can arise. We analyse in this article three basic problems: (1) what is a uniform random distribution of features, (2) how to define a distance between features, and (3) what is the 'mean feature' of a number of feature measurements, and we propose generic methods to solve them.
A systematic methodology is presented for automatic selection of scale levels when detecting one-dimensional features, such as edges and ridges. A novel concept of a scale-space edge is introduced and defined as a con...
详细信息
ISBN:
(纸本)0818672587
A systematic methodology is presented for automatic selection of scale levels when detecting one-dimensional features, such as edges and ridges. A novel concept of a scale-space edge is introduced and defined as a connected set of points in scale-space. Two specific measures of edge strength are analyzed in detail. It is shown that by expressing these in terms of γ-normalized derivatives, an immediate consequence of this definition is that fine scales are selected for sharp edges, whereas coarse scales are selected for diffuse edge, such that an edge model constitutes a valid abstraction of the intensity profile across the edge.
Real-time recognition may be limited by scarce memory and computing resources for performing classification. Although, prior research has addressed the problem of training classifiers with limited data and computation...
详细信息
ISBN:
(纸本)9781467312288
Real-time recognition may be limited by scarce memory and computing resources for performing classification. Although, prior research has addressed the problem of training classifiers with limited data and computation, few efforts have tackled the problem of memory constraints on recognition. We explore methods that can guide the allocation of limited storage resources for classifying streaming data so as to maximize discriminatory power. We focus on computation of the expected value of information with nearest neighbor classifiers for online face recognition. Experiments on real-world datasets show the effectiveness and power of the approach. The methods provide a principled approach to vision under bounded resources, and have immediate application to enhancing recognition capabilities in consumer devices with limited memory.
Illumination estimation is the process of determining the chromaticity of the illumination in an imaged scene in order to remove undesirable color casts through white-balancing. While computational color constancy is ...
详细信息
ISBN:
(纸本)9781467369640
Illumination estimation is the process of determining the chromaticity of the illumination in an imaged scene in order to remove undesirable color casts through white-balancing. While computational color constancy is a well-studied topic in computervision, it remains challenging due to the ill posed nature of the problem. One class of techniques relies on low-level statistical information in the image color distribution and works under various assumptions (e.g. Grey World, White-Patch, etc). These methods have an advantage that they are simple and fast, but often do not perform well. More recent state-of-the-art methods employ learning-based techniques that produce better results, but often rely on complex features and have long evaluation and training times. In this paper, we present a learning-based method based on four simple color features and show how to use this with an ensemble of regression trees to estimate the illumination. We demonstrate that our approach is not only faster than existing learning-based methods in terms of both evaluation and training time, but also gives the best results reported to date on modern color constancy data sets.
暂无评论