The basic limitations of the current appearance-based matching methods using eigenimages are non-robust estimation of coefficients and inability to cope with problems related to occlusions and segmentation. In this pa...
详细信息
ISBN:
(纸本)0818672587
The basic limitations of the current appearance-based matching methods using eigenimages are non-robust estimation of coefficients and inability to cope with problems related to occlusions and segmentation. In this paper we present a new approach which successfully solves these problems. The major novelty of our approach lies in the way how the coefficients of the eigenimages are determined. Instead of computing the coefficients by a projection of the data onto the eigenimages, we extract them by a hypothesize-and-test paradigm using subsets of image points. Competing hypotheses are then subject to a selection procedure based on the Minimum Description Length principle. The approach enables us not only to reject outliers and to deal with occlusions but also to simultaneously use multiple classes of eigenimages.
This paper describes a probabilistic decomposition of human dynamics at multiple abstractions, and shows how to propagate hypotheses across space, time, and abstraction levels. recognition in this framework is the suc...
详细信息
ISBN:
(纸本)0780342364
This paper describes a probabilistic decomposition of human dynamics at multiple abstractions, and shows how to propagate hypotheses across space, time, and abstraction levels. recognition in this framework is the succession of very general low level grouping mechanisms to increased specific and learned model based grouping techniques at higher levels. Hard decision thresholds are delayed and resolved by higher level statistical models and temporal context. Low-level primitives are areas of coherent motion found by EM clustering, mid-level categories are simple movements represented by dynamical systems, and high-level complex gestures are represented by Hidden Markov Models as successive phases of simple movements. We show how such a representation can be learned from training data, and apply It to the example of human gait recognition.
This paper concerns action recognition from unseen and unknown views. We propose unsupervised learning of a non-linear model that transfers knowledge from multiple views to a canonical view. The proposed Non-linear Kn...
详细信息
ISBN:
(纸本)9781467369640
This paper concerns action recognition from unseen and unknown views. We propose unsupervised learning of a non-linear model that transfers knowledge from multiple views to a canonical view. The proposed Non-linear Knowledge Transfer Model (NKTM) is a deep network, with weight decay and sparsity constraints, which finds a shared high-level virtual path from videos captured from different unknown viewpoints to the same canonical view. The strength of our technique is that we learn a single NKTM for all actions and all camera viewing directions. Thus, NKTM does not require action labels during learning and knowledge of the camera viewpoints during training or testing. NKTM is learned once only from dense trajectories of synthetic points fitted to mocap data and then applied to real video data. Trajectories are coded with a general codebook learned from the same mocap data. NKTM is scalable to new action classes and training data as it does not require re-learning. Experiments on the IX MAS and N-UCLA datasets show that NKTM outperforms existing state-of-the-art methods for cross-view action recognition.
Current computervision systems whose basic methodology is open-loop or filter type typically use image segmentation followed by object recognition algorithms. These systems are not robust for most real-world applicat...
详细信息
ISBN:
(纸本)0818672587
Current computervision systems whose basic methodology is open-loop or filter type typically use image segmentation followed by object recognition algorithms. These systems are not robust for most real-world applications. In contrast, the system presented here achieves robust performance by using reinforcement learning to induce a mapping from input images to corresponding segmentation parameters. This is accomplished by using the confidence level of model matching as a reinforcement signal for a team of learning automata to search for segmentation parameters during training. The use of the recognition algorithm as part of the evaluation function for image segmentation gives rise to significant improvement of the system performance by automatic generation of recognition strategies. The system is verified through experiments on sequences of color images with varying external conditions.
This paper addresses the problem of learning word image representations: given the cropped image of a word, we are interested in finding a descriptive, robust, and compact fixed-length representation. Machine learning...
详细信息
ISBN:
(纸本)9781467369640
This paper addresses the problem of learning word image representations: given the cropped image of a word, we are interested in finding a descriptive, robust, and compact fixed-length representation. Machine learning techniques can then be supplied with these representations to produce models useful for word retrieval or recognition tasks. Although many works have focused on the machine learning aspect once a global representation has been produced, little work has been devoted to the construction of those base image representations: most works use standard coding and aggregation techniques directly on top of standard computervision features such as SIFT or HOG. We propose to learn local mid-level features suitable for building word image representations. These features are learnt by leveraging character bounding box annotations on a small set of training images. However, contrary to other approaches that use character bounding box information, our approach does not rely on detecting the individual characters explicitly at testing time. Our local mid-level features can then be aggregated to produce a global word image signature. When pairing these features with the recent word attributes framework of [4], we obtain results comparable with or better than the state-of-the-art on matching and recognition tasks using global descriptors of only 96 dimensions.
In this contribution we present an algorithm for tracking non-rigid, moving objects in a sequence of colored images, which were recorded by a non-stationary camera. The application background is vision-based driving a...
详细信息
ISBN:
(纸本)0780342364
In this contribution we present an algorithm for tracking non-rigid, moving objects in a sequence of colored images, which were recorded by a non-stationary camera. The application background is vision-based driving assistance in the inner city In an initial step, object parts are determined by a divisive clustering algorithm, which is applied to all pixels in the first image of the sequence. The feature space is defined by the color and position of a pixel. For each new image the clusters of the previous image are adapted iteratively by a parallel k-means clustering algorithm. Instead of tracking single points, edges, or areas over a sequence of images, only the centroids of the clusters are tracked. The proposed method remarkably simplifies the correspondence problem and also ensures a robust tracking behavior.
Object recognition systems have shown great progress over recent years. However, creating object representations that are robust to changes in viewpoint while capturing local visual details continues to be a challenge...
详细信息
ISBN:
(纸本)9781467369640
Object recognition systems have shown great progress over recent years. However, creating object representations that are robust to changes in viewpoint while capturing local visual details continues to be a challenge. In particular, recent convolutional architectures employ spatial pooling to achieve scale and shift invariances, but they are still sensitive to out-of-plane rotations. In this paper, we formulate a probabilistic framework for analyzing the performance of pooling. This framework suggests two directions for improvement. First, we apply multiple scales of filters coupled with different pooling granularities, and second we make use of color as an additional pooling domain, thereby reducing the sensitivity to spatial deformations. We evaluate our algorithm on the object instance recognition task using two independent publicly available RGB-D datasets, and demonstrate significant improvements over the current state-of-the-art. In addition, we present a new dataset for industrial objects to further validate the effectiveness of our approach versus other state-of-the-art approaches for object recognition using RGB-D data.
Scaling machine learning methods to very large datasets has attracted considerable attention in recent years, thanks to easy access to ubiquitous sensing and data from the web. We study face recognition and show that ...
详细信息
ISBN:
(纸本)9781467369640
Scaling machine learning methods to very large datasets has attracted considerable attention in recent years, thanks to easy access to ubiquitous sensing and data from the web. We study face recognition and show that three distinct properties have surprising effects on the transferability of deep convolutional networks (CNN): (1) The bottleneck of the network serves as an important transfer learning regularizer, and (2) in contrast to the common wisdom, performance saturation may exist in CNN's (as the number of training samples grows);we propose a solution for alleviating this by replacing the naive random subsampling of the training set with a bootstrapping process. Moreover, (3) we find a link between the representation norm and the ability to discriminate in a target domain, which sheds lights on how such networks represent faces. Based on these discoveries, we are able to improve face recognition accuracy on the widely used LFW benchmark, both in the verification (1:1) and identification (1:N) protocols, and directly compare, for the first time, with the state of the art Commercially-Off-The-Shelf system and show a sizable leap in performance.
It is widely accepted that textureless surfaces cannot be recovered using passive sensing techniques. The problem is approached by viewing image formation as a Sully three-dimensional mapping. It is shown that the len...
详细信息
ISBN:
(纸本)0780342364
It is widely accepted that textureless surfaces cannot be recovered using passive sensing techniques. The problem is approached by viewing image formation as a Sully three-dimensional mapping. It is shown that the lens encodes structural information of the scene within a compact three-dimensional space behind it. After analyzing the information content of this space and by using its properties we derive necessary and sufficient conditions for the recovery of textureless scenes. Based on these conditions, a simple procedure for recovering textureless scenes is described. We experimentally demonstrate the recovery of three textureless surfaces, namely, a line, a plane, and a paraboloid. Since textureless surfaces represent the worst case recovery scenario, all the results and the recovery procedure are naturally applicable to scenes with texture.
Many vision tasks require a multi-class classifier to discriminate multiple categories, on the order of hundreds or thousands. In this paper, we propose sparse output coding, a principled way for large-scale multi-cla...
详细信息
ISBN:
(纸本)9780769549897
Many vision tasks require a multi-class classifier to discriminate multiple categories, on the order of hundreds or thousands. In this paper, we propose sparse output coding, a principled way for large-scale multi-class classification, by turning high-cardinality multi-class categorization into a bit-by-bit decoding problem. Specifically, sparse output coding is composed of two steps: efficient coding matrix learning with scalability to thousands of classes, and probabilistic decoding. Empirical results on object recognition and scene classification demonstrate the effectiveness of our proposed approach.
暂无评论