Random Forests (RFs) have become commonplace in many computer vision applications. Their popularity is mainly driven by their high computational efficiency during both training and evaluation while still being able to achieve state-of-the-art accuracy. This work extends the usage of Random Forests to Semi-Supervised Learning (SSL) problems. We show that traditional decision trees are optimizing multiclass margin maximizing loss functions. From this intuition, we develop a novel multi-class margin definition for the unlabeled data, and an iterative deterministic annealing-style training algorithm maximizing both the multi-class margin of labeled and unlabeled samples. In particular, this allows us to use the predicted labels of the unlabeled data as additional optimization variables. Furthermore, we propose a control mechanism based on the out-of-bag error, which prevents the algorithm from degradation if the unlabeled data is not useful for the task. Our experiments demonstrate state-of-the-art semisupervised learning performance in typical machine learning problems and constant improvement using unlabeled data for the Caltech-101 object categorization task. 1.

Action recognition methods suffer from many drawbacks in practice, which include (1)the inability to cope with incremental recognition problems; (2)the requirement of an intensive training stage to obtain good performance; (3) the inability to recognize simultaneous multiple actions; and (4) difficulty in performing recognition frame by frame. In order to overcome all these drawbacks using a single method, we propose a novel framework involving the feature-tree to index large scale motion features using Sphere/Rectangle-tree (SR-tree). Our method consists of the following two steps: 1) recognizing the local features by non-parametric nearest neighbor (NN), 2) using a simple voting strategy to label the action. The proposed method can provide the localization of the action. Since our method does not require feature quantization, the feature-tree can be efficiently grown by adding features from new training examples of actions or categories. Our method provides an effective way for practical incremental action recognition. Furthermore, it can handle large scale datasets due to the fact that the SR-tree is a disk-based data structure. We have tested our approach on two publicly available datasets, the KTH and the IXMAS multi-view datasets, and obtained promising results. 1.

Codebook-based representations are widely employed in the classification of complex objects such as images and documents. Most previous codebook-based methods construct a single codebook via clustering that maps a bag of lowlevel features into a fixed-length histogram that describes the distribution of these features. This paper describes a simple yet effective framework for learning multiple non-redundant codebooks that produces surprisingly good results. In this framework, each codebook is learned in sequence to extract discriminative information that was not captured by preceding codebooks and their corresponding classifiers. We apply this framework to two application domains: visual object categorization and document classification. Experiments on large classification tasks show substantial improvements in performance compared to a single codebook or codebooks learned in a bagging style. 1.

As datasets grow increasingly large in content-based image and video retrieval, computational efficiency of concept classification is important. This paper reviews techniques to accelerate concept classification, where we show the trade-off between computational efficiency and accuracy. As a basis, we use the Bag-of-Words algorithm that in the 2008 benchmarks of TRECVID and PASCAL lead to the best performance scores. We divide the evaluation in three steps: 1) Descriptor Extraction, where we evaluate SIFT, SURF, DAISY, and Semantic Textons. 2) Visual Word Assignment, where we compare a k-means visual vocabulary with a Random Forest and evaluate subsampling, dimension reduction with PCA, and division strategies of the Spatial Pyramid. 3) Classification, where we evaluate the 2, RBF, and Fast Histogram Intersection kernel for the SVM. Apart from the evaluation, we accelerate the calculation of densely sampled SIFT and SURF, accelerate nearest neighbor assignment, and improve accuracy of the Histogram Intersection kernel. We conclude by discussing whether further acceleration of the Bag-of-Words pipeline is possible. Our results lead to a 7-fold speed increase without accuracy loss, and a 70-fold speed increase with 3 % accuracy loss. The latter system does classification in real-time, which opens up new applications for automatic concept classification. For example, this system permits five standard desktop PCs to automatically tag for 20 classes all images that are currently uploaded to Flickr.

Random Forests (RFs) are frequently used in many computer vision and machine learning applications. Their popularity is mainly driven by their high computational efficiency during both training and evaluation while still achieving state-of-the-art results. However, in most applications RFs are used off-line. This limits their usability for many practical problems, for instance, when training data arrives sequentially or the underlying distribution is continuously changing. In this paper, we propose a novel on-line random forest algorithm. We combine ideas from on-line bagging, extremely randomized forests and propose an on-line decision tree growing procedure. Additionally, we add a temporal weighting scheme for adaptively discarding some trees based on their out-of-bag-error in given time intervals and consequently growing of new trees. The experiments on common machine learning data sets show that our algorithm converges to the performance of the off-line RF. Additionally, we conduct experiments for visual tracking, where we demonstrate real-time state-of-the-art performance on wellknown scenarios and show good performance in case of occlusions and appearance changes where we outperform trackers based on on-line boosting. Finally, we demonstrate the usability of on-line RFs on the task of interactive realtime segmentation. 1.

Human-aided computing proposes using information measured directly from the human brain in order to perform useful tasks. In this paper, we extend this idea by fusing computer vision-based processing and processing done by the human brain in order to build more effective object categorization systems. Specifically, we use an electroencephalograph (EEG) device to measure the subconscious cognitive processing that occurs in the brain as users see images, even when they are not trying to explicitly classify them. We present a novel framework that combines a discriminative visual category recognition system based on the Pyramid Match Kernel (PMK) with information derived from EEG measurements as users view images. We propose a fast convex kernel alignment algorithm to effectively combine the two sources of information. Our approach is validated with experiments using real-world data, where we show significant gains in classification accuracy. We analyze the properties of this information fusion method by examining the relative contributions of the two modalities, the errors arising from each source, and the stability of the combination in repeated experiments. 1.

A new method for localising and recognising hand poses and objects in real-time is presented. This problem is important in vision-driven applications where it is natural for a user to combine hand gestures and real objects when interacting with a machine. Examples include using a real eraser to remove words from a document displayed on an electronic surface. In this paper the task of simultaneously recognising object classes, hand gestures and detecting touch events is cast as a single classification problem. A random forest algorithm is employed which adaptively selects and combines a minimal set of appearance, shape and stereo features to achieve maximum class discrimination for a given image. This minimal set leads to both efficiency at run time and good generalisation. Unlike previous stereo works which explicitly construct disparity maps, here the stereo matching costs are used directly as visual cue and only computed on-demand, i.e. only for pixels where they are necessary for recognition. This leads to improved efficiency. The proposed method is assessed on a database of a variety of objects and hand poses selected for interacting on a flat surface in an office environment. 1.

Visual categorization is important to manage large collections of digital images and video, where textual metadata is often incomplete or simply unavailable. The bag-of-words model has become the most powerful method for visual categorization of images and video. Despite its high accuracy, a severe drawback of this model is its high computational cost. As the trend to increase computational power in newer CPU and GPU architectures is to increase their level of parallelism, exploiting this parallelism becomes an important direction to handle the computational cost of the bag-of-words approach. When optimizing a system based on the bag-of-words approach, the goal is to minimize the time it takes to process batches of images. In this paper, we analyze the bag-of-words model for visual categorization in terms of computational cost and identify two major bottlenecks: the quantization step and the classification step. We address these two bottlenecks by proposing two efficient algorithms for quantization and classification by exploiting the GPU hardware and the CUDA parallel programming model. The algorithms are designed to 1) keep categorization accuracy intact, 2) decompose the problem, and 3) give the same numerical results. In the experiments on large scale datasets, it is shown that, by using a parallel implementation on the Geforce GTX260 GPU, classifying unseen images is 4.8 times faster than a quad-core CPU version on the Core i7 920, while giving the exact same numerical results. In addition, we show how the algorithms can be generalized to other applications, such as text retrieval and video retrieval. Moreover, when the obtained speedup is used to process extra video frames in a video retrieval benchmark, the accuracy of visual categorization is improved by 29%.

The extraction and quantization of local image and video descriptors for the subsequent creation of visual codebooks is a technique that has proved extremely effective for image and video retrieval applications. In this paper we build on this concept and extract a new set of visual descriptors that are derived from spatiotemporal salient points detected on given image sequences and provide local space-time description of the visual activity. The proposed descriptors are based on the geometrical properties of three-dimensional piecewise polynomials, namely B-splines, that are fitted on the spatiotemporal locations of the salient points that are engulfed within a given spatiotemporal neighborhood. Our descriptors are inherently translation invariant, while the use of the scales of the salient points for the definition of the neighborhood dimensions ensures space-time scaling invariance. Subsequently, a clustering algorithm is used in order to cluster our descriptors across the whole dataset and create a codebook of visual verbs, where each verb corresponds to a cluster center. We use the resulting codebook in a ’bag of verbs ’ approach in order to recover the pose and short-term motion of subjects at a short set of successive frames, and we use Dynamic Time Warping (DTW) in order to align the sequences in our dataset and structure in time the recovered poses. We define a kernel based on the similarity measure provided by the DTW to classify our examples in a Relevane Vector Machine classification scheme. We present results in a well established human activity database to verify the effectiveness of our method. 1.

We propose a new supervised learning framework for visual object counting tasks, such as estimating the number of cells in a microscopic image or the number of humans in surveillance video frames. We focus on the practically-attractive case when the training images are annotated with dots (one dot per object). Our goal is to accurately estimate the count. However, we evade the hard task of learning to detect and localize individual object instances. Instead, we cast the problem as that of estimating an image density whose integral over any image region gives the count of objects within that region. Learning to infer such density can be formulated as a minimization of a regularized risk quadratic cost function. We introduce a new loss function, which is well-suited for such learning, and at the same time can be computed efficiently via a maximum subarray algorithm. The learning can then be posed as a convex quadratic program solvable with cutting-plane optimization. The proposed framework is very flexible as it can accept any domain-specific visual features. Once trained, our system provides accurate object counts and requires a very small time overhead over the feature extraction step, making it a good candidate for applications involving real-time processing or dealing with huge amount of visual data. 1