In this paper we compare the performance of descriptors computed for local interest regions, as for example extracted by the Harris-Affine detector [32]. Many different descriptors have been proposed in the literature. However, it is unclear which descriptors are more appropriate and how their performance depends on the interest region detector. The descriptors should be distinctive and at the same time robust to changes in viewing conditions as well as to errors of the detector. Our evaluation uses as criterion recall with respect to precision and is carried out for different image transformations. We compare shape context [3], steerable filters [12], PCA-SIFT [19], differential invariants [20], spin images [21], SIFT [26], complex filters [37], moment invariants [43], and cross-correlation for different types of interest regions. We also propose an extension of the SIFT descriptor, and show that it outperforms the original method. Furthermore, we observe that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT based descriptors perform best. Moments and steerable filters show the best performance among the low dimensional descriptors.

Figure 1 An image analogy. Our problem is to compute a new “analogous ” image B ′ that relates to B in “the same way ” as A ′ relates to A. Here, A, A ′ , and B are inputs to our algorithm, and B ′ is the output. The full-size images are shown in Figures 10 and 11. This paper describes a new framework for processing images by example, called “image analogies. ” The framework involves two stages: a design phase, in which a pair of images, with one image purported to be a “filtered ” version of the other, is presented as “training data”; and an application phase, in which the learned filter is applied to some new target image in order to create an “analogous” filtered result. Image analogies are based on a simple multiscale autoregression, inspired primarily by recent results in texture synthesis. By choosing different types of source image pairs as input, the framework supports a wide variety of “image filter ” effects, including traditional image filters, such as blurring or embossing; improved texture synthesis, in which some textures are synthesized with higher quality than by previous approaches; super-resolution, in which a higher-resolution image is inferred from a low-resolution source; texture transfer, in which images are “texturized ” with some arbitrary source texture; artistic filters, in which various drawing and painting styles are synthesized based on scanned real-world examples; and texture-by-numbers, in which realistic scenes, composed of a variety of textures, are created using a simple painting interface.

We show how to use “complementary priors ” to eliminate the explaining away effects that make inference difficult in densely-connected belief nets that have many hidden layers. Using complementary priors, we derive a fast, greedy algorithm that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory. The fast, greedy algorithm is used to initialize a slower learning procedure that fine-tunes the weights using a contrastive version of the wake-sleep algorithm. After fine-tuning, a network with three hidden layers forms a very good generative model of the joint distribution of handwritten digit images and their labels. This generative model gives better digit classification than the best discriminative learning algorithms. The low-dimensional manifolds on which the digits lie are modelled by long ravines in the free-energy landscape of the top-level associative memory and it is easy to explore these ravines by using the directed connections to display what the associative memory has in mind. 1

Our goal is to recognize human actions at a distance, at resolutions where a whole person may be, say, 30 pixels tall. We introduce a novel motion descriptor based on optical flow measurements in a spatio-temporal volume for each stabilized human figure, and an associated similarity measure to be used in a nearest-neighbor framework. Making use of noisy optical flow measurements is the key challenge, which is addressed by treating optical flow not as precise pixel displacements, but rather as a spatial pattern of noisy measurements which are carefully smoothed and aggregated to form our spatio-temporal motion descriptor. To classify the action being performed by a human figure in a query sequence, we retrieve nearest neighbor(s) from a database of stored, annotated video sequences. We can also use these retrieved exemplars to transfer 2D/3D skeletons onto the figures in the query sequence, as well as two forms of data-based action synthesis "Do as I Do" and "Do as I Say". Results are demonstrated on ballet, tennis as well as football datasets.

Discriminative learning is challenging when examples are sets of features, and the sets vary in cardinality and lack any sort of meaningful ordering. Kernel-based classification methods can learn complex decision boundaries, but a kernel over unordered set inputs must somehow solve for correspondences – generally a computationally expensive task that becomes impractical for large set sizes. We present a new fast kernel function which maps unordered feature sets to multi-resolution histograms and computes a weighted histogram intersection in this space. This “pyramid match ” computation is linear in the number of features, and it implicitly finds correspondences based on the finest resolution histogram cell where a matched pair first appears. Since the kernel does not penalize the presence of extra features, it is robust to clutter. We show the kernel function is positive-definite, making it valid for use in learning algorithms whose optimal solutions are guaranteed only for Mercer kernels. We demonstrate our algorithm on object recognition tasks and show it to be accurate and dramatically faster than current approaches. 1.

Human action in video sequences can be seen as silhouettes of a moving torso and protruding limbs undergoing articulated motion. We regard human actions as three-dimensional shapes induced by the silhouettes in the space-time volume. We adopt a recent approach [14] for analyzing 2D shapes and generalize it to deal with volumetric space-time action shapes. Our method utilizes properties of the solution to the Poisson equation to extract space-time features such as local space-time saliency, action dynamics, shape structure and orientation. We show that these features are useful for action recognition, detection and clustering. The method is fast, does not require video alignment and is applicable in (but not limited to) many scenarios where the background is known. Moreover, we demonstrate the robustness of our method to partial occlusions, non-rigid deformations, significant changes in scale and viewpoint, high irregularities in the performance of an action, and low quality video. Index Terms Action representation, action recognition, space-time analysis, shape analysis, poisson equation

We show how to learn a Mahanalobis distance metric for k-nearest neighbor (kNN) classification by semidefinite programming. The metric is trained with the goal that the k-nearest neighbors always belong to the same class while examples from different classes are separated by a large margin. On seven data sets of varying size and difficulty, we find that metrics trained in this way lead to significant improvements in kNN classification—for example, achieving a test error rate of 1.3 % on the MNIST handwritten digits. As in support vector machines (SVMs), the learning problem reduces to a convex optimization based on the hinge loss. Unlike learning in SVMs, however, our framework requires no modification or extension for problems in multiway (as opposed to binary) classification. 1

We have witnessed great interest and a wealth of promise in content-based image retrieval as an emerging technology. While the last decade laid foundation to such promise, it also paved the way for a large number of new techniques and systems, got many new people involved, and triggered stronger association of weakly related fields. In this article, we survey almost 300 key theoretical and empirical contributions in the current decade related to image retrieval and automatic image annotation, and in the process discuss the spawning of related subfields. We also discuss significant challenges involved in the adaptation of existing image retrieval techniques to build systems that can be useful in the real world. In retrospect of what has been achieved so far, we also conjecture what the future may hold for image retrieval research.

We consider visual category recognition in the framework of measuring similarities, or equivalently perceptual distances, to prototype examples of categories. This approach is quite flexible, and permits recognition based on color, texture, and particularly shape, in a homogeneous framework. While nearest neighbor classifiers are natural in this setting, they suffer from the problem of high variance (in bias-variance decomposition) in the case of limited sampling. Alternatively, one could use support vector machines but they involve time-consuming optimization and computation of pairwise distances. We propose a hybrid of these two methods which deals naturally with the multiclass setting, has reasonable computational complexity both in training and at run time, and yields excellent results in practice. The basic idea is to find close neighbors to a query sample and train a local support vector machine that preserves the distance function on the collection of neighbors. Our method can be applied to large, multiclass data sets for which it outperforms nearest neighbor and support vector machines, and remains efficient when the problem becomes intractable for support vector machines. A wide variety of distance functions can be used and our experiments show state-of-the-art performance on a number of benchmark data sets for shape and texture classification (MNIST, USPS, CUReT) and object recognition (Caltech-101). On Caltech-101 we achieved a correct classification rate of 59.05%(±0.56%) at 15 training images per class, and 66.23%(±0.48%) at 30 training images. 1.

Feature-based methods for non-rigid registration frequently encounter the correspondence problem. Regardless of whether points, lines, curves or surface parameterizations are used, feature-based non-rigid matching requires us to automatically solve for correspondences between two sets of features. In addition, there could be many features in either set that have no counterparts in the other. This outlier rejection problem further complicates an already di#cult correspondence problem. We formulate feature-based non-rigid registration as a non-rigid point matching problem. After a careful review of the problem and an in-depth examination of two types of methods previously designed for rigid robust point matching (RPM), we propose a new general framework for non-rigid point matching. We consider it a general framework because it does not depend on any particular form of spatial mapping. We have also developed an algorithm---the TPS-RPM algorithm---with the thin-plate spline (TPS) as the parameterization of the non-rigid spatial mapping and the softassign for the correspondence. The performance of the TPS-RPM algorithm is demonstrated and validated in a series of carefully designed synthetic experiments. In each of these experiments, an empirical comparison with the popular iterated closest point (ICP) algorithm is also provided. Finally, we apply the algorithm to the problem of non-rigid registration of cortical anatomical structures which is required in brain mapping. While these results are somewhat preliminary, they clearly demonstrate the applicability of our approach to real world tasks involving feature-based non-rigid registration.