We propose an algorithm for learning the semantics of a (motion) verb from videos depicting the action expressed by the verb, paired with sentences describing the action participants and their roles. Acknowledging tha...
详细信息
We propose an algorithm for learning the semantics of a (motion) verb from videos depicting the action expressed by the verb, paired with sentences describing the action participants and their roles. Acknowledging that commonalities among example videos may not exist at the level of the input features, our approximation algorithm efficiently searches the space of more abstract features for a common solution. We test our algorithm by using it to learn the semantics of a sample set of verbs; results demonstrate the usefulness of the proposed framework, while identifying directions for further improvement.
Automatic construction of shape and appearance models from examples via establishing correspondences across the training set has been successful in the last decades. One successful measure for establishing corresponde...
详细信息
Automatic construction of shape and appearance models from examples via establishing correspondences across the training set has been successful in the last decades. One successful measure for establishing correspondences of high quality is minimum description length (MDL). In other approaches it has been shown that parts+geometry models which model the appearance of parts of the object and the geometric relation between the parts have been successful for automatic model building. In this paper it is shown how to fuse the above approaches and use MDL to fully automatically build optimal parts+geometry models from unlabeled images.
We present an active learning approach for visual multiple object class recognition, using a conditional random field (CRF) formulation. We name our graphical model dasiacollaborativepsila, because it infers class pos...
详细信息
We present an active learning approach for visual multiple object class recognition, using a conditional random field (CRF) formulation. We name our graphical model dasiacollaborativepsila, because it infers class posteriors in in stances of occlusion and missing information by assessing the joint appearance and geometric assortment of neighboring sites. The model can handle scenes containing multiple classes and multiple objects inherently while using the confidence of its predictions to enforce label uniformity in areas where evidence supports similarity. Our method uses classification uncertainty to dynamically select new training samples to retrain the discriminative classifiers used in the CRF. We demonstrate the performance of our approach using cluttered scenes containing multiple objects and multiple class instances.
We propose a novel approach to 3D hand geometry based person authentication using projected light patterns. Instead of explicitly computing a depth map of the palm for recognition, we capture the depth information in ...
详细信息
We propose a novel approach to 3D hand geometry based person authentication using projected light patterns. Instead of explicitly computing a depth map of the palm for recognition, we capture the depth information in the deformations of a projected texture pattern, and use it directly for recognition. The deformed pattern is characterized using local texture measures, which can encode the certain depth characteristics of the palm. An authentication system built using the proposed technique achieves an equal error rate of 0.84% on a dataset of 1341 samples collected from 149 users, as opposed to 4.03% using traditional 2D features on an identical dataset. The approach is robust as well as computationally efficient and could be applied to other 3D object recognition problems as well.
This paper address the problem of automatically extracting the 3D configurations of deformable objects from 2D features. Our focus in this work is to build on the observation that the subspace spanned by the motion pa...
详细信息
This paper address the problem of automatically extracting the 3D configurations of deformable objects from 2D features. Our focus in this work is to build on the observation that the subspace spanned by the motion parameters is a subset of a smooth manifold, and therefore we hunt for the solution in this space, rather than use heuristics (as previously attempted earlier). We succeed in this by attaching a canonical Riemannian metric, and using a variant of the non-rigid factorisation algorithm for structure from motion. We qualitatively and quantitatively show that our algorithm produces better results when compared to the state of art.
Partial matching is probably one of the most challenging problems in nonrigid shape analysis. The problem consists of matching similar parts of shapes that are dissimilar on the whole and can assume different forms by...
详细信息
Partial matching is probably one of the most challenging problems in nonrigid shape analysis. The problem consists of matching similar parts of shapes that are dissimilar on the whole and can assume different forms by undergoing nonrigid deformations. Conceptually, two shapes can be considered partially matching if they have significant similar parts, with the simplest definition of significance being the size of the parts. Thus, partial matching can be defined as a multicriterion optimization problem trying to simultaneously maximize the similarity and the size of these parts. In this paper, we propose a different definition of significance, taking into account the regularity of parts besides their size. The regularity term proposed here is similar to the spirit of the Mumford-Shah functional. Numerical experiments show that the regularized partial matching produces semantically better results compared to the non-regularized one.
This paper makes use of the continuous eccentricity transform to perform 3D shape matching. The eccentricity transform has already been proved useful in a discrete graph-theoretic setting and has been applied to 2D sh...
详细信息
This paper makes use of the continuous eccentricity transform to perform 3D shape matching. The eccentricity transform has already been proved useful in a discrete graph-theoretic setting and has been applied to 2D shape matching. We show how these ideas extend to higher dimensions. The eccentricity transform is used to compute descriptors for 3D shapes. These descriptors are defined as histograms of the eccentricity transform and are naturally invariant to Euclidean motion and articulation. They show promising results for shape discrimination.
The Laplacian raised to fractional powers can be used to generate scale spaces as was shown in recent literature. This was later extended for inhomogeneous diffusion processes and more general functions of the Laplaci...
详细信息
The Laplacian raised to fractional powers can be used to generate scale spaces as was shown in recent literature. This was later extended for inhomogeneous diffusion processes and more general functions of the Laplacian and studied for the Perona-Malik case. In this paper we extend the results to the truly anisotropic Beltrami flow. We additionally introduce a technique for splitting up the work into smaller patches of the image which greatly reduce the computational complexity and allow for the parallelization of the algorithm. Important issues involved in the numerical implementation are discussed.
This paper illustrates our recent work on the analysis of expressive gesture related to the motion of the upper body (the head and the hands) in the context of emotional portrayals performed by professional actors. An...
详细信息
This paper illustrates our recent work on the analysis of expressive gesture related to the motion of the upper body (the head and the hands) in the context of emotional portrayals performed by professional actors. An experiment is presented which is the result of a multidisciplinary joint work. The experiment aims at (i) developing models and algorithms for analysis of such expressive content (ii) individuating which motion cues are involved in conveying the actorpsilas expressive intentions to portray four emotions (anger, joy, relief, sadness) via a scenario approach. The paper discusses the experiment in detail with reference to related conceptual issues, developed techniques, and the obtained results.
Human age prediction is useful for many applications. The age information could be used as a kind of semantic knowledge for multimedia content analysis and understanding. In this paper we propose a probabilistic fusio...
详细信息
Human age prediction is useful for many applications. The age information could be used as a kind of semantic knowledge for multimedia content analysis and understanding. In this paper we propose a probabilistic fusion approach (PFA) that produces a high performance estimator for human age prediction. The PFA framework fuses a regressor and a classifier. We derive the predictor based on Bayespsila rule without the mutual independence assumption that is very common for traditional classifier combination methods. Using a sequential fusion strategy, the predictor reduces age estimation errors significantly. Experiments on the large UIUC-IFP-Y aging database and the FG-NET aging database show the merit of the proposed approach to human age prediction.
暂无评论