We address the problem of human motion tracking by registering a surface to 3-D data. We propose a method that iteratively computes two things: Maximum likelihood estimates for both the kinematic and free-motion parameters of a kinematic human-body representation, as well as probabilities that the data are assigned either to a body part, or to an outlier cluster. We introduce a new metric between observed points and normals on one side, and a parameterized surface on the other side, the latter being defined as a blending over a set of ellipsoids. We claim that this metric is well suited when one deals with either visual-hull or visual-shape observations. We illustrate the method by tracking human motions using sparse visual-shape data (3-D surface points and normals) gathered from imperfect silhouettes.
This paper addresses the problem of sound-source localization (SSL) with a robot head, which remains a challenge in real-world environments. In particular we are interested in locating speech sources, as they are of high interest for human-robot interaction. The microphone-pair response corresponding to the direct-path sound propagation is a function of the source direction. In practice, this response is contaminated by noise and reverberations. The direct-path relative transfer function (DP-RTF) is defined as the ratio between the direct-path acoustic transfer function (ATF) of the two microphones, and it is an important feature for SSL. We propose a method to estimate the DP-RTF from noisy and reverberant signals in the short-time Fourier transform (STFT) domain. First, the convolutive transfer function (CTF) approximation is adopted to accurately represent the impulse response of the microphone array, and the first coefficient of the CTF is mainly composed of the direct-path ATF. At each frequency, the frame-wise speech auto- and cross-power spectral density (PSD) are obtained by spectral subtraction. Then a set of linear equations is constructed by the speech auto- and cross-PSD of multiple frames, in which the DP-RTF is an unknown variable, and is estimated by solving the equations. Finally, the estimated DP-RTFs are concatenated across frequencies and used as a feature vector for SSL. Experiments with a robot, placed in various reverberant environments, show that the proposed method outperforms two state-of-the-art methods.
Face frontalization consists of synthesizing a frontally-viewed face from an arbitrarily-viewed one. The main contribution of this paper is a robust face alignment method that enables pixel-to-pixel warping. The method simultaneously estimates the \textit{rigid transformation} (scale, rotation, and translation) and the \textit{non-rigid deformation} between two 3D point sets: a set of 3D landmarks extracted from an arbitrary-viewed face, and a set of 3D landmarks parameterized by a frontally-viewed deformable face model. An important merit of the proposed method is its ability to deal both with noise (small perturbations) and with outliers (large errors). We propose to model inliers and outliers with the generalized Student's t-probability distribution function -- a heavy-tailed distribution that is immune to non-Gaussian errors in the data. We describe in detail the associated expectation-maximization (EM) algorithm that alternates between the estimation of (i)~the rigid parameters, (ii)~the deformation parameters, and (iii)~ the t-distribution parameters. We also propose to use the \textit{zero-mean normalized cross-correlation}, between a frontalized face and the corresponding ground-truth frontally-viewed face, to evaluate the performance of frontalization. To this end, we use a dataset that contains pairs of profile-viewed and frontally-viewed faces. This evaluation, based on direct image-to-image comparison, stands in contrast with indirect evaluation, based on analyzing the effect of frontalization on face recognition.
Visual voice activity detection (V-VAD) uses visual features to predict whether a person is speaking or not. V-VAD is useful whenever audio VAD (A-VAD) is inefficient either because the acoustic signal is difficult to analyze or because it is simply missing. We propose two deep architectures for V-VAD, one based on facial landmarks and one based on optical flow. Moreover, available datasets, used for learning and for testing V-VAD, lack content variability. We introduce a novel methodology to automatically create and annotate very large datasets in-the-wild -- WildVVAD -- based on combining A-VAD with face detection and tracking. A thorough empirical evaluation shows the advantage of training the proposed deep V-VAD models with this dataset.
Modeling the temporal behavior of data is of primordial importance in many scientific and engineering fields. The baseline method assumes that both the dynamic and observation models follow linear-Gaussian models. Non-linear extensions lead to intractable solvers. It is also possible to consider several linear models, or a piecewise linear model, and to combine them with a switching mechanism, which is also intractable because of the exponential explosion of the number of Gaussian components. In this paper, we propose a variational approximation of piecewise linear dynamic systems. We provide full details of the derivation of a variational expectation-maximization algorithm that can be used either as a filter or as a smoother. We show that the model parameters can be split into two sets, a set of static (or observation parameters) and a set of dynamic parameters. The immediate consequences are that the former set can be estimated off-line and that the number of linear models (or the number of states of the switching variable) can be learned based on model selection. We apply the proposed method to the problem of visual tracking and we thoroughly compare our algorithm with several visual trackers applied to the problem of head-pose estimation.
We address the problem of analyzing the performance of 3D face alignment (3DFA) algorithms. Traditionally, performance analysis relies on carefully annotated datasets. Here, these annotations correspond to the 3D coordinates of a set of pre-defined facial landmarks. However, this annotation process, be it manual or automatic, is rarely error-free, which strongly biases the analysis. In contrast, we propose a fully unsupervised methodology based on robust statistics and a parametric confidence test. We revisit the problem of robust estimation of the rigid transformation between two point sets and we describe two algorithms, one based on a mixture between a Gaussian and a uniform distribution, and another one based on the generalized Student's t-distribution. We show that these methods are robust to up to 50\% outliers, which makes them suitable for mapping a face, from an unknown pose to a frontal pose, in the presence of facial expressions and occlusions. Using these methods in conjunction with large datasets of face images, we build a statistical frontal facial model and an associated parametric confidence metric, eventually used for performance analysis. We empirically show that the proposed pipeline is neither method-biased nor data-biased, and that it can be used to assess both the performance of 3DFA algorithms and the accuracy of annotations of face datasets.
This paper presents a generative approach to speech enhancement based on a recurrent variational autoencoder (RVAE). The deep generative speech model is trained using clean speech signals only, and it is combined with a nonnegative matrix factorization noise model for speech enhancement. We propose a variational expectation-maximization algorithm where the encoder of the RVAE is fine-tuned at test time, to approximate the distribution of the latent variables given the noisy speech observations. Compared with previous approaches based on feed-forward fully-connected architectures, the proposed recurrent deep generative speech model induces a posterior temporal dynamic over the latent variables, which is shown to improve the speech enhancement results.
Variational auto-encoders (VAEs) are deep generative latent variable models that can be used for learning the distribution of complex data. VAEs have been successfully used to learn a probabilistic prior over speech signals, which is then used to perform speech enhancement. One advantage of this generative approach is that it does not require pairs of clean and noisy speech signals at training. In this paper, we propose audio-visual variants of VAEs for single-channel and speaker-independent speech enhancement. We develop a conditional VAE (CVAE) where the audio speech generative process is conditioned on visual information of the lip region. At test time, the audio-visual speech generative model is combined with a noise model based on nonnegative matrix factorization, and speech enhancement relies on a Monte Carlo expectation-maximization algorithm. Experiments are conducted with the recently published NTCD-TIMIT dataset. The results confirm that the proposed audio-visual CVAE effectively fuse audio and visual information, and it improves the speech enhancement performance compared with the audio-only VAE model, especially when the speech signal is highly corrupted by noise. We also show that the proposed unsupervised audio-visual speech enhancement approach outperforms a state-of-the-art supervised deep learning method.
Multiple Object Tracking accuracy and precision (MOTA and MOTP) are two standard and widely-used metrics to assess the quality of multiple object trackers. They are specifically designed to encode the challenges and difficulties of tracking multiple objects. To directly optimize a tracker based on MOTA and MOTP is difficult, since both the metrics are strongly rely on the Hungarian algorithm, which are non-differentiable. We propose a differentiable proxy for the MOTA and MOTP, thus allowing to train a deep multiple-object tracker by directly optimizing (a proxy of) the standard MOT metrics. The proposed approximation is based on a bidirectional recurrent network that inputs the object-to-hypothesis distance matrix and outputs the optimal hypothesis-to-object association, thus emulating the Hungarian algorithm. Followed by a differentiable module, the estimated association is used to compute the MOTA and MOTP. The experimental study demonstrates the benefits of this differentiable framework on two recent deep trackers over the MOT17 dataset. Moreover, the code is publicly available from https://gitlab.inria.fr/yixu/deepmot.