Blind face inpainting refers to the task of reconstructing visual contents without explicitly indicating the corrupted regions in a face image. Inherently, this task faces two challenges: (1) how to detect various mask patterns of different shapes and contents; (2) how to restore visually plausible and pleasing contents in the masked regions. In this paper, we propose a novel two-stage blind face inpainting method named Frequency-guided Transformer and Top-Down Refinement Network (FT-TDR) to tackle these challenges. Specifically, we first use a transformer-based network to detect the corrupted regions to be inpainted as masks by modeling the relation among different patches. We also exploit the frequency modality as complementary information for improved detection results and capture the local contextual incoherence to enhance boundary consistency. Then a top-down refinement network is proposed to hierarchically restore features at different levels and generate contents that are semantically consistent with the unmasked face regions. Extensive experiments demonstrate that our method outperforms current state-of-the-art blind and non-blind face inpainting methods qualitatively and quantitatively.
This paper is about pregroup models of natural languages, and how they relate to the explicitly categorical use of pregroups in Compositional Distributional Semantics and Natural Language Processing. These categorical interpretations make certain assumptions about the nature of natural languages that, when stated formally, may be seen to impose strong restrictions on pregroup grammars for natural languages. We formalize this as a hypothesis about the form that pregroup models of natural languages must take, and demonstrate by an artificial language example that these restrictions are not imposed by the pregroup axioms themselves. We compare and contrast the artificial language examples with natural languages (using Welsh, a language where the 'noun' type cannot be taken as primitive, as an illustrative example). The hypothesis is simply that there must exist a causal connection, or information flow, between the words of a sentence in a language whose purpose is to communicate information. This is not necessarily the case with formal languages that are simply generated by a series of 'meaning-free' rules. This imposes restrictions on the types of pregroup grammars that we expect to find in natural languages; we formalize this in algebraic, categorical, and graphical terms. We take some preliminary steps in providing conditions that ensure pregroup models satisfy these conjectured properties, and discuss the more general forms this hypothesis may take.
For a multivariate normal distribution, the sparsity of the covariance and precision matrices encodes complete information about independence and conditional independence properties. For general distributions, the covariance and precision matrices reveal correlations and so-called partial correlations between variables, but these do not, in general, have any correspondence with respect to independence properties. In this paper, we prove that, for a certain class of non-Gaussian distributions, these correspondences still hold, exactly for the covariance and approximately for the precision. The distributions -- sometimes referred to as "nonparanormal" -- are given by diagonal transformations of multivariate normal random variables. We provide several analytic and numerical examples illustrating these results.
Location-aware networks will introduce innovative services and applications for modern convenience, applied ocean sciences, and public safety. In this paper, we establish a hybrid method for model-based and data-driven inference. We consider a cooperative localization (CL) scenario where the mobile agents in a wireless network aim to localize themselves by performing pairwise observations with other agents and by exchanging location information. A traditional method for distributed CL in large agent networks is belief propagation (BP) which is completely model-based and is known to suffer from providing inconsistent (overconfident) estimates. The proposed approach addresses these limitations by complementing BP with learned information provided by a graph neural network (GNN). We demonstrate numerically that our method can improve estimation accuracy and avoid overconfident beliefs, while its computational complexity remains comparable to BP. Notably, more consistent beliefs are obtained by not explicitly addressing overconfidence in the loss function used for training of the GNN.
This dissertation proposes the study of multimodal learning in the context of musical signals. Throughout, we focus on the interaction between audio signals and text information. Among the many text sources related to music that can be used (e.g. reviews, metadata, or social network feedback), we concentrate on lyrics. The singing voice directly connects the audio signal and the text information in a unique way, combining melody and lyrics where a linguistic dimension complements the abstraction of musical instruments. Our study focuses on the audio and lyrics interaction for targeting source separation and informed content estimation.
Dynamic objects in the environment, such as people and other agents, lead to challenges for existing simultaneous localization and mapping (SLAM) approaches. To deal with dynamic environments, computer vision researchers usually apply some learning-based object detectors to remove these dynamic objects. However, these object detectors are computationally too expensive for mobile robot on-board processing. In practical applications, these objects output noisy sounds that can be effectively detected by on-board sound source localization. The directional information of the sound source object can be efficiently obtained by direction of sound arrival (DoA) estimation, but depth estimation is difficult. Therefore, in this paper, we propose a novel audio-visual fusion approach that fuses sound source direction into the RGB-D image and thus removes the effect of dynamic obstacles on the multi-robot SLAM system. Experimental results of multi-robot SLAM in different dynamic environments show that the proposed method uses very small computational resources to obtain very stable self-localization results.
Good quality reconstruction and comprehension of a scene rely on 3D estimation methods. The 3D information was usually obtained from images by stereo-photogrammetry, but deep learning has recently provided us with excellent results for monocular depth estimation. Building up a sufficiently large and rich training dataset to achieve these results requires onerous processing. In this paper, we address the problem of learning outdoor 3D point cloud from monocular data using a sparse ground-truth dataset. We propose Pix2Point, a deep learning-based approach for monocular 3D point cloud prediction, able to deal with complete and challenging outdoor scenes. Our method relies on a 2D-3D hybrid neural network architecture, and a supervised end-to-end minimisation of an optimal transport divergence between point clouds. We show that, when trained on sparse point clouds, our simple promising approach achieves a better coverage of 3D outdoor scenes than efficient monocular depth methods.
Visually-aware recommendation on E-commerce platforms aims to leverage visual information of items to predict a user's preference. It is commonly observed that user's attention to visual features does not always reflect the real preference. Although a user may click and view an item in light of a visual satisfaction of their expectations, a real purchase does not always occur due to the unsatisfaction of other essential features (e.g., brand, material, price). We refer to the reason for such a visually related interaction deviating from the real preference as a visual bias. Existing visually-aware models make use of the visual features as a separate collaborative signal similarly to other features to directly predict the user's preference without considering a potential bias, which gives rise to a visually biased recommendation. In this paper, we derive a causal graph to identify and analyze the visual bias of these existing methods. In this causal graph, the visual feature of an item acts as a mediator, which could introduce a spurious relationship between the user and the item. To eliminate this spurious relationship that misleads the prediction of the user's real preference, an intervention and a counterfactual inference are developed over the mediator. Particularly, the Total Indirect Effect is applied for a debiased prediction during the testing phase of the model. This causal inference framework is model agnostic such that it can be integrated into the existing methods. Furthermore, we propose a debiased visually-aware recommender system, denoted as CausalRec to effectively retain the supportive significance of the visual information and remove the visual bias. Extensive experiments are conducted on eight benchmark datasets, which shows the state-of-the-art performance of CausalRec and the efficacy of debiasing.
Micro-expressions are spontaneous, unconscious facial movements that show people's true inner emotions and have great potential in related fields of psychological testing. Since the face is a 3D deformation object, the occurrence of an expression can arouse spatial deformation of the face, but limited by the available databases are 2D videos, lacking the description of 3D spatial information of micro-expressions. Therefore, we proposed a new micro-expression database containing 2D video sequences and 3D point clouds sequences. The database includes 259 micro-expressions sequences, and these samples were classified using the objective method based on facial action coding system, as well as the non-objective method that combines video contents and participants' self-reports. We extracted 2D and 3D features using the local binary patterns on three orthogonal planes (LBP-TOP) and curvature algorithms, respectively, and evaluated the classification accuracies of these two features and their fusion results with leave-one-subject-out (LOSO) and 10-fold cross-validation. Further, we performed various neural network algorithms for database classification, the results show that classification accuracies are improved by fusing 3D features than using only 2D features. The database offers original and cropped micro-expression samples, which will facilitate the exploration and research on 3D Spatio-temporal features of micro-expressions.
Aiming at the problem that delay time is difficult to determine and prediction accuracy is low in building prediction model of SCR system, a dynamic modeling scheme based on a hybrid of multiple data-driven algorithms was proposed. First, processed abnormal values and normalized the data. To improve the relevance of the input data, used MIC to estimate delay time and reconstructed production data. Then used combined feature selection method to determine input variables. To further mine data information, VMD was used to decompose input time series. Finally, established NOx emission prediction model combining ELM and EC model. Experimental results based on actual historical operating data show that the MAPE of predicted results is 2.61%. Model sensitivity analysis shows that besides the amount of ammonia injection, the inlet oxygen concentration and the flue gas temperature have a significant impact on NOx emission, which should be considered in SCR process control and optimization.