In this work we tackle the task of video-based visual emotion recognition in the wild. Standard methodologies that rely solely on the extraction of bodily and facial features often fall short of accurate emotion prediction in cases where the aforementioned sources of affective information are inaccessible due to head/body orientation, low resolution and poor illumination. We aspire to alleviate this problem by leveraging visual context in the form of scene characteristics and attributes, as part of a broader emotion recognition framework. Temporal Segment Networks (TSN) constitute the backbone of our proposed model. Apart from the RGB input modality, we make use of dense Optical Flow, following an intuitive multi-stream approach for a more effective encoding of motion. Furthermore, we shift our attention towards skeleton-based learning and leverage action-centric data as means of pre-training a Spatial-Temporal Graph Convolutional Network (ST-GCN) for the task of emotion recognition. Our extensive experiments on the challenging Body Language Dataset (BoLD) verify the superiority of our methods over existing approaches, while by properly incorporating all of the aforementioned modules in a network ensemble, we manage to surpass the previous best published recognition scores, by a large margin.
Semantic text matching models have been widely used in community question answering, information retrieval, and dialogue. However, these models cannot well address the long-form text matching problem. That is because there are usually many noises in the setting of long-form text matching, and it is difficult for existing semantic text matching to capture the key matching signals from this noisy information. Besides, these models are computationally expensive because they simply use all textual data indiscriminately in the matching process. To tackle the effectiveness and efficiency problem, we propose a novel hierarchical noise filtering model in this paper, namely Match-Ignition. The basic idea is to plug the well-known PageRank algorithm into the Transformer, to identify and filter both sentence and word level noisy information in the matching process. Noisy sentences are usually easy to detect because the sentence is the basic unit of a long-form text, so we directly use PageRank to filter such information, based on a sentence similarity graph. While words need to rely on their contexts to express concrete meanings, so we propose to jointly learn the filtering process and the matching process, to reflect the contextual dependencies between words. Specifically, a word graph is first built based on the attention scores in each self-attention block of Transformer, and keywords are then selected by applying PageRank on this graph. In this way, noisy words will be filtered out layer by layer in the matching process. Experimental results show that Match-Ignition outperforms both traditional text matching models for short text and recent long-form text matching models. We also conduct detailed analysis to show that Match-Ignition can efficiently capture important sentences or words, which are helpful for long-form text matching.
Target speech extraction, which extracts the speech of a target speaker in a mixture given auxiliary speaker clues, has recently received increased interest. Various clues have been investigated such as pre-recorded enrollment utterances, direction information, or video of the target speaker. In this paper, we explore the use of speaker activity information as an auxiliary clue for single-channel neural network-based speech extraction. We propose a speaker activity driven speech extraction neural network (ADEnet) and show that it can achieve performance levels competitive with enrollment-based approaches, without the need for pre-recordings. We further demonstrate the potential of the proposed approach for processing meeting-like recordings, where the speaker activity is obtained from a diarization system. We show that this simple yet practical approach can successfully extract speakers after diarization, which results in improved ASR performance, especially in high overlapping conditions, with a relative word error rate reduction of up to 25%.
Predicate constraints of general-purpose knowledge bases (KBs) like Wikidata, DBpedia and Freebase are often limited to subproperty, domain and range constraints. In this demo we showcase CounQER, a system that illustrates the alignment of counting predicates, like staffSize, and enumerating predicates, like workInstitution^{-1} . In the demonstration session, attendees can inspect these alignments, and will learn about the importance of these alignments for KB question answering and curation. CounQER is available at https://counqer.mpi-inf.mpg.de/spo.
Deep learning techniques have been widely applied to hyperspectral image (HSI) classification and have achieved great success. However, the deep neural network model has a large parameter space and requires a large number of labeled data. Deep learning methods for HSI classification usually follow a patchwise learning framework. Recently, a fast patch-free global learning (FPGA) architecture was proposed for HSI classification according to global spatial context information. However, FPGA has difficulty extracting the most discriminative features when the sample data is imbalanced. In this paper, a spectral-spatial dependent global learning (SSDGL) framework based on global convolutional long short-term memory (GCL) and global joint attention mechanism (GJAM) is proposed for insufficient and imbalanced HSI classification. In SSDGL, the hierarchically balanced (H-B) sampling strategy and the weighted softmax loss are proposed to address the imbalanced sample problem. To effectively distinguish similar spectral characteristics of land cover types, the GCL module is introduced to extract the long short-term dependency of spectral features. To learn the most discriminative feature representations, the GJAM module is proposed to extract attention areas. The experimental results obtained with three public HSI datasets show that the SSDGL has powerful performance in insufficient and imbalanced sample problems and is superior to other state-of-the-art methods. Code can be obtained at: https://github.com/dengweihuan/SSDGL.
Adversarial examples mainly exploit changes to input pixels to which humans are not sensitive to, and arise from the fact that models make decisions based on uninterpretable features. Interestingly, cognitive science reports that the process of interpretability for human classification decision relies predominantly on low spatial frequency components. In this paper, we investigate the robustness to adversarial perturbations of models enforced during training to leverage information corresponding to different spatial frequency ranges. We show that it is tightly linked to the spatial frequency characteristics of the data at stake. Indeed, depending on the data set, the same constraint may results in very different level of robustness (up to 0.41 adversarial accuracy difference). To explain this phenomenon, we conduct several experiments to enlighten influential factors such as the level of sensitivity to high frequencies, and the transferability of adversarial perturbations between original and low-pass filtered inputs.
Although monocular 3D human pose estimation methods have made significant progress, it's far from being solved due to the inherent depth ambiguity. Instead, exploiting multi-view information is a practical way to achieve absolute 3D human pose estimation. In this paper, we propose a simple yet effective pipeline for weakly-supervised cross-view 3D human pose estimation. By only using two camera views, our method can achieve state-of-the-art performance in a weakly-supervised manner, requiring no 3D ground truth but only 2D annotations. Specifically, our method contains two steps: triangulation and refinement. First, given the 2D keypoints that can be obtained through any classic 2D detection methods, triangulation is performed across two views to lift the 2D keypoints into coarse 3D poses.Then, a novel cross-view U-shaped graph convolutional network (CV-UGCN), which can explore the spatial configurations and cross-view correlations, is designed to refine the coarse 3D poses. In particular, the refinement progress is achieved through weakly-supervised learning, in which geometric and structure-aware consistency checks are performed. We evaluate our method on the standard benchmark dataset, Human3.6M. The Mean Per Joint Position Error on the benchmark dataset is 27.4 mm, which outperforms the state-of-the-arts remarkably (27.4 mm vs 30.2 mm).
Over the years motor deficit in Parkinson's Disease (PD) patients was largely studied, however, no consistent pattern of relations between quantitative electroencephalography (qEEG) and motor scales emerged. There is a general lack of information on the relation between EEG changes and scales related to specific motor deficits. Therefore, the study aimed to investigate the relation between brain oscillatory activity alterations (EEG power bands) and most used PD-related motor deficit scales. A positive correlation was found between the freezing of the gait questionnaire (FOGQ) and delta spectral power band (rho=0.67; p=0.008), while a negative correlation with the same scale was observed in the alpha spectral power band (rho=-0.59, p=0.027). Additionally, motor scores measure by motor part of Unified Parkinson's Disease Rating Scale (UPDRS) correlated directly with theta (rho=0.55, p=0.040) and inversely with beta EEG power band (rho=-0.77, p=0.001). No significant correlation was found between spectral powers and Hoehn and Yahr (H&Y), BERG (Berg K. et. al. 1995), Modified Parkinson Activity Scale (MPAS), Six-Minute Walk Test (6MWT) and Timed Up and Go Test (TUG). In conclusion, our study supports the earlier findings suggesting a link between EEG slowing and motor decline, providing more insight into the relation between EEG alteration and deficits in different motor domains. These findings indicate that EEG assessment may be a useful biomarker for objective monitoring of progression and neurophysiological effect of rehabilitation approaches in PD's.
In stochastic dynamic environments, team stochastic games have emerged as a versatile paradigm for studying sequential decision-making problems of fully cooperative multi-agent systems. However, the optimality of the derived policies is usually sensitive to the model parameters, which are typically unknown and required to be estimated from noisy data in practice. To mitigate the sensitivity of the optimal policy to these uncertain parameters, in this paper, we propose a model of "robust" team stochastic games, where players utilize a robust optimization approach to make decisions. This model extends team stochastic games to the scenario of incomplete information and meanwhile provides an alternative solution concept of robust team optimality. To seek such a solution, we develop a learning algorithm in the form of a Gauss-Seidel modified policy iteration and prove its convergence. This algorithm, compared with robust dynamic programming, not only possesses a faster convergence rate, but also allows for using approximation calculations to alleviate the curse of dimensionality. Moreover, some numerical simulations are presented to demonstrate the effectiveness of the algorithm by generalizing the game model of social dilemmas to sequential robust scenarios.
Because of the efficiency of modeling fuzziness and vagueness, Z-number plays an important role in real practice. However, Z-numbers, defined in the real number field, lack the ability to process the quantum information in quantum environment. It is reasonable to generalize Z-number into its quantum counterpart. In this paper, we propose quantum Z-numbers (QZNs), which are the quantum generalization of Z-numbers. In addition, seven basic quantum fuzzy operations of QZNs and their corresponding quantum circuits are presented and illustrated by numerical examples. Moreover, based on QZNs, a novel quantum multi-attributes decision making (MADM) algorithm is proposed and applied in medical diagnosis. The results show that, with the help of quantum computation, the proposed algorithm can make diagnoses correctly and efficiently.