We offer an alternative proof of a result of Conlon, Fox, Sudakov and Zhao on solving translation-invariant linear equations in dense Sidon sets. Our proof generalises to equations in more than five variables and yields effective bounds.

A perfect matroid design (PMD) is a matroid whose flats of the same rank all have the same size. In this paper we introduce the q-analogue of a PMD and its properties. In order to do that, we first establish new cryptomorphic definitions for q-matroids. We show that q-Steiner systems are examples of q-PMD's and we use this matroid structure to construct subspace designs from q-Steiner systems. We apply this construction to S(2, 13, 3; q) Steiner systems and hence establish the existence of subspace designs with previously unknown parameters.

This paper develops a method for obtaining guaranteed outer approximations for global attractors of continuous and discrete time nonlinear dynamical systems. The method is based on a hierarchy of semidefinite programming problems of increasing size with guaranteed convergence to the global attractor. The approach taken follows an established line of reasoning, where we first characterize the global attractor via an infinite dimensional linear programming problem (LP) in the space of Borel measures. The dual to this LP is in the space of continuous functions and its feasible solutions provide guaranteed outer approximations to the global attractor. For systems with polynomial dynamics, a hierarchy of finite-dimensional sum-of-squares tightenings of the dual LP provides a sequence of outer approximations to the global attractor with guaranteed convergence in the sense of volume discrepancy tending to zero. The method is very simple to use and based purely on convex optimization. Numerical examples with the code available online demonstrate the method.

Given a standard graded polynomial ring over a commutative Noetherian ring $A$, we prove that the cohomological dimension and the height of the ideals defining any of its Veronese subrings are equal. This result is due to Ogus when $A$ is a field of characteristic zero, and follows from a result of Peskine and Szpiro when $A$ is a field of positive characteristic; our result applies, for example, when $A$ is the ring of integers.

In the spirit of very recent articles by J. Bonet, W. Lusky and J. Taskinen we are studying the so-called solid hulls and cores of spaces of weighted entire functions when the weights are given in terms of associated weight functions coming from weight sequences. These sequences are required to satisfy certain (standard) growth and regularity properties which are frequently arising and used in the theory of ultradifferentiable and ultraholomorphic function classes (where also the associated weight function plays a prominent role). Thanks to this additional information we are able to see which growth behavior the so-called "Lusky-numbers", arising in the representations of the solid hulls and cores, have to satisfy resp. if such numbers can exist.

We prove that there are no irreducible representations of $B_n$ of dimension $n+1$ for $ngeq 10.$

With the increase in use of Unmanned Aerial Vehicles (UAVs)/drones, it is important to detect and identify causes of failure in real time for proper recovery from a potential crash-like scenario or post incident forensics analysis. The cause of crash could be either a fault in the sensor/actuator system, a physical damage/attack, or a cyber attack on the drone's software. In this paper, we propose novel architectures based on deep Convolutional and Long Short-Term Memory Neural Networks (CNNs and LSTMs) to detect (via Autoencoder) and classify drone mis-operations based on sensor data. The proposed architectures are able to learn high-level features automatically from the raw sensor data and learn the spatial and temporal dynamics in the sensor data. We validate the proposed deep-learning architectures via simulations and experiments on a real drone. Empirical results show that our solution is able to detect with over 90% accuracy and classify various types of drone mis-operations (with about 99% accuracy (simulation data) and upto 88% accuracy (experimental data)).

In this paper we prove that any odd multigrid with non-zero rational offsets is regular, which means that its dual is a rhombic tiling. To prove this result we use a result on trigonometric diophantine equations.

Recent single image unsupervised representation learning techniques show remarkable success on a variety of tasks. The basic principle in these works is instance discrimination: learning to differentiate between two augmented versions of the same image and a large batch of unrelated images. Networks learn to ignore the augmentation noise and extract semantically meaningful representations. Prior work uses artificial data augmentation techniques such as cropping, and color jitter which can only affect the image in superficial ways and are not aligned with how objects actually change e.g. occlusion, deformation, viewpoint change. In this paper, we argue that videos offer this natural augmentation for free. Videos can provide entirely new views of objects, show deformation, and even connect semantically similar but visually distinct concepts. We propose Video Noise Contrastive Estimation, a method for using unlabeled video to learn strong, transferable single image representations. We demonstrate improvements over recent unsupervised single image techniques, as well as over fully supervised ImageNet pretraining, across a variety of temporal and non-temporal tasks. Code and the Random Related Video Views dataset are available at https://www.github.com/danielgordon10/vince

In this paper, we work on intra-variable handwriting, where the writing samples of an individual can vary significantly. Such within-writer variation throws a challenge for automatic writer inspection, where the state-of-the-art methods do not perform well. To deal with intra-variability, we analyze the idiosyncrasy in individual handwriting. We identify/verify the writer from highly idiosyncratic text-patches. Such patches are detected using a deep recurrent reinforcement learning-based architecture. An idiosyncratic score is assigned to every patch, which is predicted by employing deep regression analysis. For writer identification, we propose a deep neural architecture, which makes the final decision by the idiosyncratic score-induced weighted average of patch-based decisions. For writer verification, we propose two algorithms for patch-fed deep feature aggregation, which assist in authentication using a triplet network. The experiments were performed on two databases, where we obtained encouraging results.

Introduction of spectrum-sharing in 5G and subsequent generation networks demand base-station(s) with the capability to characterize the wideband spectrum spanned over licensed, shared and unlicensed non-contiguous frequency bands. Spectrum characterization involves the identification of vacant bands along with center frequency and parameters (energy, modulation, etc.) of occupied bands. Such characterization at Nyquist sampling is area and power-hungry due to the need for high-speed digitization. Though sub-Nyquist sampling (SNS) offers an excellent alternative when the spectrum is sparse, it suffers from poor performance at low signal to noise ratio (SNR) and demands careful design and integration of digital reconstruction, tunable channelizer and characterization algorithms. In this paper, we propose a novel deep-learning framework via a single unified pipeline to accomplish two tasks: 1)~Reconstruct the signal directly from sub-Nyquist samples, and 2)~Wideband spectrum characterization. The proposed approach eliminates the need for complex signal conditioning between reconstruction and characterization and does not need complex tunable channelizers. We extensively compare the performance of our framework for a wide range of modulation schemes, SNR and channel conditions. We show that the proposed framework outperforms existing SNS based approaches and characterization performance approaches to Nyquist sampling-based framework with an increase in SNR. Easy to design and integrate along with a single unified deep learning framework make the proposed architecture a good candidate for reconfigurable platforms.

For Convolutional Neural Network-based object detection, there is a typical dilemma: the spatial information is well kept in the shallow layers which unfortunately do not have enough semantic information, while the deep layers have a high semantic concept but lost a lot of spatial information, resulting in serious information imbalance. To acquire enough semantic information for shallow layers, Feature Pyramid Networks (FPN) is used to build a top-down propagated path. In this paper, except for top-down combining of information for shallow layers, we propose a novel network called Image Pyramid Guidance Network (IPG-Net) to make sure both the spatial information and semantic information are abundant for each layer. Our IPG-Net has two main parts: the image pyramid guidance transformation module and the image pyramid guidance fusion module. Our main idea is to introduce the image pyramid guidance into the backbone stream to solve the information imbalance problem, which alleviates the vanishment of the small object features. This IPG transformation module promises even in the deepest stage of the backbone, there is enough spatial information for bounding box regression and classification. Furthermore, we designed an effective fusion module to fuse the features from the image pyramid and features from the backbone stream. We have tried to apply this novel network to both one-stage and two-stage detection models, state of the art results are obtained on the most popular benchmark data sets, i.e. MS COCO and Pascal VOC.

Interaction languages such as MSC are often associated with formal semantics by means of translations into distinct behavioral formalisms such as automatas or Petri nets. In contrast to translational approaches we propose an operational approach. Its principle is to identify which elementary communication actions can be immediately executed, and then to compute, for every such action, a new interaction representing the possible continuations to its execution. We also define an algorithm for checking the validity of execution traces (i.e. whether or not they belong to an interaction's semantics). Algorithms for semantic computation and trace validity are analyzed by means of experiments.

Histopathology is a reflection of the molecular changes and provides prognostic phenotypes representing the disease progression. In this study, we introduced feature scores generated from hematoxylin and eosin histology images based on deep learning (DL) models developed for prostate pathology. We demonstrated that these feature scores were significantly prognostic for time to event endpoints (biochemical recurrence and cancer-specific survival) and had simultaneously molecular biologic associations to relevant genomic alterations and molecular subtypes using already trained DL models that were not previously exposed to the datasets of the current study. Further, we discussed the potential of such feature scores to improve the current tumor grading system and the challenges that are associated with tumor heterogeneity and the development of prognostic models from histology images. Our findings uncover the potential of feature scores from histology images as digital biomarkers in precision medicine and as an expanding utility for digital pathology.

For real-time semantic video segmentation, most recent works utilised a dynamic framework with a key scheduler to make online key/non-key decisions. Some works used a fixed key scheduling policy, while others proposed adaptive key scheduling methods based on heuristic strategies, both of which may lead to suboptimal global performance. To overcome this limitation, we model the online key decision process in dynamic video segmentation as a deep reinforcement learning problem and learn an efficient and effective scheduling policy from expert information about decision history and from the process of maximising global return. Moreover, we study the application of dynamic video segmentation on face videos, a field that has not been investigated before. By evaluating on the 300VW dataset, we show that the performance of our reinforcement key scheduler outperforms that of various baselines in terms of both effective key selections and running speed. Further results on the Cityscapes dataset demonstrate that our proposed method can also generalise to other scenarios. To the best of our knowledge, this is the first work to use reinforcement learning for online key-frame decision in dynamic video segmentation, and also the first work on its application on face videos.

For $n$-vertex graphs with treewidth $k = O(n^{1/2-epsilon})$ and an arbitrary $epsilon>0$, we present a word-RAM algorithm to compute vertex separators using only $O(n)$ bits of working memory. As an application of our algorithm, we give an $O(1)$-approximation algorithm for tree decomposition. Our algorithm computes a tree decomposition in $c^k n (log log n) log^* n$ time using $O(n)$ bits for some constant $c > 0$.

We finally use the tree decomposition obtained by our algorithm to solve Vertex Cover, Independent Set, Dominating Set, MaxCut and $3$-Coloring by using $O(n)$ bits as long as the treewidth of the graph is smaller than $c' log n$ for some problem dependent constant $0 < c' < 1$.

The Hierarchical Equal Area isoLatitude Pixelation (HEALPix) scheme is used extensively in astrophysics for data collection and analysis on the sphere. The scheme was originally designed for studying the Cosmic Microwave Background (CMB) radiation, which represents the first light to travel during the early stages of the universe's development and gives the strongest evidence for the Big Bang theory to date. Refined analysis of the CMB angular power spectrum can lead to revolutionary developments in understanding the nature of dark matter and dark energy. In this paper, we present a new method for performing spherical harmonic analysis for HEALPix data, which is a central component to computing and analyzing the angular power spectrum of the massive CMB data sets. The method uses a novel combination of a non-uniform fast Fourier transform, the double Fourier sphere method, and Slevinsky's fast spherical harmonic transform (Slevinsky, 2019). For a HEALPix grid with $N$ pixels (points), the computational complexity of the method is $mathcal{O}(Nlog^2 N)$, with an initial set-up cost of $mathcal{O}(N^{3/2}log N)$. This compares favorably with $mathcal{O}(N^{3/2})$ runtime complexity of the current methods available in the HEALPix software when multiple maps need to be analyzed at the same time. Using numerical experiments, we demonstrate that the new method also appears to provide better accuracy over the entire angular power spectrum of synthetic data when compared to the current methods, with a convergence rate at least two times higher.

Finding a good regularization parameter for Tikhonov regularization problems is a though yet often asked question. One approach is to use leave-one-out cross-validation scores to indicate the goodness of fit. This utilizes only the noisy function values but, on the downside, comes with a high computational cost. In this paper we present a general approach to shift the main computations from the function in question to the node distribution and, making use of FFT and FFT-like algorithms, even reduce this cost tremendously to the cost of the Tikhonov regularization problem itself. We apply this technique in different settings on the torus, the unit interval, and the two-dimensional sphere. Given that the sampling points satisfy a quadrature rule our algorithm computes the cross-validations scores in floating-point precision. In the cases of arbitrarily scattered nodes we propose an approximating algorithm with the same complexity. Numerical experiments indicate the applicability of our algorithms.

Compromised accounts on social networks are regular user accounts that have been taken over by an entity with malicious intent. Since the adversary exploits the already established trust of a compromised account, it is crucial to detect these accounts to limit the damage they can cause. We propose a novel general framework for discovering compromised accounts by semantic analysis of text messages coming out from an account. Our framework is built on the observation that normal users will use language that is measurably different from the language that an adversary would use when the account is compromised. We use our framework to develop specific algorithms that use the difference of language models of users and adversaries as features in a supervised learning setup. Evaluation results show that the proposed framework is effective for discovering compromised accounts on social networks and a KL-divergence-based language model feature works best.

This work deals with the efficient numerical solution of the time-fractional heat equation discretized on non-uniform temporal meshes. Non-uniform grids are essential to capture the singularities of "typical" solutions of time-fractional problems. We propose an efficient space-time multigrid method based on the waveform relaxation technique, which accounts for the nonlocal character of the fractional differential operator. To maintain an optimal complexity, which can be obtained for the case of uniform grids, we approximate the coefficient matrix corresponding to the temporal discretization by its hierarchical matrix (${cal H}$-matrix) representation. In particular, the proposed method has a computational cost of ${cal O}(k N M log(M))$, where $M$ is the number of time steps, $N$ is the number of spatial grid points, and $k$ is a parameter which controls the accuracy of the ${cal H}$-matrix approximation. The efficiency and the good convergence of the algorithm, which can be theoretically justified by a semi-algebraic mode analysis, are demonstrated through numerical experiments in both one- and two-dimensional spaces.

The accurate assembly of the system matrix is an important step in any code that solves partial differential equations on a mesh. We either explicitly set up a matrix, or we work in a matrix-free environment where we have to be able to quickly return matrix entries upon demand. Either way, the construction can become costly due to non-trivial material parameters entering the equations, multigrid codes requiring cascades of matrices that depend upon each other, or dynamic adaptive mesh refinement that necessitates the recomputation of matrix entries or the whole equation system throughout the solve. We propose that these constructions can be performed concurrently with the multigrid cycles. Initial geometric matrices and low accuracy integrations kickstart the multigrid, while improved assembly data is fed to the solver as and when it becomes available. The time to solution is improved as we eliminate an expensive preparation phase traditionally delaying the actual computation. We eliminate algorithmic latency. Furthermore, we desynchronise the assembly from the solution process. This anarchic increase of the concurrency level improves the scalability. Assembly routines are notoriously memory- and bandwidth-demanding. As we work with iteratively improving operator accuracies, we finally propose the use of a hierarchical, lossy compression scheme such that the memory footprint is brought down aggressively where the system matrix entries carry little information or are not yet available with high accuracy.

In response to the coronavirus disease (COVID-19) outbreak, there is an ever-increasing number of national governments that are rolling out contact-tracing Apps to aid the containment of the virus. The first hugely contentious issue facing the Apps is the deployment framework, i.e. centralised or decentralised. Based on this, the debate branches out to the corresponding technologies that underpin these architectures, i.e. GPS, QR codes, and Bluetooth. This work conducts a pioneering review of the above scenarios and contributes a geolocation mapping of the current deployment. The vulnerabilities and the directions of research are identified, with a special focus on the Bluetooth-based decentralised scheme.

Domain of mathematical logic in computers is dominated by automated theorem provers (ATP) and interactive theorem provers (ITP). Both of these are hard to access by AI from the human-imitation approach: ATPs often use human-unfriendly logical foundations while ITPs are meant for formalizing existing proofs rather than problem solving. We aim to create a simple human-friendly logical system for mathematical problem solving. We picked the case study of Euclidean geometry as it can be easily visualized, has simple logic, and yet potentially offers many high-school problems of various difficulty levels. To make the environment user friendly, we abandoned strict logic required by ITPs, allowing to infer topological facts from pictures. We present our system for Euclidean geometry, together with a graphical application GeoLogic, similar to GeoGebra, which allows users to interactively study and prove properties about the geometrical setup.

Image-based tracking of medical instruments is an integral part of many surgical data science applications. Previous research has addressed the tasks of detecting, segmenting and tracking medical instruments based on laparoscopic video data. However, the methods proposed still tend to fail when applied to challenging images and do not generalize well to data they have not been trained on. This paper introduces the Heidelberg Colorectal (HeiCo) data set - the first publicly available data set enabling comprehensive benchmarking of medical instrument detection and segmentation algorithms with a specific emphasis on robustness and generalization capabilities of the methods. Our data set comprises 30 laparoscopic videos and corresponding sensor data from medical devices in the operating room for three different types of laparoscopic surgery. Annotations include surgical phase labels for all frames in the videos as well as instance-wise segmentation masks for surgical instruments in more than 10,000 individual frames. The data has successfully been used to organize international competitions in the scope of the Endoscopic Vision Challenges (EndoVis) 2017 and 2019.

Graph convolution network (GCN) have achieved state-of-the-art performance in the task of node prediction in the graph structure. However, with the gradual various of graph attack methods, there are lack of research on the robustness of GCN. At this paper, we will design a robust GCN method for node prediction tasks. Considering the graph structure contains two types of information: node information and connection information, and attackers usually modify the connection information to complete the interference with the prediction results of the node, we first proposed a method to hide the connection information in the generator, named Anonymized GCN (AN-GCN). By hiding the connection information in the graph structure in the generator through adversarial training, the accurate node prediction can be completed only by the node number rather than its specific position in the graph. Specifically, we first demonstrated the key to determine the embedding of a specific node: the row corresponding to the node of the eigenmatrix of the Laplace matrix, by target it as the output of the generator, we designed a method to hide the node number in the noise. Take the corresponding noise as input, we will obtain the connection structure of the node instead of directly obtaining. Then the encoder and decoder are spliced both in discriminator, so that after adversarial training, the generator and discriminator can cooperate to complete the encoding and decoding of the graph, then complete the node prediction. Finally, All node positions can generated by noise at the same time, that is to say, the generator will hides all the connection information of the graph structure. The evaluation shows that we only need to obtain the initial features and node numbers of the nodes to complete the node prediction, and the accuracy did not decrease, but increased by 0.0293.

Unsupervised learning of hidden representations has been one of the most vibrant research directions in machine learning in recent years. In this work we study the brain-like Bayesian Confidence Propagating Neural Network (BCPNN) model, recently extended to extract sparse distributed high-dimensional representations. The saliency and separability of the hidden representations when trained on MNIST dataset is studied using an external classifier, and compared with other unsupervised learning methods that include restricted Boltzmann machines and autoencoders.

We show that combining a prediction model (based on neural networks), with a new method of test pooling (better than the original Dorfman method, and better than double-pooling) called 'Grid', we can reduce the number of Covid-19 tests by 73%.

Neural style transfer is a well-known branch of deep learning research, with many interesting works and two major drawbacks. Most of the works in the field are hard to use by non-expert users and substantial hardware resources are required. In this work, we present a solution to both of these problems. We have applied neural style transfer to real-time video (over 25 frames per second), which is capable of running on mobile devices. We also investigate the works on achieving temporal coherence and present the idea of fine-tuning, already trained models, to achieve stable video. What is more, we also analyze the impact of the common deep neural network architecture on the performance of mobile devices with regard to number of layers and filters present. In the experiment section we present the results of our work with respect to the iOS devices and discuss the problems present in current Android devices as well as future possibilities. At the end we present the qualitative results of stylization and quantitative results of performance tested on the iPhone 11 Pro and iPhone 6s. The presented work is incorporated in Kunster - AR Art Video Maker application available in the Apple's App Store.

Diagnosis of high impedance fault (HIF) is a challenge for nowadays distribution network protections. The fault current of a HIF is much lower than that of a normal load, and fault feature is significantly affected by fault scenarios. A detection and feeder identification algorithm for HIFs is proposed in this paper, based on the high-resolution and synchronous waveform data. In the algorithm, an interval slope is defined to describe the waveform distortions, which guarantees a uniform feature description under various HIF nonlinearities and noise interferences. For three typical types of network neutrals, i.e.,isolated neutral, resonant neutral, and low-resistor-earthed neutral, differences of the distorted components between the zero-sequence currents of healthy and faulty feeders are mathematically deduced, respectively. As a result, the proposed criterion, which is based on the distortion relationships between zero-sequence currents of feeders and the zero-sequence voltage at the substation, is theoretically supported. 28 HIFs grounded to various materials are tested in a 10kV distribution networkwith three neutral types, and are utilized to verify the effectiveness of the proposed algorithm.

With the rapidly worldwide spread of Coronavirus disease (COVID-19), it is of great importance to conduct early diagnosis of COVID-19 and predict the time that patients might convert to the severe stage, for designing effective treatment plan and reducing the clinicians' workloads. In this study, we propose a joint classification and regression method to determine whether the patient would develop severe symptoms in the later time, and if yes, predict the possible conversion time that the patient would spend to convert to the severe stage. To do this, the proposed method takes into account 1) the weight for each sample to reduce the outliers' influence and explore the problem of imbalance classification, and 2) the weight for each feature via a sparsity regularization term to remove the redundant features of high-dimensional data and learn the shared information across the classification task and the regression task. To our knowledge, this study is the first work to predict the disease progression and the conversion time, which could help clinicians to deal with the potential severe cases in time or even save the patients' lives. Experimental analysis was conducted on a real data set from two hospitals with 422 chest computed tomography (CT) scans, where 52 cases were converted to severe on average 5.64 days and 34 cases were severe at admission. Results show that our method achieves the best classification (e.g., 85.91% of accuracy) and regression (e.g., 0.462 of the correlation coefficient) performance, compared to all comparison methods. Moreover, our proposed method yields 76.97% of accuracy for predicting the severe cases, 0.524 of the correlation coefficient, and 0.55 days difference for the converted time.

We present a LiDAR-based and real-time capable 3D perception system for automated driving in urban domains. The hierarchical system design is able to model stationary and movable parts of the environment simultaneously and under real-time conditions. Our approach extends the state of the art by innovative in-detail enhancements for perceiving road users and drivable corridors even in case of non-flat ground surfaces and overhanging or protruding elements. We describe a runtime-efficient pointcloud processing pipeline, consisting of adaptive ground surface estimation, 3D clustering and motion classification stages. Based on the pipeline's output, the stationary environment is represented in a multi-feature mapping and fusion approach. Movable elements are represented in an object tracking system capable of using multiple reference points to account for viewpoint changes. We further enhance the tracking system by explicit consideration of occlusion and ambiguity cases. Our system is evaluated using a subset of the TUBS Road User Dataset. We enhance common performance metrics by considering application-driven aspects of real-world traffic scenarios. The perception system shows impressive results and is able to cope with the addressed scenarios while still preserving real-time capability.

This paper provides a method for the simultaneous topology optimization of parts and their corresponding joint locations in an assembly. Therein, the joint locations are not discrete and predefined, but continuously movable. The underlying coupling equations allow for connecting dissimilar meshes and avoid the need for remeshing when joint locations change. The presented method models the force transfer at a joint location not only by using single spring elements but accounts for the size and type of the joints. When considering riveted or bolted joints, the local part geometry at the joint location consists of holes that are surrounded by material. For spot welds, the joint locations are filled with material and may be smaller than for bolts. The presented method incorporates these material and clearance zones into the simultaneously running topology optimization of the parts. Furthermore, failure of joints may be taken into account at the optimization stage, yielding assemblies connected in a fail-safe manner.

Any media experience must be fully inclusive and accessible to all users regardless of their ability. With the current trend towards immersive experiences, such as Virtual Reality (VR) and 360-degree video, it becomes key that these environments are adapted to be fully accessible. However, until recently the focus has been mostly on adapting the existing techniques to fit immersive displays, rather than considering new approaches for accessibility designed specifically for these increasingly relevant media experiences. This paper surveys a wide range of 360-degree video players and examines the features they include for dealing with accessibility, such as Subtitles, Audio Description, Sign Language, User Interfaces, and other interaction features, like voice control and support for multi-screen scenarios. These features have been chosen based on guidelines from standardization contributions, like in the World Wide Web Consortium (W3C) and the International Communication Union (ITU), and from research contributions for making 360-degree video consumption experiences accessible. The in-depth analysis has been part of a research effort towards the development of a fully inclusive and accessible 360-degree video player. The paper concludes by discussing how the newly developed player has gone above and beyond the existing solutions and guidelines, by providing accessibility features that meet the expectations for a widely used immersive medium, like 360-degree video.

Thin structures, such as wire-frame sculptures, fences, cables, power lines, and tree branches, are common in the real world.

It is extremely challenging to acquire their 3D digital models using traditional image-based or depth-based reconstruction methods because thin structures often lack distinct point features and have severe self-occlusion.

We propose the first approach that simultaneously estimates camera motion and reconstructs the geometry of complex 3D thin structures in high quality from a color video captured by a handheld camera.

Specifically, we present a new curve-based approach to estimate accurate camera poses by establishing correspondences between featureless thin objects in the foreground in consecutive video frames, without requiring visual texture in the background scene to lock on.

Enabled by this effective curve-based camera pose estimation strategy, we develop an iterative optimization method with tailored measures on geometry, topology as well as self-occlusion handling for reconstructing 3D thin structures.

Extensive validations on a variety of thin structures show that our method achieves accurate camera pose estimation and faithful reconstruction of 3D thin structures with complex shape and topology at a level that has not been attained by other existing reconstruction methods.

Previous methods on estimating detailed human depth often require supervised training with `ground truth' depth data. This paper presents a self-supervised method that can be trained on YouTube videos without known depth, which makes training data collection simple and improves the generalization of the learned network. The self-supervised learning is achieved by minimizing a photo-consistency loss, which is evaluated between a video frame and its neighboring frames warped according to the estimated depth and the 3D non-rigid motion of the human body. To solve this non-rigid motion, we first estimate a rough SMPL model at each video frame and compute the non-rigid body motion accordingly, which enables self-supervised learning on estimating the shape details. Experiments demonstrate that our method enjoys better generalization and performs much better on data in the wild.

Despite recent progress on computer vision and natural language processing, developing video understanding intelligence is still hard to achieve due to the intrinsic difficulty of story in video. Moreover, there is not a theoretical metric for evaluating the degree of video understanding. In this paper, we propose a novel video question answering (Video QA) task, DramaQA, for a comprehensive understanding of the video story. The DramaQA focused on two perspectives: 1) hierarchical QAs as an evaluation metric based on the cognitive developmental stages of human intelligence. 2) character-centered video annotations to model local coherence of the story. Our dataset is built upon the TV drama "Another Miss Oh" and it contains 16,191 QA pairs from 23,928 various length video clips, with each QA pair belonging to one of four difficulty levels. We provide 217,308 annotated images with rich character-centered annotations, including visual bounding boxes, behaviors, and emotions of main characters, and coreference resolved scripts. Additionally, we provide analyses of the dataset as well as Dual Matching Multistream model which effectively learns character-centered representations of video to answer questions about the video. We are planning to release our dataset and model publicly for research purposes and expect that our work will provide a new perspective on video story understanding research.

We propose Cotatron, a transcription-guided speech encoder for speaker-independent linguistic representation. Cotatron is based on the multispeaker TTS architecture and can be trained with conventional TTS datasets. We train a voice conversion system to reconstruct speech with Cotatron features, which is similar to the previous methods based on Phonetic Posteriorgram (PPG). By training and evaluating our system with 108 speakers from the VCTK dataset, we outperform the previous method in terms of both naturalness and speaker similarity. Our system can also convert speech from speakers that are unseen during training, and utilize ASR to automate the transcription with minimal reduction of the performance. Audio samples are available at https://mindslab-ai.github.io/cotatron, and the code with a pre-trained model will be made available soon.

Automated person re-identification in a multi-camera surveillance setup is very important for effective tracking and monitoring crowd movement. In the recent years, few deep learning based re-identification approaches have been developed which are quite accurate but time-intensive, and hence not very suitable for practical purposes. In this paper, we propose an efficient hierarchical re-identification approach in which color histogram based comparison is first employed to find the closest matches in the gallery set, and next deep feature based comparison is carried out using Siamese network. Reduction in search space after the first level of matching helps in achieving a fast response time as well as improving the accuracy of prediction by the Siamese network by eliminating vastly dissimilar elements. A silhouette part-based feature extraction scheme is adopted in each level of hierarchy to preserve the relative locations of the different body structures and make the appearance descriptors more discriminating in nature. The proposed approach has been evaluated on five public data sets and also a new data set captured by our team in our laboratory. Results reveal that it outperforms most state-of-the-art approaches in terms of overall accuracy.

Chest computed tomography (CT) becomes an effective tool to assist the diagnosis of coronavirus disease-19 (COVID-19). Due to the outbreak of COVID-19 worldwide, using the computed-aided diagnosis technique for COVID-19 classification based on CT images could largely alleviate the burden of clinicians. In this paper, we propose an Adaptive Feature Selection guided Deep Forest (AFS-DF) for COVID-19 classification based on chest CT images. Specifically, we first extract location-specific features from CT images. Then, in order to capture the high-level representation of these features with the relatively small-scale data, we leverage a deep forest model to learn high-level representation of the features. Moreover, we propose a feature selection method based on the trained deep forest model to reduce the redundancy of features, where the feature selection could be adaptively incorporated with the COVID-19 classification model. We evaluated our proposed AFS-DF on COVID-19 dataset with 1495 patients of COVID-19 and 1027 patients of community acquired pneumonia (CAP). The accuracy (ACC), sensitivity (SEN), specificity (SPE) and AUC achieved by our method are 91.79%, 93.05%, 89.95% and 96.35%, respectively. Experimental results on the COVID-19 dataset suggest that the proposed AFS-DF achieves superior performance in COVID-19 vs. CAP classification, compared with 4 widely used machine learning methods.

Recently, the outbreak of Coronavirus Disease 2019 (COVID-19) has spread rapidly across the world. Due to the large number of affected patients and heavy labor for doctors, computer-aided diagnosis with machine learning algorithm is urgently needed, and could largely reduce the efforts of clinicians and accelerate the diagnosis process. Chest computed tomography (CT) has been recognized as an informative tool for diagnosis of the disease. In this study, we propose to conduct the diagnosis of COVID-19 with a series of features extracted from CT images. To fully explore multiple features describing CT images from different views, a unified latent representation is learned which can completely encode information from different aspects of features and is endowed with promising class structure for separability. Specifically, the completeness is guaranteed with a group of backward neural networks (each for one type of features), while by using class labels the representation is enforced to be compact within COVID-19/community-acquired pneumonia (CAP) and also a large margin is guaranteed between different types of pneumonia. In this way, our model can well avoid overfitting compared to the case of directly projecting highdimensional features into classes. Extensive experimental results show that the proposed method outperforms all comparison methods, and rather stable performances are observed when varying the numbers of training data.

Person re-identification (re-ID) remains challenging in a real-world scenario, as it requires a trained network to generalise to totally unseen target data in the presence of variations across domains. Recently, generative adversarial models have been widely adopted to enhance the diversity of training data. These approaches, however, often fail to generalise to other domains, as existing generative person re-identification models have a disconnect between the generative component and the discriminative feature learning stage. To address the on-going challenges regarding model generalisation, we propose an end-to-end domain adaptive attention network to jointly translate images between domains and learn discriminative re-id features in a single framework. To address the domain gap challenge, we introduce an attention module for image translation from source to target domains without affecting the identity of a person. More specifically, attention is directed to the background instead of the entire image of the person, ensuring identifying characteristics of the subject are preserved. The proposed joint learning network results in a significant performance improvement over state-of-the-art methods on several benchmark datasets.

We establish versions of Conley's (i) fundamental theorem and (ii) decomposition theorem for a broad class of hybrid dynamical systems. The hybrid version of (i) asserts that a globally-defined "hybrid complete Lyapunov function" exists for every hybrid system in this class. Motivated by mechanics and control settings where physical or engineered events cause abrupt changes in a system's governing dynamics, our results apply to a large class of Lagrangian hybrid systems (with impacts) studied extensively in the robotics literature. Viewed formally, these results generalize those of Conley and Franks for continuous-time and discrete-time dynamical systems, respectively, on metric spaces. However, we furnish specific examples illustrating how our statement of sufficient conditions represents merely an early step in the longer project of establishing what formal assumptions can and cannot endow hybrid systems models with the topologically well characterized partitions of limit behavior that make Conley's theory so valuable in those classical settings.

Over the years, performance evaluation has become essential in computer vision, enabling tangible progress in many sub-fields. While talking-head video generation has become an emerging research topic, existing evaluations on this topic present many limitations. For example, most approaches use human subjects (e.g., via Amazon MTurk) to evaluate their research claims directly. This subjective evaluation is cumbersome, unreproducible, and may impend the evolution of new research. In this work, we present a carefully-designed benchmark for evaluating talking-head video generation with standardized dataset pre-processing strategies. As for evaluation, we either propose new metrics or select the most appropriate ones to evaluate results in what we consider as desired properties for a good talking-head video, namely, identity preserving, lip synchronization, high video quality, and natural-spontaneous motion. By conducting a thoughtful analysis across several state-of-the-art talking-head generation approaches, we aim to uncover the merits and drawbacks of current methods and point out promising directions for future work. All the evaluation code is available at: https://github.com/lelechen63/talking-head-generation-survey.

We identify the structure of the lexicographically least word avoiding 5/4-powers on the alphabet of nonnegative integers. Specifically, we show that this word has the form $p au(varphi(z) varphi^2(z) cdots)$ where $p, z$ are finite words, $varphi$ is a 6-uniform morphism, and $ au$ is a coding. This description yields a recurrence for the $i$th letter, which we use to prove that the sequence of letters is 6-regular with rank 188. More generally, we prove $k$-regularity for a sequence satisfying a recurrence of the same type.

In this work, we consider a group of robots working together to manipulate a rigid object to track a desired trajectory in $SE(3)$. The robots have no explicit communication network among them, and they do no know the mass or friction properties of the object, or where they are attached to the object. However, we assume they share data from a common IMU placed arbitrarily on the object. To solve this problem, we propose a decentralized adaptive control scheme wherein each agent maintains and adapts its own estimate of the object parameters in order to track a reference trajectory. We present an analysis of the controller's behavior, and show that all closed-loop signals remain bounded, and that the system trajectory will almost always (except for initial conditions on a set of measure zero) converge to the desired trajectory. We study the proposed controller's performance using numerical simulations of a manipulation task in 3D, and with hardware experiments which demonstrate our algorithm on a planar manipulation task. These studies, taken together, demonstrate the effectiveness of the proposed controller even in the presence of numerous unmodelled effects, such as discretization errors and complex frictional interactions.

Monitoring users on large computing platforms such as high performance computing (HPC) and cloud computing systems is non-trivial. Utilities such as process viewers provide limited insight into what users are running, due to granularity limitation, and other sources of data, such as system call tracing, can impose significant operational overhead. However, despite technical and procedural measures, instances of users abusing valuable HPC resources for personal gains have been documented in the past cite{hpcbitmine}, and systems that are open to large numbers of loosely-verified users from around the world are at risk of abuse. In this paper, we show how electrical power consumption data from an HPC platform can be used to identify what programs are executed. The intuition is that during execution, programs exhibit various patterns of CPU and memory activity. These patterns are reflected in the power consumption of the system and can be used to identify programs running. We test our approach on an HPC rack at Lawrence Berkeley National Laboratory using a variety of scientific benchmarks. Among other interesting observations, our results show that by monitoring the power consumption of an HPC rack, it is possible to identify if particular programs are running with precision up to and recall of 95\% even in noisy scenarios.

We introduce a variant of PCPs, that we refer to as rectangular PCPs, wherein proofs are thought of as square matrices, and the random coins used by the verifier can be partitioned into two disjoint sets, one determining the row of each query and the other determining the *column*.

We construct PCPs that are efficient, short, smooth and (almost-)rectangular. As a key application, we show that proofs for hard languages in NTIME$(2^n)$, when viewed as matrices, are rigid infinitely often. This strengthens and considerably simplifies a recent result of Alman and Chen [FOCS, 2019] constructing explicit rigid matrices in FNP. Namely, we prove the following theorem: - There is a constant $delta in (0,1)$ such that there is an FNP-machine that, for infinitely many $N$, on input $1^N$ outputs $N imes N$ matrices with entries in $mathbb{F}_2$ that are $delta N^2$-far (in Hamming distance) from matrices of rank at most $2^{log N/Omega(log log N)}$.

Our construction of rectangular PCPs starts with an analysis of how randomness yields queries in the Reed--Muller-based outer PCP of Ben-Sasson, Goldreich, Harsha, Sudan and Vadhan [SICOMP, 2006; CCC, 2005]. We then show how to preserve rectangularity under PCP composition and a smoothness-inducing transformation. This warrants refined and stronger notions of rectangularity, which we prove for the outer PCP and its transforms.

Coordinating the operation of combined heat and power plants (CHPs) and heat pumps (HPs) at the interface between heat and power systems is essential to achieve a cost-effective and efficient operation of the overall energy system. Indeed, in the current sequential market practice, the heat market has no insight into the impacts of heat dispatch on the electricity market. While preserving this sequential practice, this paper introduces an electricity-aware heat unit commitment model. Coordination is achieved through bid validity constraints, which embed the techno-economic linkage between heat and electricity outputs and costs of CHPs and HPs. This approach constitutes a novel market mechanism for the coordination of heat and power systems, defining heat bids conditionally on electricity market prices. The resulting model is a trilevel optimization problem, which we recast as a mixed-integer linear program using a lexicographic function. We use a realistic case study based on the Danish power and heat system, and show that the proposed model yields a 4.5% reduction in total operating cost of heat and power systems compared to a traditional decoupled unit commitment model, while reducing the financial losses of each CHP and HP due to invalid bids by up-to 20.3 million euros.

Feature pyramid has been an efficient method to extract features at different scales. Development over this method mainly focuses on aggregating contextual information at different levels while seldom touching the inter-level correlation in the feature pyramid. Early computer vision methods extracted scale-invariant features by locating the feature extrema in both spatial and scale dimension. Inspired by this, a convolution across the pyramid level is proposed in this study, which is termed pyramid convolution and is a modified 3-D convolution. Stacked pyramid convolutions directly extract 3-D (scale and spatial) features and outperforms other meticulously designed feature fusion modules. Based on the viewpoint of 3-D convolution, an integrated batch normalization that collects statistics from the whole feature pyramid is naturally inserted after the pyramid convolution. Furthermore, we also show that the naive pyramid convolution, together with the design of RetinaNet head, actually best applies for extracting features from a Gaussian pyramid, whose properties can hardly be satisfied by a feature pyramid. In order to alleviate this discrepancy, we build a scale-equalizing pyramid convolution (SEPC) that aligns the shared pyramid convolution kernel only at high-level feature maps. Being computationally efficient and compatible with the head design of most single-stage object detectors, the SEPC module brings significant performance improvement ($>4$AP increase on MS-COCO2017 dataset) in state-of-the-art one-stage object detectors, and a light version of SEPC also has $sim3.5$AP gain with only around 7% inference time increase. The pyramid convolution also functions well as a stand-alone module in two-stage object detectors and is able to improve the performance by $sim2$AP. The source code can be found at https://github.com/jshilong/SEPC.

This paper illustrates five different techniques to assess the distinctiveness of topics, key terms and features, speed of information dissemination, and network behaviors for Covid19 tweets. First, we use pattern matching and second, topic modeling through Latent Dirichlet Allocation (LDA) to generate twenty different topics that discuss case spread, healthcare workers, and personal protective equipment (PPE). One topic specific to U.S. cases would start to uptick immediately after live White House Coronavirus Task Force briefings, implying that many Twitter users are paying attention to government announcements. We contribute machine learning methods not previously reported in the Covid19 Twitter literature. This includes our third method, Uniform Manifold Approximation and Projection (UMAP), that identifies unique clustering-behavior of distinct topics to improve our understanding of important themes in the corpus and help assess the quality of generated topics. Fourth, we calculated retweeting times to understand how fast information about Covid19 propagates on Twitter. Our analysis indicates that the median retweeting time of Covid19 for a sample corpus in March 2020 was 2.87 hours, approximately 50 minutes faster than repostings from Chinese social media about H7N9 in March 2013. Lastly, we sought to understand retweet cascades, by visualizing the connections of users over time from fast to slow retweeting. As the time to retweet increases, the density of connections also increase where in our sample, we found distinct users dominating the attention of Covid19 retweeters. One of the simplest highlights of this analysis is that early-stage descriptive methods like regular expressions can successfully identify high-level themes which were consistently verified as important through every subsequent analysis.