Captioned images are widely available on the web, while the captions often contain the names of the subjects in the images.
Deep neural networks (DNNs) have achieved great successes in various vision applications due to their strong expressive power.
Specifically, the data preprocessing step addresses the data quality issues of PMU measurements (e. g., bad data and missing data); in the fine-grained event data extraction step, a model-free event detection method is developed to accurately localize the events from the inaccurate event timestamps in the event logs; and the feature engineering step constructs the event features based on the patterns of different event types, in order to improve the performance and the interpretability of the event classifiers.
Image- and video-based 3D human recovery (i. e. pose and shape estimation) have achieved substantial progress.
In this paper, we introduce a brand new dataset to promote the study of instance segmentation for objects with irregular shapes.
Ranked #1 on Instance Segmentation on iShape
Specifically, this paper targets quantum neural network (QNN), and proposes to learn the errors in the training phase, so that the identified QNN model can be resilient to noise.
While the average prediction accuracy has been improved significantly over the years, the performance on hard poses with depth ambiguity, self-occlusion, and complex or rare poses is still far from satisfactory.
We study the problem of weakly supervised grounded image captioning.
In this paper, we propose a Geometry Uncertainty Projection Network (GUP Net) to tackle the error amplification problem at both inference and training stages.
To handle multiple objects and generalize to unseen objects, we disentangle the latent object shape and pose representations, so that the latent shape space models shape similarities, and the latent pose code is used for rotation retrieval by comparison with canonical rotations.
Through an IPS (Intersection Perception System) installed at the diagonal of the intersection, this paper proposes a high-quality multimodal dataset for the intersection perception task.
3D object detection with a single image is an essential and challenging task for autonomous driving.
In these applications, a neural network is trained to predict a time-varying target (e. g., solar power), based on multiple correlated features (e. g., temperature, humidity, and cloud coverage).
The Travelling Thief Problem (TTP) is a challenging combinatorial optimization problem that attracts many scholars.
By proposing a framework of Edge Computing Assisted Autonomous Flight (ECAAF), we illustrate that vision and communications can interact with and assist each other with the aid of edge computing and offloading, and further speed up the UAV mission completion.
CoEdge utilizes available computation and communication resources at the edge and dynamically partitions the DNN inference workload adaptive to devices' computing capabilities and network conditions.
This paper presents a machine learning method for event cause analysis to enhance situational awareness in distribution networks.
This paper presents a wide-area event classification in transmission power grids.
In this paper, we propose a novel decentralized model learning approach, namely E-Tree, which makes use of a well-designed tree structure imposed on the edge devices.
We propose an unsupervised learning framework with the pretext task of finding dense correspondences between point cloud shapes from the same category based on the cycle-consistency formulation.
Recent works have shown that exploiting unlabeled data through label propagation can substantially reduce the labeling cost, which has been a critical issue in developing visual recognition models.
To tackle this issue, HotNAS builds a chain of tools to design hardware to support compression, based on which a global optimizer is developed to automatically co-search all the involved search spaces.
With the vertex confidence and edge connectivity, we can naturally organize more relevant vertices on the affinity graph and group them into clusters.
Neural Architecture Search (NAS) has demonstrated its power on various AI accelerating platforms such as Field Programmable Gate Arrays (FPGAs) and Graphic Processing Units (GPUs).
This study focuses on a reverse question answering (QA) procedure, in which machines proactively raise questions and humans supply the answers.
In this paper, we aim to provide a comprehensive survey on application of blockchain in smart grid.
Cryptography and Security Distributed, Parallel, and Cluster Computing Networking and Internet Architecture Social and Information Networks Systems and Control Systems and Control
In this paper, we are the first to bring the computing-in-memory architecture, which can easily transcend the memory wall, to interplay with the neural architecture search, aiming to find the most efficient neural architectures with high network accuracy and maximized hardware efficiency.
Bitcoin is the first fully decentralized permissionless blockchain protocol and achieves a high level of security: the ledger it maintains has guaranteed liveness and consistency properties as long as the adversary has less compute power than the honest nodes.
Distributed, Parallel, and Cluster Computing Cryptography and Security Networking and Internet Architecture
We propose a novel hardware and software co-exploration framework for efficient neural architecture search (NAS).
In this paper, we use blockchain to prevent logs from being tampered with and propose a pvalue-guided anomaly detection approach.
Cryptography and Security
Specifically, without any condition on the matrix $A$, we provide upper bounds in cardinality and infinity norm for the optimal solutions, and show that all optimal solutions must be on the boundary of the feasible set when $0<p<1$.
In this paper, we aim to explore the impact of semantic manipulation on DNNs predictions by manipulating the semantic attributes of images and generate "unrestricted adversarial examples".
In order to address this task, we propose a system based on the BERT model with meta information of questions.
In this paper, a biologically-inspired adaptive intelligent secondary controller is developed for microgrids to tackle system dynamics uncertainties, faults, and/or disturbances.
In addition, with a performance abstraction model to analyze the latency of neural architectures without training, our framework can quickly prune architectures that do not satisfy the specification, leading to higher efficiency.
The main challenge of this problem comes from the large scale and the fine-grained nature of the product categories as well as the difficulty for collecting training images that reflect the realistic checkout scenarios due to continuous update of the products.
When the support points of the barycenter are pre-specified, this problem can be modeled as a linear programming (LP) problem whose size can be extremely large.
In recent years, Fully Convolutional Networks (FCN) has been widely used in various semantic segmentation tasks, including multi-modal remote sensing imagery.
For the task of subdecimeter aerial imagery segmentation, fine-grained semantic segmentation results are usually difficult to obtain because of complex remote sensing content and optical conditions.
Massive classification, a classification task defined over a vast number of classes (hundreds of thousands or even millions), has become an essential part of many real-world systems, such as face recognition.
To solve this class of problems, we propose a proximal gradient method with extrapolation and line search (PGels).
Semantic segmentation is a fundamental research in remote sensing image processing.
In many applications involving large dataset or online updating, stochastic gradient descent (SGD) provides a scalable way to compute parameter estimates and has gained increasing popularity due to its numerical convenience and memory efficiency.
Finally, we conduct some numerical experiments using real datasets to compare our method with some existing efficient methods for non-negative matrix factorization and matrix completion.
Additionally, combining an effective heuristic for determining $n$-rank, we can also apply the proposed algorithm to solve MnRA when $n$-rank is unknown in advance.