We present an algorithm for simultaneous face detection, landmarks localization, pose estimation and gender recognition using deep convolutional neural networks (CNN). The proposed method called, HyperFace, fuses the intermediate layers of a deep CNN using a separate CNN followed by a multi-task learning algorithm that operates on the fused features. It exploits the synergy among the tasks which boosts up their individual performances. Additionally, we propose two variants of HyperFace: (1) HyperFace-ResNet that builds on the ResNet-101 model and achieves significant improvement in performance, and (2) Fast-HyperFace that uses a high recall fast face detector for generating region proposals to improve the speed of the algorithm. Extensive experiments show that the proposed models are able to capture both global and local information in faces and performs significantly better than many competitive algorithms for each of these four tasks.

HyperFace: A Deep Multi-Task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition

Rechargeable lithium-ion batteries are promising candidates for building grid-level storage systems because of their high energy and power density, low discharge rate, and decreasing cost. A vital aspect in energy storage planning and operations is to accurately model the aging cost of battery cells, especially in irregular cycling operations. This paper proposes a semi-empirical lithium-ion battery degradation model that assesses battery cell life loss from operating profiles. We formulate the model by combining fundamental theories of battery degradation and our observations in battery aging test results. The model is adaptable to different types of lithium-ion batteries, and methods for tuning the model coefficients based on manufacturer’s data are presented. A cycle-counting method is incorporated to identify stress cycles from irregular operations, allowing the degradation model to be applied to any battery energy storage (BES) applications. The usefulness of this model is demonstrated through an assessment of the degradation that a BES would incur by providing frequency control in the PJM regulation market.

Modeling of Lithium-Ion Battery Degradation for Cell Life Assessment

Current object detectors are limited in vocabulary size due to the small scale of detection datasets. Image classifiers, on the other hand, reason about much larger vocabularies, as their datasets are larger and easier to collect. We propose Detic, which simply trains the classifiers of a detector on image classification data and thus expands the vocabulary of detectors to tens of thousands of concepts. Unlike prior work, Detic does not need complex assignment schemes to assign image labels to boxes based on model predictions, making it much easier to implement and compatible with a range of detection architectures and backbones. Our results show that Detic yields excellent detectors even for classes without box annotations. It outperforms prior work on both open-vocabulary and long-tail detection benchmarks. Detic provides a gain of 2.4 mAP for all classes and 8.3 mAP for novel classes on the open-vocabulary LVIS benchmark. On the standard LVIS benchmark, Detic obtains 41.7 mAP when evaluated on all classes, or only rare classes, hence closing the gap in performance for object categories with few samples. For the first time, we train a detector with all the twenty-one-thousand classes of the ImageNet dataset and show that it generalizes to new datasets without finetuning. Code is available at https://github.com/facebookresearch/Detic . 

/pdf/detecting-twenty-thousand-classes-using-image-level-2smh6ep1.pdf

Detecting Twenty-Thousand Classes Using Image-Level Supervision

This work is a sequel of the studies in the analysis of vulnerabilities in computer systems. It applied boolean algebras to develop a mathematical model describing the exploits of the NVD data source when using the classification based on the concept of measurement. Quasimeasure has been offered for the boolean algebra, proved that she is a measure from the point of view of measure theory. Shows that the algebraic structure is also algebra of events.

Анализ уязвимостей вычислительных систем на основе алгебраических структур и потоков данных National Vulnerability Database

Human Action Recognition (HAR) aims to understand human behavior and assign a label to each action. It has a wide range of applications, and therefore has been attracting increasing attention in the field of computer vision. Human actions can be represented using various data modalities, such as RGB, skeleton, depth, infrared, point cloud, event stream, audio, acceleration, radar, and WiFi signal, which encode different sources of useful yet distinct information and have various advantages depending on the application scenarios. Consequently, lots of existing works have attempted to investigate different types of approaches for HAR using various modalities. In this paper, we present a comprehensive survey of recent progress in deep learning methods for HAR based on the type of input data modality. Specifically, we review the current mainstream deep learning methods for single data modalities and multiple data modalities, including the fusion-based and the co-learning-based frameworks. We also present comparative results on several benchmark datasets for HAR, together with insightful observations and inspiring future research directions. 

Human Action Recognition From Various Data Modalities: A Review

To accommodate the increasing presence of volatile and intermittent renewable energy sources in power generation, independent system operators (ISO) offer opportunities for demand side regulation service (RS) so as to stabilize the grid load. These power market features allow the demand side to earn monetary credits by modulating its power consumption dynamically following an RS signal broadcast by ISO. This paper studies the capacities and benefits of a major potential demand side, the data center, to provide RS. We propose a dynamic control policy that modulates the data center power consumption in response to ISO requests by leveraging server power capping techniques and various server power states. Results demonstrate that using our policy, data centers can provide fast reserves in quantities that are substantial proportions (around 50%) of their average energy consumption, with no major deterioration in quality of service (QoS). By doing so, data centers decrease their energy costs around 50%, while providing the ISOs and the society in general with cost effective demand side reserves that render massive renewable generation adoption affordable.

/pdf/the-data-center-as-a-grid-load-stabilizer-54madksu4c.pdf

The data center as a grid load stabilizer

Data centers account for 3% of the national electricity consumption today. Recent advances in power capping enable data centers to provide Regulation Service (RS) reserves to power markets. RS reserve requirements are expected to increase with the integration of substantial environmentally sustainable, albeit volatile and intermittent, renewable generation. We investigate the ability of server clusters to provide RS reserves while meeting contractual Quality-of-Service (QoS) guarantees for user applications running on the cluster. We propose a dynamic server power regulation policy for processing randomly arriving applications within probabilistic QoS constraints while tracking dynamically broadcasted RS requests by the power market Independent System Operator (ISO). Numerical results demonstrate the ability to select optimal RS reserve and average energy consumption levels that allow data centers to both deliver probabilistic QoS guarantees to customers and track real time ISO RS requests. Finally, we argue that simulated optimal policy performance statistics can enable data centers to bid for energy and to offer RS reserves in the the hour-ahead power markets.

http://www.bu.edu/pcms/caramanis/CDC13_1371_FIHao.pdf

Real-time power control of data centers for providing Regulation Service

Today's US power markets offer new opportunities for the energy consumers to reduce their energy costs by first promising an average consumption rate for the next hour and then by following a regulation signal broadcast by the independent system operators (ISOs), who need to match supply and demand in real time in presence of volatile and intermittent renewable energy generation. This paper leverages the power regulation capabilities of the servers so as to enable the data centers to participate in these emerging power markets. As the data center energy consumption continues to grow, proposed participation in the power markets has the promise to achieve significant monetary savings. The paper first solves a data center regulation service (RS) optimization problem to determine the optimal average power consumption and regulation quantity that minimize the energy cost. We then propose a dynamic server power capping technique to modulate the real-time power consumption in response to ISO requests while maintaining the desired quality-of-service (QoS). Experiments on a real-life server demonstrate that our technique can reduce the energy cost by 29% on average compared to using a fixed power cap.

/pdf/dynamic-server-power-capping-for-enabling-data-center-hew1sookpk.pdf

Dynamic server power capping for enabling data center participation in power markets

In this paper, we present Long Short-term TRansformer (LSTR), a new temporal modeling algorithm for online action detection, by employing a long- and short-term memories mechanism that is able to model prolonged sequence data. It consists of an LSTR encoder that is capable of dynamically exploiting coarse-scale historical information from an extensively long time window (e.g., 2048 long-range frames of up to 8 minutes), together with an LSTR decoder that focuses on a short time window (e.g., 32 short-range frames of 8 seconds) to model the fine-scale characterization of the ongoing event. Compared to prior work, LSTR provides an effective and efficient method to model long videos with less heuristic algorithm design. LSTR achieves significantly improved results on standard online action detection benchmarks, THUMOS'14, TVSeries, and HACS Segment, over the existing state-of-the-art approaches. Extensive empirical analysis validates the setup of the long- and short-term memories and the design choices of LSTR.

Long Short-Term Transformer for Online Action Detection

Recent advances in deep learning greatly boost the performance of object detection. State-of-the-art methods such as Faster-RCNN, FPN and R-FCN have achieved high accuracy in challenging benchmark datasets. However, these methods require fully annotated object bounding boxes for training, which are incredibly hard to scale up due to the high annotation cost. Weakly-supervised methods, on the other hand, only require image-level labels for training, but the performance is far below their fully-supervised counterparts. In this paper, we propose a semi-supervised large scale fine-grained detection method, which only needs bounding box annotations of a smaller number of coarse-grained classes and image-level labels of large scale fine-grained classes, and can detect all classes at nearly fully-supervised accuracy. We achieve this by utilizing the correlations between coarse-grained and fine-grained classes with shared backbone, soft-attention based proposal re-ranking, and a dual-level memory module. Experiment results show that our methods can achieve close accuracy on object detection to state-of-the-art fully-supervised methods on two large scale datasets, ImageNet and OpenImages, with only a small fraction of fully annotated classes.

/pdf/detecting-11k-classes-large-scale-object-detection-without-36t8plb99h.pdf

Detecting 11K Classes: Large Scale Object Detection Without Fine-Grained Bounding Boxes

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Hao Chen

Author Tools

Chat about Author