Hewlett Packard Enterprise Development LP

Qun Yang Lin

Jun Qing Xie

Shuai Wang

Xunteng Xu

Kyu-Han Kim

Xiaofeng Yu

Zhi-Yong Shen

A video annotation system for deep learning based video analytics and corresponding methods of use and operation are described that significantly improve the efficiency of video data frame labeling and the user experience. The video annotation system described herein may be deployed at a network edge and may support various intelligent annotation functionality including annotation tracking, adaptive video segmentation, and execution of predictive annotation algorithms. In addition, the video annotation system described herein supports team collaboration functionality in connection with large-scale labeling tasks.

Video annotation system for deep learning based video analytics

An apparatus includes a display, a wireless communication device, an input device, and a processor. The processor to provide a first connection plan and a second connection plan via the display to a user. The first connection plan identifies a first set of rules of wireless access point selection and the second connection plan identifies a second set of rules for wireless access point selection. The processor also to receive a selection corresponding one of the first connection plan and the second connection plan from the user via the input device and to select one of a first wireless access point and a second wireless access point based on first network performance data of the first wireless access point, second network performance data of the second wireless access point, and the selection. The processor further to establish a network connection with the selected wireless access point via the wireless communication device.

Wireless access point selection based on a connection plan

A SCI (Split, Compression and Intersection) packet classifier, wherein the SCI packet classifier comprises a construction module to generate rule ID array, h pairs of ISG and three binary search trees, and a lookup engine to look up the binary search trees and ISGs to find the highest priority rule matching the incoming packet and to output a corresponding rule ID.

Memory efficient packet classification method

In one implementation, instructions stored on a non-transitory computer-readable medium are executable by a processing resource to cause a computing device to fetch a token code from a home subscriber server (HSS) for a user and log in to a Virtual Private Network (VPN) server using the token code.

User authentication

Load balancing among wireless access points (APs) can include a plurality of wireless APs, and a transition-in transition-out (TITO) engine instructing a client to dissociate from a first wireless AP selected from the plurality of wireless APs and associate with a second wireless AP selected from the plurality of wireless APs.

Load balancing among wireless access points

Systems, devices, and methods, including executable instructions and/or logic thereon, are provided for server site selection. A system includes a load balancing master configured to have a domain name server (DNS) capability with extensions to support iterative control and a manager capability to select among server sites to probe. The system includes a load balancing slave, communicatively coupled to the master, configured to have a DNS reflection capability to measure a round trip time (RTT) between the load balancing slave and a client local DNS server and an actor capability to respond to commands from the manager and to report a measured RTT to the load balancing master.

Growing community of inventors

Beijing, China

Qun Yang Lin