Abstract: An action recognition method includes: obtaining original feature submaps of each of temporal frames on a plurality of convolutional channels by using a multi-channel convolutional layer; calculating, by using each of the temporal frames as a target temporal frame, motion information weights of the target temporal frame on the convolutional channels according to original feature submaps of the target temporal frame and original feature submaps of a next temporal frame, and obtaining motion information feature maps of the target temporal frame on the convolutional channels according to the motion information weights; performing temporal convolution on the motion information feature maps of the target temporal frame to obtain temporal motion feature maps of the target temporal frame; and recognizing an action type of a moving object in image data of the target temporal frame according to the temporal motion feature maps of the target temporal frame on the convolutional channels.

Abstract: A method for preparing aluminum foam sandwich material by rotating friction extrusion and electromagnetic pulse hybrid process includes: step 1: preparing the filler; step 2: processing the filler to prepare a plurality of preforms; step 3: clamping and fixing the plurality of preforms to form a preform assembly; step 4: welding the panel on the surface of the preform assembly to form an non-foaming sandwich material; step 5: heating and foaming the non-foaming sandwich material through a foaming mold; step 6: insulating the foaming mold after completion of foaming; injecting cooling water into the foaming mold after completion of insulation to maintain pressure and shape, forming the aluminum foam sandwich material of the required shape. The aluminum foam sandwich material produced by this method has good interface bonding, no adverse interface reaction, high bending resistance, impact resistance, and excellent sound absorption and insulation properties.

Abstract: Training and using a machine learning model for data extraction is provided. The method comprises receiving keys of interest received from a user through an interface and receiving a batch of documents containing unstructured text. Unstructured text of a first document is processed to extract structured text. The model predicts text classifications of the structured text according to the keys of interest. The predicted text classifications are output to the user through the interface. Annotations to correct any incorrect predictions are received from the user, and the model is retrained according to the annotations. The above steps are repeated for less than ten additional documents from the batch until the model has been trained to predict text classifications with a specified level of accuracy. The trained model then classifies extracted structured text in the remaining documents in the batch.

Abstract: The present invention includes a durable, weather resistant, and light weight apparatus for covering a vehicle and providing protection from objects that might strike and damage the exterior surfaces of the vehicle. The object of this invention is to provide a vehicle cover which covers both the horizontal and vertical surfaces of a vehicle, which can deployed by a single person, folded for easy deployment, retrieval and storage, and which can be stretched or compressed to fit various sizes of automobiles while maintaining its protective effectiveness.

Abstract: The present invention includes a durable, weather resistant, and light weight apparatus for covering a vehicle and providing protection from objects that might strike and damage the exterior surfaces of the vehicle. The object of this invention is to provide a vehicle cover which covers both the horizontal and vertical surfaces of a vehicle, which can deployed by a single person, folded for easy deployment, retrieval and storage, and which can be stretched or compressed to fit various sizes of automobiles while maintaining its protective effectiveness.

Abstract: A garage stop guidance pole, including: a) a telescopic pole, b) a support spring that holds the telescopic pole, and c) a base holding the support spring and requiring no fastening to a wall or a floor. The support spring is strong enough to hold the pole straight when neither the pole nor the spring is touched by a vehicle to be guided but provides swing motion when it is bumped by the vehicle to provide indication to the vehicle driver to stop at a preferred location.

Abstract: A glare reducing shield as a sun visor extender for use with traditional existing sun visor and the side window of a vehicle comprises a support bar, elastic band and glare reducing shields which may be in different color and transparent, magnets are used in the easy removable attachments, storages and provides flexibility to shift shield in ways that can deflect or reduce light from different directions.