From Yezhou Yang, Yi Li, Cornelia Fermuller and Yiannis Aloimonos: In order to advance action generation and creation in robots beyond simple learned schemas we need computational tools that allow us to automatically interpret and represent human actions. This paper presents a system that learns manipulation action plans by processing unconstrained videos from the World Wide Web. Its goal is to robustly generate the sequence of atomic actions of seen longer actions in video in order to acquire knowledge for robots. The lower level of the system consists of two convolutional neural network (CNN) based recognition modules, one for classifying the hand grasp type and the other for object recognition. The higher level is a probabilistic manipulation action grammar based parsing module that aims at generating visual sentences for robot manipulation. The list of the grasping types. Experiments conducted on a publicly available unconstrained video dataset show that the system is able to learn manipulation actions by “watching” unconstrained videos with high accuracy.... ( article at Kurzweilai.net ) ( original paper )
Records 526 to 526 of 526
Print On Any Surface...Metals, Plastics/Composites and Glass. Handheld Printers and InLine Inkjet Printing Systems for Factory Automation, with PLC Control. Inkjet Coding and Marking Printers can be used for direct coding of parts or industrial products and compliance marking on Primary or Secondary Packaging. Small or Large Character Inkjet Coding & Marking with Barcodes and Logo Graphics printing. Integration with Handheld Barcode Readers (Scan and Print) for Track and Trace and Database connectivity printing of variables data. Motion Control Traverser Printing Automation. Top Brands: EBS HandJet 260, EBS250 HandJet, Sojet V1H Handheld Printer, Reiner JetStamp 790MP and RN Mark 7 Printing System.