Deep Visual-Semantic Alignments for Generating Image Descriptions

Because of the Nov. 14th submission  deadline for this years IEEE Conference on Computer Vision and Pattern Recognition (CVPR) several big image-recognition papers are coming out this week: From Andrej Karpathy and Li Fei-Fei of Stanford: We present a model that generates free-form natural language descriptions of image regions. Our model leverages datasets of images and their sentence descriptions to learn about the inter-modal correspondences between text and visual data. Our approach is based on a novel combination of Convolutional Neural Networks over image regions, bidirectional Recurrent Neural Networks over sentences, and a structured objective that aligns the two modalities through a multimodal embedding. We then describe a Recurrent Neural Network architecture that uses the inferred alignments to learn to generate novel descriptions of image regions. We demonstrate the effectiveness of our alignment model with ranking experiments on Flickr8K, Flickr30K and COCO datasets, where we substantially improve on the state of the art. We then show that the sentences created by our generative model outperform retrieval baselines on the three aforementioned datasets and a new dataset of region-level annotations... ( website with examples ) ( full paper ) From Oriol Vinyals, Alexander Toshev, Samy Bengio, and Dumitru Erhan at Google: Show and Tell: A Neural Image Caption Generator  ( announcement post ) ( full paper ) From Ryan Kiros, Ruslan Salakhutdinov, Richard S. Zemel at University of Toronto: Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models  ( full paper ) From Junhua Mao, Wei Xu, Yi Yang, Jiang Wang and Alan L. Yuille at Baidu Research/UCLA: Explain Images with Multimodal Recurrent Neural Networks  ( full paper ) From Jeff Donahue, Lisa Anne Hendricks, Sergio Guadarrama, Marcus Rohrbach, Subhashini Venugopalan, Kate Saenko, and Trevor Darrell at UT Austin, UMass Lowell and UC Berkeley: Long-term Recurrent Convolutional Networks for Visual Recognition and Description ( full paper ) All these came from this Hacker News discussion .

Boston Magazine Profiles Rodney Brooks of Rethink

Long article about Rodney Brooks co-founder of Rethink and former CTO at iRobot: ...Brooks cofounded the bedford-based iRobot in 1990, and his motivation, he explains, had something to do with vanity: “My thoughts on my self-image at the time was that I didn’t really want to be remembered for building insects.” Then he pauses for a moment and laughs. “But after that I started building vacuum-cleaning robots. And now there is a research group using Baxter to open stool samples. So now it’s shit-handling robots. I think maybe I should have quit while I was ahead. You know, that’s something no one ever says: ‘I hope my kid grows up to open stool samples... ( full article )

Rethink Robotics Introduces Industry-First Robot Positioning System

This disruptive technology enables Baxter to switch between tasks without retraining by using environmental markers, called Landmarks™, in conjunction with its existing, embedded vision system.

NEXCOM IoT Controller Solution Brings Intelligence to Manufacturing

In this white paper, NEXCOM will explain how the NEXCOM IoT controller NIFE 100 provides a unique open-architecture solution with the configuration flexibility to surmount communication barriers in building the Factory-of- Things and supporting the necessary data communications for connecting the enterprise domain and the operation domain.

Grabit Inc. Demos Electrostatic Gripper

From Grabit Inc.: Enhanced Flexibility Grabit technology eliminates the need for part-specific grippers and minimizes gripper changeover, dramatically reducing costs and downtime. Gentle Handling Grabit grippers offer scratch and smudge-free handling with its clean grasping and eliminates the need to remove residue left by vacuum cups. Grabit’s uniform grasping effect eliminates high “point stresses” on large format glass sheets. Low Energy & Quiet Operations Grabit products operate at ultra-low energy levels providing cost savings and enabling mobile robot applications, and also offer quiet operations improving factory conditions and supporting the adoption of collaborative robots... ( homepage )

Formosa Plastics Wins with Open Intel ® Architecture and Scalable Roadmap

Replacing legacy application-specific integrated circuits (ASIC) with x86 architecture allows the company to deliver products just in time and to achieve about 20 percent of overhead in inventory.

Current Transducer Implementation Phenomena

Implementation of a current transducer is typically a straightforward affair. In the event that the output is not as expected, it must be understood that the source of the challenge may be rooted in the mechanical, magnetic or electric nature of the device.

At Japan Robot Week, Mechanical Barista Treats Visitors to Coffee

From  Japan Times :

iRobot Unveils Its First Multi-Robot Tablet Controller for First Responders, Defense Forces and Industrial Customers

From iRobot: The uPoint MRC system runs an Android-based app that standardizes the control of any robot within the iRobot family of unmanned vehicles. Utilizing the same intuitive touchscreen technology in use today on millions of digital devices, the uPoint MRC system simplifies robot operations including driving, manipulation and inspection, allowing operators to focus more on the mission at hand... ( full press release )

Integrated 2D Imaging Engine from Microscan Helps Improve Production Yield, Quality and Traceability at Each Step of the PCB Manufacturing Process

Case Study: Prodrive Technologies, The Netherlands

Robotics Design, Synthesis and Processing

The total process of building a robot is first to identify a need, then defining the problem that must be overcome to accomplish the need.

Collaborative Robot Development

Since the operator can work in the robot's workspace even when the robot is still in motion at full speed, there is much more collaboration between the operator and robot.

Filling Without Spilling

Watching a form-fill-seal machine in operation is rather fascinating. It looks so easy, but the precision technology needed to ensure that bag after bag is being filled without breaking, or its intended content being misdirected and wasted, is far from simple.

7 Signs That Your Business is Ready for Automation

Investing in automation has to make financial sense for individual businesses, regardless of trends. Here are seven signs that could point to your company's need to automate.

The Hershey Company

Until 2005, everything at the Hershey plant was hand-palletized, resulting in low palletizing rates and high manual labor costs.

Records 211 to 225 of 282

First | Previous | Next | Last

Factory Automation - Featured Product

Stäubli - New TX2 Robotic Series

Stäubli - New TX2 Robotic Series

TX2 series of robots: the next generation of fast and precise 6-axis robots. This new robot range is redefining performance with the optimum balance of speed, rigidity, size and envelope. Those pioneer robots can be used in all areas, including sensitive and restrictive environments thanks to their unique features. Known worldwide for the quality of our design and innovation for more than a century, the Stäubli Group has brought its renowned engineering expertise and technological ingenuity to the forefront of robotics. Since 1982, we have built a highly regarded robotics business, and more significantly, transformed the way thousands of manufacturing operations perform. Today Stäubli Robotics is a leading player in robotics around the world, consistently delivering engineering as effective and reliable as our service and support.