Personal Profile

Google

Teaching an AI to Detect Key Actors in Multi-person Videos

Teaching an AI to Detect Key Actors in Multi-person Videos

Teaching an AI to Detect Key Actors in Multi-person Videos

Researchers from Google and Stanford have taught their computer vision model to detect the most important person in a multi-person video scene – for example, who the shooter is in a basketball game which typically contains dozens or hundreds of people in a scene.

Using 20 Tesla K40 GPUs and the cuDNN-accelerated Tensorflow deep learning framework to train their recurrent neural network on 257 NCAA basketball games from YouTube, an attention mask selects which of the several people are most relevant to the action being performed, then tracks relevance of each object as time proceeds. The team published a paper detailing more of their work.

The distribution of attention for the model with tracking, at the beginning of “free-throw success”. The attention is concentrated at a specific defender’s position. Free-throws have a distinctive defense formation, and observing the defenders can be helpful as shown in the sample images in the top row.

The distribution of attention for the model with tracking, at the beginning of “free-throw success”. The attention is concentrated at a specific defender’s position. Free-throws have a distinctive defense formation, and observing the defenders can be helpful as shown in the sample images in the top row.

Over time the system can identify not only the most important actor, but potential important actors and the events with which they are associated – such as, the ability to understand the player going up for a layup could be important, but that the most important player is the one who then blocks the shot.

Daniel Ambrosi Dreamscapes Share Your Science: Pushing the Limits of Computational Photography

Share Your Science: Pushing the Limits of Computational Photography

Share Your Science: Pushing the Limits of Computational Photography

Daniel Ambrosi, Artist and Photographer, is using NVIDIA GPUs in the Amazon cloud and CUDA to create giant 2D-stitched HDR panoramas called “Dreamscapes.” Ambrosi applies a modified version of Google’s DeepDream neural net visualization code to his original panoramic landscape images to create truly one-of-a-kind pieces of art.

For more information visit http://www.danielambrosi.com/Dreamscapes.

Share your GPU-accelerated science with us at http://nvda.ly/Vpjxr and with the world on #ShareYourScience.

Watch more scientists and researchers share how accelerated computing is benefiting their work at http://nvda.ly/X7WpH

AlphaGo Wins Game One Against World Go Champion

AlphaGo Wins Game One Against World Go Champion

AlphaGo Wins Game One Against World Go Champion

Last night Google’s AI AlphaGo won the first in a five-game series against the world’s best Go player, in Seoul, South Korea. The success comes just five months after a slightly less experienced version of the same program became the first machine to defeat any Go professional by winning five games against the European champion.

This victory was far more impressive though because it came at the expense of Lee Sedol, 33, who has dominated the ancient Chinese game for a decade. The European champion, Fan Hui, is ranked only 663rd in the world.

And the machine, by all accounts, played a noticeably stronger game than it did back in October, evidence that it has learned much since then. Describing their research in the journal Nature, AlphaGo’s programmers insist that it now studies mostly on its own, tuning its deep neural networks by playing millions of games against itself.

AlphaGo Wins Game One Against World Go Champion

AlphaGo Wins Game One Against World Go Champion

The object of Go is to surround and capture territory on a 19-by-19 board; each player alternates to place a lozenge-shaped white or black piece, called a stone, on the intersections of the lines. Unlike in chess, the player of the black stones moves first.

The neural networks judge the position, and do so well enough to play a good game. But AlphaGo rises one level further by yoking its networks to a system that generates a “tree” of analysis that represents the many branching possibilities that the game might follow. Because so many moves are possible the branches quickly become an impenetrable thicket, one reason why Go programmers haven’t had the same success as chess programmers when using this “brute force” method alone. Chess has a far lower branching factor than Go.

It seems that AlphaGo’s self-improving capability largely explains its quick rise to world mastery. By contrast, chess programs’ brute-force methods required endless fine-tuning by engineers working together with chess masters. That partly explains why programs took nine years to progress from the first defeat of a grandmaster in a single game, back in 1988, to defeating then World Champion Garry Kasparov, in a six-game match, in 1997.

Even that crowning achievement—garnered with worldwide acclaim by IBM’s Deep Blue machine—came only on the second attempt. The previous year Deep Blue had managed to win only one game in the match—the first. Kasparov then exploited weaknesses he’d spotted in the computer’s game to win three and draw four subsequent games.

Sedol appears to face longer odds of staging a comeback. Unlike Deep Blue, AlphaGo can play numerous games against itself during the 24 hours until Game Two (to be streamed live tonight at 11 pm EST, 4 am GMT). The machine can study ceaselessly, unclouded by worry, ambition, fear, or hope.

Sedol, the king of the Go world, must spend much of his time sleeping—if he can. Uneasy lies the head that wears a crown.

Deep-learning algorithm predicts photos’ memorability at “near-human” levels

Future versions of an algorithm from the Computer Science and Artificial Intelligence Lab could help with teaching, marketing, and memory improvement.

Deep-learning algorithm predicts photos’ memorability at “near-human” levels

Deep-learning algorithm predicts photos’ memorability at “near-human” levels

Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) have created an algorithm that can predict how memorable or forgettable an image is almost as accurately as humans — and they plan to turn it into an app that subtly tweaks photos to make them more memorable.

For each photo, the “MemNet” algorithm — which you can try out online by uploading your own photos — also creates a heat map that identifies exactly which parts of the image are most memorable.

“Understanding memorability can help us make systems to capture the most important information, or, conversely, to store information that humans will most likely forget,” says CSAIL graduate student Aditya Khosla, who was lead author on a related paper. “It’s like having an instant focus group that tells you how likely it is that someone will remember a visual message.”

Team members picture a variety of potential applications, from improving the content of ads and social media posts, to developing more effective teaching resources, to creating your own personal “health-assistant” device to help you remember things.

Part of the project the team has also published the world’s largest image-memorability dataset, LaMem. With 60,000 images, each annotated with detailed metadata about qualities such as popularity and emotional impact, LaMem is the team’s effort to spur further research on what they say has often been an under-studied topic in computer vision.

The paper was co-written by CSAIL graduate student Akhil Raju, Professor Antonio Torralba, and principal research scientist Aude Oliva, who serves as senior investigator of the work. Khosla will present the paper in Chile this week at the International Conference on Computer Vision.

How it works

The team previously developed a similar algorithm for facial memorability. What’s notable about the new one, besides the fact that it can now perform at near-human levels, is that it uses techniques from “deep-learning,” a field of artificial intelligence that use systems called “neural networks” to teach computers to sift through massive amounts of data to find patterns all on their own.

Such techniques are what drive Apple’s Siri, Google’s auto-complete, and Facebook’s photo-tagging, and what have spurred these tech giants to spend hundreds of millions of dollars on deep-learning startups.

“While deep-learning has propelled much progress in object recognition and scene understanding, predicting human memory has often been viewed as a higher-level cognitive process that computer scientists will never be able to tackle,” Oliva says. “Well, we can, and we did!”

Neural networks work to correlate data without any human guidance on what the underlying causes or correlations might be. They are organized in layers of processing units that each perform random computations on the data in succession. As the network receives more data, it readjusts to produce more accurate predictions.

The team fed its algorithm tens of thousands of images from several different datasets, including LaMem and the scene-oriented SUN and Places (all of which were developed at CSAIL). The images had each received a “memorability score” based on the ability of human subjects to remember them in online experiments.

The team then pitted its algorithm against human subjects by having the model predicting how memorable a group of people would find a new never-before-seen image. It performed 30 percent better than existing algorithms and was within a few percentage points of the average human performance.

For each image, the algorithm produces a heat map showing which parts of the image are most memorable. By emphasizing different regions, they can potentially increase the image’s memorability.

“CSAIL researchers have done such manipulations with faces, but I’m impressed that they have been able to extend it to generic images,” says Alexei Efros, an associate professor of computer science at the University of California at Berkeley. “While you can somewhat easily change the appearance of a face by, say, making it more ‘smiley,’ it is significantly harder to generalize about all image types.”

Looking ahead

The research also unexpectedly shed light on the nature of human memory. Khosla says he had wondered whether human subjects would remember everything if they were shown only the most memorable images.

“You might expect that people will acclimate and forget as many things as they did before, but our research suggests otherwise,” he says. “This means that we could potentially improve people’s memory if we present them with memorable images.”

The team next plans to try to update the system to be able to predict the memory of a specific person, as well as to better tailor it for individual “expert industries” such as retail clothing and logo design.

“This sort of research gives us a better understanding of the visual information that people pay attention to,” Efros says. “For marketers, movie-makers and other content creators, being able to model your mental state as you look at something is an exciting new direction to explore.”

The work is supported by grants from the National Science Foundation, as well as the McGovern Institute Neurotechnology Program, the MIT Big Data Initiative at CSAIL, research awards from Google and Xerox, and a hardware donation from Nvidia.

5 tricks for working faster in Google Drive

Send files directly to Drive, create new documents with one click, and more.

5 tricks for working faster in Google Drive

5 tricks for working faster in Google Drive

Create a Drive bookmark

Google Chrome was designed to give you easy access to Drive. But if Firefox is your preferred browser, you can create your own shortcut to Drive and its contents.

With Drive open in your browser, create a bookmark. Then right-click on that bookmark and select Properties. Enter Drive in the keyword field. Now when you want to access Drive, just type Drive in Firefox’s address bar, and it will open.

Follow the same steps to create shortcuts to any files in your Drive account.

Find shared documents by collaborator

Google Drive makes collaboration nearly effortless. So, it’s likely you’ve accumulated a healthy collection of shared documents. That can make it difficult to find the one you need even when using the Shared with Me link in Drive’s left sidebar.

You can search for collaborators by name in Drive.

You can search for collaborators by name in Drive.

 

To narrow the list of shared documents to a particular collaborator, type their name in the search bar at the top. This will thin the choices just to docs you worked on together.

Add Drive to Windows’ “Send to” menu

If you’ve already installed Google Drive on Windows, you can enable this useful shortcut. Navigate to Users > [yourusername] > AppData > Roaming > Microsoft > Windows > SendTo. Find Google Drive on the Favorites bar and drag it to the SendTo folder. This will let you right-click on any file in Windows and express it directly to Drive.

Preview multiple documents

There’s nothing efficient about opening a bunch of individual documents to find the one you want. Fortunately, in Drive you don’t have to.

Use Drive’s preview feature to toggle through a range of files without opening them all.

Use Drive’s preview feature to toggle through a range of files without opening them all.

 

Start by either Shift-clicking (for a continuous range of files) or Control-clicking (for a non-continuous range) the documents you want to preview. Next, click the eye icon in the top right of the browser window. Thumbnails of each file will appear in a preview bar across the bottom of the browser window. Toggle through them to sneak a full-size peek at each one.

Use quick creation links

Rather than opening a new browser tab and logging in to Drive each time you want to create a new document or spreadsheet, shave off some time by using quick creation links. These links are written as “http://drive.google.com/document/create” but you replace “document” with “presentation,” “spreadsheet,” and “drawing” for each link. Then drag all of them to your bookmark toolbar. Next time you need to create one of these documents, you can do it with one click.

Google Docs now lets you dictate formatting edits

New Voice Commands give additional control beyond Google’s dictation system

Google Docs now lets you dictate formatting edits

Google Docs now lets you dictate formatting edits

Last year, Google introduced a Voice Typing feature for the desktop Web version of Google Docs that allowed users to dictate their documents. It’s now getting upgraded to let people control formatting with voice commands as well.

Using voice commands, people can select and format text, all without having to touch the keyboard. This is great news for people who already use the feature to transcribe their words.

Google says the accuracy is improved by the work it’s already done with voice recognition in other applications. Now, that same technology is making it possible to do things like align text and even remove formatting altogether.

Right now, the feature is only available through Google Docs when using Google’s Chrome browser on a desktop computer. But looking to the future, this feature could be a major boost to Docs’s editing capabilities on mobile. One of the biggest issues with writing a long document on a mobile device is that the keyboards on smartphones and tablets are usually awkward for extended use.

Right now, people can use the system keyboards on iOS and Android to do dictation, but they don’t have support for the voice commands.

What’s more, this feature has implications for accessibility in Google Docs. Using these tools, people who have limited use of a keyboard will be able to talk to their computer and type out documents more easily without using their hands.

Google competes with several other players in the productivity application market, notable Microsoft, and a powerful voice typing feature in Docs could help Google to attract new users.

Google AI Algorithm Masters Ancient Game of Go

GPU accelerated GoFor the first time, a computer has beaten a human professional at the game of Go — an ancient board game that has long been viewed as one of the greatest challenges for Artificial Intelligence.

Google DeepMind’s GPU-accelerated AlphaGo program beat Fan Hui, the European Go champion, five times out of five in tournament conditions.

Demis Hassabis, who oversees DeepMind, mentioned in a recent article that DeepMind’s deep learning system works pretty well on a single computer equipped with a decent number of GPU accelerators, but for the match against Fan Hui, the researchers used a larger network of computers that spanned about 170 GPUs. This larger computer network both trained the system and played the actual game, drawing on the results of the training.

The team confirmed they will use the same setup when they take on the Go world champion in South Korea.

Rémi Coulom, the French researcher behind what was previously the world’s top artificially intelligent Go player, has spent the past decade trying to build a system capable of beating the world’s best players, and now, he believes that system is here. “I’m busy buying some GPUs,” he says.



Popular Pages
Popular posts
Interested
About me

My name is Sayed Ahmadreza Razian and I am a graduate of the master degree in Artificial intelligence .
Click here to CV Resume page

Related topics such as image processing, machine vision, virtual reality, machine learning, data mining, and monitoring systems are my research interests, and I intend to pursue a PhD in one of these fields.

جهت نمایش صفحه معرفی و رزومه کلیک کنید

My Scientific expertise
  • Image processing
  • Machine vision
  • Machine learning
  • Pattern recognition
  • Data mining - Big Data
  • CUDA Programming
  • Game and Virtual reality

Download Nokte as Free


Coming Soon....

Greatest hits

The fear of death is the most unjustified of all fears, for there’s no risk of accident for someone who’s dead.

Albert Einstein

Anyone who has never made a mistake has never tried anything new.

Albert Einstein

You are what you believe yourself to be.

Paulo Coelho

Waiting hurts. Forgetting hurts. But not knowing which decision to take can sometimes be the most painful.

Paulo Coelho

One day you will wake up and there won’t be any more time to do the things you’ve always wanted. Do it now.

Paulo Coelho

Imagination is more important than knowledge.

Albert Einstein

It’s the possibility of having a dream come true that makes life interesting.

Paulo Coelho

Gravitation is not responsible for people falling in love.

Albert Einstein


Site by images
Statistics
  • 2,319
  • 10,075
  • 92,535
  • 25,499
Recent News Posts