Showing posts with label algorithm. Show all posts
Showing posts with label algorithm. Show all posts
YouTube have refreshed home screen for its app it also updated recommendation system, now YouTube mobile app have bigger images(Thumbnail) and very smart recommendations based on “deep neural network” technology.
YouTube is launching a redesigned home tab for its mobile apps — touting its “clean and simple” format — along with an improved recommendation engine, in a bid to spur smartphone users to watch even more videos. The new design, available for the YouTube app on iOS and Android, features large, high-resolution images to make it easier for users to identify videos they want to watch, and a prominent icon highlights the creator for every video.
Youtube app kind of cluttered home screen for quite some time. In fact, many users steered away from the home screen as soon as possible, going directly to the search bar or their subscribed lists. Now, however, YouTube is taking some design cues from the likes of Instagram to make their home screen far cleaner and more enjoyable.
Gone are the cramped videos splattered across the screen like a dropped shoebox filled with polaroids. Instead, suggested videos take up the entire width of the screen with only about two being visible at once. This friendlier look encourages scrolling and makes the app feel slicker and tidier all around. The update is live now, so check your app and see if it’s hit your device yet.
That’s not all this update brings to the table. The devs have also toyed with the algorithms for recommending videos, meaning the videos you see on your home screen are more relevant and personalized than before. These alterations make use of deep neural network technology, so the app will continue to learn your preferences and habits to deliver you content you’ve never seen but are sure to enjoy. The company claims that users who have had test versions of this update have spent more time watching new videos from the creators they subscribe to.
According to YouTube, the video service adds a few tweaks every week to improve its recommendation engine. In the new versions of the app, the “shelves” that grouped similar videos together have been replaced with a single ranked list.
Give the new design a try and then let us know what you think about youtube new design in the comment section below!
Researchers at the Georgia Institute of Technology unveiled a novel video-editing solution this week that automatically sorts and edits untouched footage into the most picturesque highlights for a vacation reel that could fill anyone with envy.
The new approach is an algorithm -- developed by students Daniel Castro and Vinay Bettadapura under the guidance of Professor Irfan Essa -- that analyzes video for images with ideal artistic properties. It first considers geolocation, then composition, symmetry and color vibrancy to determine what is important or picturesque. Video frames with the highest scores are processed into a highlight reel.
Castro and Bettadapura conceived the approach after the latter returned from a two-week vacation, driving coast-to-coast across the southern United States. He ended the trip with 26.5 hours of footage from a wearable, head-mounted camera. He had no idea what do with it.
"The data was essentially useless because there was just too much of it," said Bettadapura, who completed his Ph.D. in the fall and now is a Google software engineer. "We liked the idea of being able to automatically generate photo albums from your vacation, algorithmically."
The algorithm turned 26 hours of video into a 38-second highlight reel in three hours. Because Bettadapura had worn a head-mounted Contour Action Camera that captured GPS data, the algorithm could filter by geographical location. That reduced the footage to 16 hours. Shot boundary detection further reduced it into 1,724 video shots or about 10.2 hours of video. It then processed for artistic quality and provided an output of the most picturesque content. Processing time is variable and depends on the number of computers used.
The algorithm can be adapted to user preferences.
"We can tweak the weights in our algorithm based on the user's aesthetic preferences," Bettadapura said. "By incorporating facial recognition, we can further adapt the system to generate highlights that include people the user cares about."
Castro and Bettadapura presented their findings at WACV 2016: IEEE's Winter Conference on the Applications of Computer Vision, March 7, 2016 in Lake Placid, N.Y. The pair will continue to work together testing the algorithm with multiple participants to help generalize the approach, incorporate facial recognition, and develop data visualization techniques that make it easy to browse and search specific moments. The implications of future, successful tests could echo far beyond their initial work at Georgia Tech.
"This research brings together multiple modalities to more efficiently understand large amounts of data," said Castro, who is completing his Ph.D. in computer science and also working as an intern at Google. "We are trying to optimize how easy it is to understand all of the data we have in an efficient manner because otherwise it would be impossible to do so."
Castro and Bettadapura conceived the approach after the latter returned from a two-week vacation, driving coast-to-coast across the southern United States. He ended the trip with 26.5 hours of footage from a wearable, head-mounted camera. He had no idea what do with it.
"The data was essentially useless because there was just too much of it," said Bettadapura, who completed his Ph.D. in the fall and now is a Google software engineer. "We liked the idea of being able to automatically generate photo albums from your vacation, algorithmically."
The algorithm turned 26 hours of video into a 38-second highlight reel in three hours. Because Bettadapura had worn a head-mounted Contour Action Camera that captured GPS data, the algorithm could filter by geographical location. That reduced the footage to 16 hours. Shot boundary detection further reduced it into 1,724 video shots or about 10.2 hours of video. It then processed for artistic quality and provided an output of the most picturesque content. Processing time is variable and depends on the number of computers used.
The algorithm can be adapted to user preferences.
"We can tweak the weights in our algorithm based on the user's aesthetic preferences," Bettadapura said. "By incorporating facial recognition, we can further adapt the system to generate highlights that include people the user cares about."
Castro and Bettadapura presented their findings at WACV 2016: IEEE's Winter Conference on the Applications of Computer Vision, March 7, 2016 in Lake Placid, N.Y. The pair will continue to work together testing the algorithm with multiple participants to help generalize the approach, incorporate facial recognition, and develop data visualization techniques that make it easy to browse and search specific moments. The implications of future, successful tests could echo far beyond their initial work at Georgia Tech.
"This research brings together multiple modalities to more efficiently understand large amounts of data," said Castro, who is completing his Ph.D. in computer science and also working as an intern at Google. "We are trying to optimize how easy it is to understand all of the data we have in an efficient manner because otherwise it would be impossible to do so."
1. In BFS the root node is expanded first, then all the successors of the root node are expanded, and in next step all the successors of every node are expanded, the process continues till the goal is achived. while
In DFS we explore the root node and traverse as far as possible from the root node untill the goal is achived.
2.In BFS the space complexity is more critical as compared to time complexity. while
In DFS has lesser space complexity, because at a time it needs to store only single path from the root to leaf node.
3.Breadth First Search can be done with the help of queue i.e, FIFO(First In First Out) while
Depth First Search can be done with the help of stack i.e. LIFO(Last In First Out).
4.BFS is slower than DFS while
DFS is more faster than BFS.
5.BFS requires more memory compare to DFS while
DFS require less memory compare to BFS.
6.BFS is useful in finding shortest path while
DFS in not so useful in finding shortest path.
BFS Example

DFS Example

In DFS we explore the root node and traverse as far as possible from the root node untill the goal is achived.
2.In BFS the space complexity is more critical as compared to time complexity. while
In DFS has lesser space complexity, because at a time it needs to store only single path from the root to leaf node.
3.Breadth First Search can be done with the help of queue i.e, FIFO(First In First Out) while
Depth First Search can be done with the help of stack i.e. LIFO(Last In First Out).
4.BFS is slower than DFS while
DFS is more faster than BFS.
5.BFS requires more memory compare to DFS while
DFS require less memory compare to BFS.
6.BFS is useful in finding shortest path while
DFS in not so useful in finding shortest path.
BFS Example
DFS Example

