video search - ReadWriteWeb http://www.readwriteweb.com/feeds/tag/video search en Copyright 2012 Richard MacManus readwriteweb@gmail.com Tue, 14 Feb 2012 18:04:00 -0800 http://www.sixapart.com/movabletype/?v=4.35-en http://blogs.law.harvard.edu/tech/rss Microsoft to Bolster Its Futuristic Video Search With VideoSurf Acquisition VideoSurf, a search engine for online video content, has been acquired by Microsoft, it was announced today. The service's sophisticated, multi-source video search technology will be built into Microsoft's XBox Live platform, which will see several new entertainment media partnerships in the coming months.

The acquisition, which cost Microsoft a reported $70 million, brings facial and object-recognition video search to the XBox, so it no longer relies solely on descriptions and other meta data when conducting searches. It works across services, so a search for "Lady Gaga" will return results from Netflix, Hulu and a variety of online video sources.

]]> Microsoft is planning on adding content from HBO, Comcast, Verizon, the BBC and several others over the course of the next few months. This expanded offering of video content will be more easily searched and accessed thanks to VideoSurf's backend technology.

In the meantime, they're also going to be rolling out voice search capabilities on the Kinect for XBox 360, which will add a Siri-like functionality to the experience. The Kinect can already understand basic voice commands for things like pausing and playing a movie, in addition to its infamously awesome motion-based, hands-free controls.

Microsoft said they plan on launching voice search for XBox LIVE over the course of the holiday season and they expect the VideoSurf integration to improve the functionality over time.

]]> Discuss]]>
http://www.readwriteweb.com/archives/microsoft_xbox_kinect_video_search_videosurf.php http://www.readwriteweb.com/archives/microsoft_xbox_kinect_video_search_videosurf.php Microsoft Tue, 22 Nov 2011 13:45:01 -0800 John Paul Titlow
Yahoo Video Search Gets Musical yahoo logo.jpgYahoo just announced that it has upgraded its video search product with new features that make it easier to discover music videos. Yahoo Video Search now recognizes and shows the most popular albums and songs whenever a user searches for an artist or band. A sidebar on Yahoo Video Search now displays an artist's most popular albums and songs. The album view then allows users to drill down even deeper and see videos for all the songs on this album.

]]> yahoo_video_twitter.jpg

Yahoo Video Search lets users filter searches by the length of the videos. Search queries can also be restricted to official videos from a band or artist. Just like it does with non-music related searches, Yahoo also features recently shared videos from Twitter at the top of the search results.

Yahoo Video displays videos from services like YouTube, DailyMotion or MetaCafe right on the search results page. For the vast majority of video services like Artist Direct, however, users have to leave the site to see these videos. In our tests, this new feature mostly worked as advertised, though it sometimes showed songs that weren't part of the album we had selected.

Reaction to Google Music Search?

It is worth noting that while Google launched its new Google Music Search service last month, Yahoo also offers a seamless integration with Rhapsody on its site.

]]> Discuss]]>
http://www.readwriteweb.com/archives/yahoos_video_search_music.php http://www.readwriteweb.com/archives/yahoos_video_search_music.php News Thu, 05 Nov 2009 10:36:23 -0800 Frederic Lardinois
Jinni: Wants to be Pandora for Movies We're currently running a series of posts about recommendation technologies and in the comments of our last post about the Netflix Prize, a company called Jinni made itself known. Jinni is a kind of 'Pandora for movies', because it aims to recommend movies and tv shows to you based on its Movie Genome (aping Pandora's Music Genome Project). Jinni's genome project contains over two thousand "genes" that describe plot, mood, style, setting, soundtrack and more. Jinni says that its ontology was created by film professionals - much like Pandora employs people to create its unique music database.

]]> How it Works

Jinni says that its video content is automatically indexed, using a mixture of metadata and reviews. It has a strong semantic technologies component, as it uses a proprietary Natural Language Processing solution to assign semantic tags to content and users. The company claims that this allows Jinni to "rapidly index more titles, becoming the universal catalog for professional video." When it launched in December, Jinni had 10,000 movie, TV and video titles. It also offers APIs for Internet and TV content providers.

In terms of its recommendations philosophy, Jinni believes that a mix of algorithms and human selection is the best solution. Although the initial data set comes from humans entering movie information into a computer, the actual recommendations come from its algorithm - which "can deeply analyze the type of content you like" and hence learn about your tastes in movies. Jinni gives you recommendations by "comparing your Taste Types and the genes of all the titles in our catalog".

Does it Work?

I took Jinni for a test drive, with a search on 'mood'. I quite like an "offbeat" movie on a Friday night, so it was an appropriate place to start. Also 'offbeat' movies like Napoleon Dynamite are the type of films that have caused the Netflix Prize contestants a lot of problems. So I clicked on that mood to see what came up.

The default video selections included ones like Twin Peaks, Donnie Darko, Hot Fuzz, Monty Python, and so on. It was a fairly predictable selection, but where Jinni promises to come into its own is when you filter down. There is a 'Story Tuner', which presented some interesting filter options.

I filtered based on the story tuners (little known, light, realistic, fast-ish) and got recommended a 1990 movie called 'Mr Destiny' starring James Belushi. I can't recall ever seeing it (little known? check!) and while I'm not really a James Belushi fan, it'd be worth a try. I tweaked the light/serious meter up to 'serious' and that gave me a neat selection of 9 films, few of which I'd seen - but they all looked interesting. This is what you want from a recommendation engine - to be told about products you didn't know about before. So Jinni appears to work quite well. There are many other filters other than mood; rating, date, length, plot, genres, and more.

In his review, Chris Gampat concluded that Jinni isn't quite Pandora for movies. That may be true, but we think Jinni is worth a try if you're a movie or tv show buff. It's also similar to ClerkDogs, which we reviewed recently. So if you've tried either or both, let us know in the comments what you thought.

ReadWriteWeb Resources for Recommendation Technologies

We will be profiling other recommendation companies in upcoming posts. We also invite you to explore using our custom ReadWriteWeb Resources:

]]> Discuss]]>
http://www.readwriteweb.com/archives/jinni_pandora_for_movies.php http://www.readwriteweb.com/archives/jinni_pandora_for_movies.php Recommendation Engines Thu, 22 Jan 2009 22:15:49 -0800 Richard MacManus
LeWeb'08 Wrapup Le Web 2008 conference, the web conference held this week in Paris, was not about bright, shiny, and new. It was about solid, reliable, and usable. The creative energy of the past few years now seems to be channelled towards building and growing apps that everyone, not just the tech community, wants. Here's a rundown of the major topics covered: portable identity, improved search, cloud storage, and video search.

]]> This is a guest post by Conor O'Neill, CEO, LouderVoice.

Portable Identity

Identity and portable identity/data remain hot topics. Luckily, the conference wasn't just another pointless "200x is the year of OpenID" love-fest. There were sessions on OAuth, MySpaceID, and Facebook Connect. At one of the Facebook Garage sessions, Dave Morin dug into the nitty gritty of Facebook Connect and really impressed. OpenID and OAuth remain medium-term goals for many web apps, while Connect has jumped immediately to the front on their development road map. This goes to the core vibe of Le Web 2008, which was all about business benefit.

Improved Search

Despite having nothing earth-shattering to say, Marissa Meyer of Google still captured the attention of the audience. Led by some excellent questions, she covered topics such as temporal search (which gives only results from a certain time period), personal search (if the search engine knows what you searched for and liked before, it can give you better results next time), and local search. Meyer noted that she thinks local search in particular will be a hot feature for 2009. There are many start-ups trying to crack this particular nut, but one can see from Google Maps, and more specifically the latest versions of Google Maps Mobile, that these start-ups should be very afraid and need to create something far better than a Google Maps mashup to succeed.

Cloud Storage

Cloud computing and storage is becoming more mainstream every day. There was nothing particularly new from Werner Vogels at Le Web apart from news that EC2 is now fully available in Europe. Amazon's offerings remain geared more to infrastructure, relying on others, such as PutPlace, JungleDisk, and RightScale, to deliver storage that is easily accessible. This is why people have been paying attention to Microsoft's current direction. Every Live product put out by Microsoft in the past two years has been bettered by the competition. There is one clear exception to this: Live Mesh. This is the first consumer-facing Microsoft web app that nails it. At my home we have it installed on four machines and have a directory tree on each syncing seamlessly no matter where we are. Who needs a home server or home network-attached storage (NAS) when Live Mesh does it all without you having to think?

Video Search

Didier Lombard, the head of France Telecom/Orange, said that the next big thing would be "video search," which initially sounded laughable. Then Google confirmed that it has been studying it for a long time, and then we found out that the start-up competition winner was Viewdle, which does exactly that. Viewdle's reps gave a fantastic overview of the technology, which of course spooked many when it was pointed out that it was originally developed for military applications. Being able to parse faces in video and associate them with specific people is mind-blowing. With $500 dual-core boxes, they can parse in nearly real-time, and with massively parallel NVidia GPUs, they can go far beyond that. Expect an exit here in 2009.

Business as usual

Much of the rest of Le Web was about business (and love!), with many presentations by successful web companies that aren't particularly technically innovative. From travel review websites to website builders to mobile IM, we've seen these before. The difference now is that many of these businesses are making money. Let's hope that 2009 shows more progress in both business and technology.

This was a guest post by Conor O'Neill, CEO, LouderVoice; conference photos courtesy of Flickr.

]]> Discuss]]>
http://www.readwriteweb.com/archives/le_web_2008.php http://www.readwriteweb.com/archives/le_web_2008.php Conferences Sat, 13 Dec 2008 01:00:00 -0800 Guest Author