Videogram changes the way online visual media is discovered,consumed, shared and monetized. Rich navigation and social features create an user experience that is totally intuitive and enhances the experience of discovering and consuming video. Patented in 60 countries, Videogram’s deep technologies are incorporated into the platforms and offered as Cloud Services. Videogram is used in website embeds, social feeds, live streaming, mobile and on smart TVs.
Videogram uses its proprietary technology to index video and extract data from each frame automatically. The automatically extracted data includes metadata of the video , speech (sound), scene data using machine learning vision algorithms, objects in frame (Machine Vision Learning), color, motion, & image similarity. A patented statistical model is used to extract area of interest from all the frames of the video. The output of this model is then used to pack the frames into pictorial summary (similar to a comic book). Videogram is the only platform in the world that does this.
Videogram implements Machine Learning techniques across its state-of-the-art models of video content and user behavior. Pixel by pixel, click by click, big data is collected and analysed to improve model accuracy and deliver the most engaging user experience. From proprietary, user-adjusting video presentation format, to accurate voice, object and scene search, all Videogram models constantly morph and evolve according to user preferences, effectively removing consumption bottlenecks across all online video real estate (Web, Smart TV, Mobile).
The first pass to produce a videogram grid/card is done entirely via the Videogram Video Indexer and Machine Learning. The videogram is then embedded in website and/or apps. The platform starts tracking user behavior, tracks frames that are getting clicked, shared, commented. Based on this tracking, algorithms can identify which parts of the video are getting traction. It also tracks objects and speech of those frames that are important to the consumer. This data is used to draw inference on consumer content preference. Machine learning is used to understand similarity of content preference between one to many. The output of this data collection is used to provide user content recommendation & personalization.
Videogram provides rich features to the user to engage on social media. Users can like, comment and share the video frame of interest to them into social networks. This allows for context when other users are discovering content on their newsfeed. This technique is used to funnel traffic from social media sites to the content owner’s site. Videogram also enables video ads relevant to the frame that the user clicked to start the video. For example, if the user clicked on a key frame that shows a person wearing sun glasses then, the platform can programmatically place a video ad for sunglasses in front of that specific frame as a pre-roll video.