In one embodiment, a method includes accessing input data from one or more different input sources. The input sources include: one or more cameras, one or more microphones, and a social graph maintained by a social-networking system. Based on the input data, generating a current descriptive model for a current audio-video communication session that comprises one or more descriptive characteristics about (1) an environment associated with the current audio-video communication session, (2) one or more people within the environment, or (3) one or more contextual elements associated with the current audio-video communication session. The method also includes generating one or more instructions for the current audio-video communication session that are based the one or more descriptive characteristics; and sending the one or more instructions to a computing device associated with the one or more cameras and the one or more microphones.

Systems and methods are provided for performing unbiased recruitment by modifying one or more informative personal attributes from a resume, or audio or audio-video interviews (live or recorded). Modifying may be masking (e.g., redacting, removing, hiding, covering, etc.) or altering (e.g., blurring, disguising, substituting, replacing, etc.), or both, and may be applied independently to the same or different personal attributes. Personal attributes may be masked, altered, or both, for all or a portion of an interview, with audio and video processing techniques being applied on a concurrent and continuous basis. Personal attributes which may be a basis for bias, discrimination or prejudice, whether conscious or unconscious, during a candidate interview include, without limitation, one or more of: color, gender, age, disability, religion, ethnicity, sexual orientation, appearance, clothes, pregnancy, parental status, marital status, caste, class, address, phone number, accent, salary, college, location, residential address, employment timeline, and the like.

In a computer-implemented method for identifying altered digital video content, a digital video content item is accessed. A visually identifiable region is identified within the digital video content item. A mask is applied to the visually identifiable region of the digital video content item, wherein the mask blocks the visually identifiable region of the digital video content item. The digital video content item with the mask is compared to other digital video content items, wherein the comparing disregards the visually identifiable region according to the mask. Provided the digital video content is identified as similar to at least one other digital video content item, the visually identifiable region of the digital content video item is compared to a visually identifiable region of the at least one other digital video content item. Provided the visually identifiable region of the digital content video item does not match the visually identifiable region of the at least one other digital video content item, it is determined that the digital video content item is altered.

The present technology relates to an encoding device, an encoding method, a reproduction device, a reproduction method, and a program enabling each reproduction equipment to reproduce an appropriate content in a simplified manner. A content data decoding unit decodes encoded metadata and outputs zoom area information, which is included in metadata acquired as a result thereof, designating an area to be zoomed. A zoom area selecting unit selects one or a plurality of pieces of zoom area information from among the zoom area information. A video segmenting unit segments a zoom area represented by the selected zoom area information in a video based on video data and outputs zoom video data acquired as a result thereof. An audio converting unit performs an audio converting process according to the selected zoom area information for audio data and outputs zoom audio data acquired as a result thereof. The present technology can be applied to a reproduction device.

In a computer-implemented method for identifying altered digital video content, a digital video content item is accessed. A visually identifiable region is identified within the digital video content item. A mask is applied to the visually identifiable region of the digital video content item, wherein the mask blocks the visually identifiable region of the digital video content item. The digital video content item with the mask is compared to other digital video content items, wherein the comparing disregards the visually identifiable region according to the mask. Provided the digital video content is identified as similar to at least one other digital video content item, the visually identifiable region of the digital content video item is compared to a visually identifiable region of the at least one other digital video content item. Provided the visually identifiable region of the digital content video item does not match the visually identifiable region of the at least one other digital video content item, it is determined that the digital video content item is altered.

Methods and devices for combining a mask with a selectively progressing video stream may include receiving a selection of at least one mask with a mask zone that obscures at least a portion of the video stream. The methods and devices may include receiving a selection to emplace the at least one mask at a first location within the video stream. The methods and devices may include receiving a selection to enable a tracking icon to move the at least one mask to a second location within the video stream while the video stream progresses. The methods and devices may include generating a combined output of the video stream and the selective emplacement and movement of the at least one mask during the video stream progression.

A method of filtering images of live stream content may include defining a prohibited frame content template; analyzing live stream content at a frame level to determine content within each frame of the live stream content; and comparing a frame of the live stream content against the prohibited frame content template to detect prohibited content in the frame that matches prohibited frame content as defined by the prohibited frame content template.

Methods and systems for image alteration. A video signal having multiple images is accessed, and images are altered to blur the video signal based on a subscriber alteration request. The alteration request is selectable among a partial blur, a full blur, and a restore image. The request includes instructions to selectably blur a partial portion of an image by stretching a first portion, without stretching a second portion. The alteration includes accessing an alternation setting selected from a cycle of alteration settings, a group of preprogrammed alteration settings and combinations thereof. The blurred video signal is provide for presentation by subscriber equipment. The video signal is restored in response to a restorative event detected within the blurred video signal. The detecting of the restorative event includes determining a location of a scene change in the blurred video signal.

In one embodiment, a method includes identifying, from a set of coordinate points that correspond to a plurality of surface points of a person in an environment, a coordinate point that corresponds to a facial feature of the person; generating a facial structure for a face of the person, wherein the facial structure: covers a plurality of facial features of the person; and substantially matches a pre-determined facial structure; generating a body skeletal structure for the person, wherein the body skeletal structure substantially matches a predetermined body skeletal structure and substantially aligns with the generated facial structure in at least one dimension of a two-dimensional coordinate plane; and associating the generated body skeletal structure and facial structure with the person in the environment.

The invention relates to a method of processing video data, a device (102) and a computer program product for implementing said method, and a data construct including video data processed by said method. The method processes unprocessed video data into processed video data, said unprocessed video data being provided by picking up (112) sequential images of a situation or scene (100), and includes the steps of: applying a motion and gesture recognition technology (114) in real time to said situation or scene; identifying undesirable image contents contained in said unprocessed video data, based on a result of said motion and gesture recognition, said undesirable image contents preferably including inappropriate body expression (128-132) such as obscene gestures or indecent exposures, and providing content information relating to any identified undesirable image contents; and using said content information to produce said processed video data.