Presents a review of 200 references in content-based image retrieval. The paper starts with discussing the working conditions of content-based retrieval: patterns of use, types of pictures, the role of semantics, and the sensory gap. Subsequent sections discuss computational steps for image retrieval systems. Step one of the review is image processing for retrieval sorted by color, texture, and local geometry. Features for retrieval are discussed next, sorted by: accumulative and global features, salient points, object and shape features, signs, and structural combinations thereof. Similarity of pictures and objects in pictures is reviewed for each of the feature types, in close connection to the types and means of feedback the user of the systems is capable of giving by interaction. We briefly discuss aspects of system engineering: databases, system architecture, and evaluation. In the concluding section, we present our view on: the driving force of the field, the heritage from computer vision, the influence on computer vision, the role of similarity and of interaction, the need for databases, the problem of evaluation, and the role of the semantic gap.

/pdf/content-based-image-retrieval-at-the-end-of-the-early-years-q45iy9ejai.pdf

Content-based image retrieval at the end of the early years

An intelligent automated assistant system engages with the user in an integrated, conversational manner using natural language dialog, and invokes external services when appropriate to obtain information or perform various actions. The system can be implemented using any of a number of different platforms, such as the web, email, smartphone, and the like, or any combination thereof. In one embodiment, the system is based on sets of interrelated domains and tasks, and employs additional functionally powered by external services with which the system can interact.

Intelligent Automated Assistant

A virtual assistant uses context information to supplement natural language or gestural input from a user. Context helps to clarify the user's intent and to reduce the number of candidate interpretations of the user's input, and reduces the need for the user to provide excessive clarification input. Context can include any available information that is usable by the assistant to supplement explicit user input to constrain an information-processing problem and/or to personalize results. Context can be used to constrain solutions during various phases of processing, including, for example, speech recognition, natural language processing, task flow processing, and dialog generation.

Using context information to facilitate processing of commands in a virtual assistant

A method for detecting against unauthorized transmission of digital works comprises the steps of maintaining a registry of information permitting identification of digital copyrighted works, monitoring a network for transmission of at least one packet-based digital signal, extracting at least one feature from the at least one digital signal, comparing the extracted at least one feature with registry information and applying business rules based on the comparison result.

Copyright detection and protection system and method

A system, method, and computer program product discover relationships among items and recommend items based on the discovered relationships. The recommendations provided by the present invention are based on user profiles that take into account actual preferences of users, without requiring users to complete questionnaires. An improved binomial log likelihood ratio analysis technique is applied, to reduce adverse effects of overstatement of coincidence and predominance of best sellers. The invention may be used, for example, to generate track lists for a personalized radio station.

Relationship discovery engine

A method and apparatus are provided for refining time alignments of closed captions. The method automatically aligns closed caption data with associated audio data such that the closed caption data can be more precisely indexed to a requested keyword by a search engine. Further, with such a structure, the closed captions can be made to appear and disappear on a display screen in direct relation to the associated spoken words and phrases. Accordingly, hearing impaired viewers can more easily understand the program that is being displayed.

Method for refining time alignments of closed captions

The disclosed method and apparatus controls the rate of playback of audio data corresponding to a stream of speech. Using speech recognition, the rate of speech of the audio data is determined. The determined rate of speech is compared to a target rate. Based on the comparison, the playback rate is adjusted, i.e. increased or decreased, to match the target rate.

Apparatus and method for controlling rate of playback of audio data

In this paper we address the problem of aligning very long (often more than one hour) audio files to their corresponding textual transcripts in an effective manner. We present an efficient recursive technique to solve this problem that works well even on noisy speech signals. The key idea of this algorithm is to turn the forced alignment problem into a recursive speech recognition problem with a gradually restricting dictionary and language model. The algorithm is tolerant to acoustic noise and errors or gaps in the text transcript or audio tracks. We report experimental results on a 3 hour audio file containing TV and radio broadcasts. We will show accurate alignments on speech under a variety of real acoustic conditions such as speech over music and speech over telephone lines. We also report results when the same audio stream has been corrupted with white additive noise or compressed using a popular web encoding format such as RealAudio. This algorithm has been used in our internal multimedia indexing project. It has processed more than 200 hours of audio from varied sources, such as WGBH NOVA documentaries and NPR web audio files. The system aligns speech media content in about one to five times realtime, depending on the acoustic conditions of the audio signal.

A recursive algorithm for the forced alignment of very long audio segments.

Disclosed is a five-step process for producing closed captions for a television program, subtitles for a movie or other uses for time-aligned transcripts. An operator transcribes the audio track while listening to the recorded material. The system helps him/her to work efficiently and produce precisely aligned captions. The first step consists of identifying the portions of the input audio that contain spoken text. Only the spoken parts are further processed by the invention system. The other parts may be used to generate non-spoken captions. The second step controls the rate of speech depending on how fast the operator types. While the operator types, the third module records the time the words were typed in. This provides a rough time alignment for the transcribed text. Then the fourth module realigns precisely the transcribed text on the audio track. A final module segments the transcribed text into captions, based on acoustic clues and natural language constraints. Further, the speech rate-control component of the system may be used in other systems where transcripts are required to be generated from spoken audio.

Efficient method for producing off-line closed captions

An electronic document searching system or word searching system which when given an input, expands the input as a function of acoustic similarity and/or word sequence occurrence frequency. Results of the system are alternative input words or phrases. The alternative input words or phrases are output from the system for further processing.

Jean-Manuel Van Thong

Papers

Method for refining time alignments of closed captions

Apparatus and method for controlling rate of playback of audio data

A recursive algorithm for the forced alignment of very long audio segments.

Efficient method for producing off-line closed captions

Method to expand inputs for word or document searching