A technique for non-binary context mixing in a compressor includes generating, by a plurality of context models, model predictions regarding a value of a next symbol to be encoded. A mixer generates a set of final predictions from the model predictions. An arithmetic encoder generates compressed data based on received input symbols and the set of final predictions. The received input symbols belong to an alphabet having a size greater than two and the mixer generates a feature matrix from the model predictions and trains a classifier that generates the set of final predictions.

The system includes a correlation extraction means for extracting at least one candidate for a correlation from a collected given data set, based on a relationship between units of data in the given data set; a correlation verification means for verifying whether or not the units of data in the given data set satisfy the correlation extracted by the correlation extraction means; and a data compression means for compressing the given data set with use of the correlation, based on the result of verification by the correlation verification means.

Techniques for handling data compression in which metadata that indicates which portions of data are compressed are which portions of data are not compressed are disclosed. Segments of a buffer referred to as block groups store compressed blocks of data along with uncompressed blocks of data and hash blocks. If a block group includes a block that is a hash of another block in the block group, then the other block is considered to be compressed. If the block group does not include a block that is a hash of another block in the block group, then the blocks in the block group are uncompressed. The hash function to generate the hash is selected to prevent collisions, which occur when the data being stored in the buffer is such that it is possible for a hash block and an uncompressed block to be the same.

Data may be efficiently analyzed and compressed as part of a data compression service. A data compression request may be received from a client indicating data to be compressed. An analysis of the data or metadata associated with the data may be performed. In at least some embodiments, this analysis may be a rules-based analysis. Some embodiments may employ one or more machine learning techniques to historical compression data to update the rules-based analysis. One or more compression techniques may be selected out of a plurality of compression techniques to be applied to the data. Data compression candidates may then be generated according to the selected compression techniques. In some embodiments, a compression service restriction may be enforced. One of the data compression candidates may be selected and sent in a response.

This disclosure provides methods, devices, and systems for data compression and decompression. The present implementations more specifically relate to entropy encoding and decoding techniques for keeping a state variable within upper and lower bounds using a noniterative process. The entropy encoding uses a fixed state threshold to determine a number of bits to remove and removes the bits from a current state prior to encoding a symbol with the current state. The entropy decoding decodes encoded data in a bitstream based on a current state to obtain the symbol and a new state and determines a number of bits to read from the bitstream and to add to the new state to update the current state.

There are disclosed various methods and apparatuses for encoding an image. In some embodiments the method comprises selecting a datastream among a first datastream and a second datastream, said first datastream and said second datastream comprising context-decision pairs, said context and decision relating to one or more images or a part of the one or more images. A context-decision pair is obtained from the selected bitstream and also an indication of the selected datastream is obtained. The datastream indication is used to select a set of registers containing parameter values relating to the selected datastream. Parameter values from the selected set of registers are provided to arithmetic encoding to form updated parameter values. Previously updated parameter values are stored to a set of registers indicated by a previous datastream indication, said previously updated parameter values relating to a datastream different than said selected datastream.

A method, system, and computer readable medium for improved decoding CABAC encoded media are described. A decoded binary string is output using two or more previously decoded elements at an end state for a decoding loop and on a first processing thread. A syntax of the decoded binary string is parsed on a second processing thread and a decoded symbol from the parsed syntax is generated on the second processing thread.

Methods and apparatuses are provided to approximate a cumulative distribution function (CDF) interval-wise with second order polynomials, while posing constraints on the polynomials within the intervals and/or on the boundary between the intervals. In this manner, a CDF approximation is obtained, which may be used in a variety of applications including entropy encoding and decoding of any source data. The constraints correspond to the characteristics of the CDF to be approximated.

The disclosure is directed at a method of data compression. The method includes creating a set of single composite data structures and then calculating a set of bit probabilities based on the set of single data structures. The bit probabilities are then used to create a set of intermediate buffers which are then sorted and traversed for data compression.

Methods, devices and systems enhance compression and decompression of data values when they comprise a plurality of semantically meaningful data fields. According to a first inventive concept of the present invention disclosure, compression is not applied to each data value as a whole, but instead to at least one of the semantically meaningful data fields of each data value, and in isolation from the other ones. A second inventive concept organizes the data fields that share the same semantic meaning together to accelerate compression and decompression as multiple compressors and decompressors can be used in parallel. A third inventive concept is a system where methods and devices are tailored to perform compression and decompression of the semantically meaningful data fields of floating-point numbers after first partitioning further at least one of said data fields into two or a plurality of sub-fields to increase the degree of value locality and improve compressibility of floating-point values.