An idea used herein is to use the same function for the dependency of the context and the dependency of the symbolization parameter on previously coded/decoded transform coefficients. Using the same function—with varying function parameter—may even be used with respect to different transform block sizes and/or frequency portions of the transform blocks in case of the transform coefficients being spatially arranged in transform blocks. A further variant of this idea is to use the same function for the dependency of a symbolization parameter on previously coded/decoded transform coefficients for different sizes of the current transform coefficient's transform block, different information component types of the current transform coefficient's transform block and/or different frequency portions the current transform coefficient is located within the transform block.

Aspects of the disclosure provide methods and apparatuses for neural network model compression/decompression. In some examples, an apparatus for neural network model decompression includes receiving circuitry and processing circuitry. The processing circuitry decodes, from a bitstream corresponding to a representation of a neural network, at least a syntax element to be applied to multiple blocks in the neural network. Then, the processing circuitry reconstructs, from the bitstream, weight coefficients in the blocks based on the syntax element.

Methods for converting an n-bit number into an m-bit number for situations where n>m and also for situations where n<m, where n and m are integers. The methods use truncation or bit replication followed by the calculation of an adjustment value which is applied to the replicated number.

A data processing system is provided including a processing element and a storage. The storage stores code portions that, when executed by the processing element, cause the data processing system to obtain a plurality of variable length codes. Each variable length code has a first portion of a variable length and a second portion. The variable length codes are separated into first portions of the variable length codes and second portions of the variable length codes. The data processing system forms a processed stream in chunks using a set of control rules so that, for each chunk of the processed stream containing data from the first portions of the variable length codes, the data from the first portions forms a sub-stream within the chunk of the processed stream that has a size that is determined in accordance with the control rules.

A method for compressing activation data of a neural network to be written to a storage is provided. The activation data is formed into a plurality of groups and a state indicator indicates whether there are any data elements within each group that have a non-zero value. A second state indicator indicates, for groups having a non-zero value, whether sub-groups within the group contain a data element having a non-zero value. A sub-group state indicator indicates, for each sub-group having a non-zero value, which data elements within that sub-group have a non-zero value. Non-zero values of data elements in the activation data are encoded and a compressed data set is formed comprising the first state indicators, any second state indicators, any sub-group state indicators and the encoded non-zero values.

Methods for converting an n-bit number into an m-bit number for situations where n>m and also for situations where n<m, where n and m are integers. The methods use truncation or bit replication followed by the calculation of an adjustment value which is applied to the replicated number.

A method for decoding a picture performed by a decoding apparatus according to the present disclosure includes receiving a bitstream including residual information, deriving a quantized transform coefficient for a current block based on the residual information included in the bitstream, deriving a transform coefficient from the quantized transform coefficient based on a dequantization process, deriving a residual sample for the current block by applying an inverse transform to the derived transform coefficient, and generating a reconstructed picture based on the residual sample for the current block.

Disclosed herein are system, method, and computer program product embodiments for providing a memory optimization system for inverted indexes. An embodiment operates by determining a value identifier corresponding to a value to be searched for in a database based on a query. From a lookup table, a prefix of an offset corresponding to a location in a compressed posting list that identifies row locations where the value is found in the database is retrieved. From a directory page, a suffix of the offset corresponding to the location is retrieved. The offset is generated based on the prefix and the suffix. From the posting list, row identifiers corresponding to the generated offset are retrieved. The retrieved row identifiers are returned responsive to the query.

Example techniques are described for coding video data by obtaining a block of video data, obtaining an adaptive parameter set, determining a set of adaptive loop filter parameters for a plurality of filters for the block of video data based on the adaptive parameter set, wherein a plurality of adaptive loop parameters of the set of adaptive loop filter parameters are signaled using the same signaling parameter for each of the plurality of filters of the adaptive parameter set, and coding the block of video data using the set of adaptive loop filter parameters. The example techniques can be performed as part of an encoding or decoding process and/or by an encoder or a decoder.

A method of decoding a transform unit (e.g., 400) of encoded video data using Golomb-Rice decoding is disclosed. Significant residual coefficients for a sub-set of the transform unit are determined A predetermined Rice parameter for Golomb-Rice decoding of the subset of the transform unit is selected. The predetermined Rice parameter being offset from a zero setting when the determined number of significant residual coefficients is higher than a predetermined threshold. The subset of the transform unit is decoded using the predetermined Rice parameter as an initial parameter for the Golomb-Rice decoding.