Abstract: A method for encoding and decoding of motion vector difference for inter-predicting a video block is provided. The method includes receiving a coded video bitstream; extracting, from the coded video bitstream, a flag indicating whether an inter-predication mode is a JOINT_NEWMV mode for a current block in a current frame, the JOINT_NEWMV mode indicating that a first delta motion vector (MV) for a first reference frame from a reference list 0 and a second delta MV for a second reference frame from a reference list 1 are jointly signaled; in response to the flag indicating that the inter-predication mode is the JOINT_NEWMV mode, extracting a joint delta motion vector (MV) for the current block, and deriving the first delta MV and the second delta MV based on the joint delta MV; and decoding the current block based on the first delta MV and the second delta MV.

Abstract: Systems and methods for encoding and decoding using syntax design for multi-symbol arithmetic coding are provided. A method includes receiving a coded video bitstream including a plurality of syntax elements; determining a first maximum alphabet size for arithmetic coding by an arithmetic coding engine, the first maximum alphabet size determined based on a hardware constraint; determining a second maximum alphabet size that is less than the first maximum alphabet size; and decoding the plurality of syntax elements included in the coded video bitstream, based on the determined second maximum alphabet size, wherein each of the plurality of syntax elements is entropy coded with an alphabet size less than or equal to the determined second maximum alphabet size.

Abstract: A method, computer program, and computer system is provided for point cloud coding. The method includes receiving, from a bitstream, data corresponding to a point cloud; obtaining from the data a first prediction residual of a first component from among a plurality of components of an attribute associated with the point cloud; reconstructing the first prediction residual; determining a predicted second prediction residual based on the reconstructed first prediction residual and at least one model parameter; obtaining a second prediction residual of a second component from among the plurality of components based on the predicted second prediction residual; reconstructing the second prediction residual; and decoding the data corresponding to the point cloud based on the reconstructed first prediction residual and the reconstructed second prediction residual.

Abstract: Aspects of the disclosure provide a method and an apparatus including processing circuitry that decodes a current block in a current picture with a subblock-based temporal motion vector prediction (SbTMVP) mode. A first collocated block in a first collocated picture is determined based on a first displacement vector candidate of the current block corresponding to a first SbTMVP candidate. The processing circuitry determines first motion information of a current template of the current block based on one or more pieces of motion information of the first collocated block or a neighboring block of the first collocated block. The processing circuitry determines one of a first reference template and a first subblock reference template in a first reference picture based on the first motion information and determines a first template matching cost based on the current template and the one of the first reference template and the first subblock reference template.

Abstract: Processing circuitry receives a coded bitstream carrying at least a picture, determines that a current coding unit (CU) in the picture is coded in a subblock based inter prediction mode based on a first syntax element value in the coded bitstream, and determines that one or more first subblocks in the current CU that is coded in the subblock based inter prediction mode are coded by intra prediction. The processing circuitry reconstructs one or more second subblocks of the current CU by inter prediction based on the subblock based inter prediction mode, the one or more second subblocks do not overlap with the one or more first subblocks in the current CU. The processing circuitry reconstructs the one or more first subblocks of the current CU by the intra prediction while the current CU is coded in the subblock based inter prediction mode.

Abstract: Aspects of the disclosure provide methods and apparatuses for gaze matching. In some examples, processing circuitry determines a position of an object of interest for a first user, and receives first one or more images of the first user that is taken by a camera at a camera position different from the position of the object of interest. The processing circuitry detects a first vergence of eyes of the first user, calculates a mismatch of the first vergence for viewing the object of interest, and performs a gaze correction of the first one or more images based on the mismatch of the first vergence for viewing the object of interest.

Abstract: A feature value is determined based on at least one of (i) neighboring reconstructed chroma samples of a current chroma block and (ii) neighboring reconstructed luma samples of a luma block that is collocated with the current chroma block. Chroma samples of the current chroma block and luma samples of the luma block that is collocated with the current chroma block are grouped into a plurality of groups based on a threshold of the feature value. Each of the plurality of groups includes a respective chroma sample and a respective luma sample. A respective cross-component prediction mode is determined for each of the plurality of groups by comparing the respective chroma sample and the respective luma sample of each respective group to the determined feature value. The current chroma block is reconstructed based on the determined cross-component prediction modes of the plurality of groups.

Abstract: Aspects of the disclosure provide methods and apparatuses for video data processing. In some examples, an apparatus for video data processing includes processing circuitry. For example, the processing circuitry determines a first syntax element for coding control in a first scope of coded video data in a bitstream. The first syntax element is associated with a second coding tool that is alternative to a first coding tool for Rice parameter derivation in a residual coding. In response to the first syntax element being a first value indicative of disabling of the second coding tool in the first scope, the processing circuitry decodes the first scope of coded video data that includes one or more second scopes of coded video data without invoking the second coding tool.

Abstract: A method, performed by at least one processor, and an apparatus for cross-lingual text-to-SQL semantic parsing is provided. The method and computer program code performed by the at least one processor include: generating a contextual representation of a source language utterances, a target language utterances, and a database schema; generating a mixed representation of the target language utterances and the database schema based on the contextual representation of the source language utterances, the target language utterances, and the database schema; concatenating the mixed representation of the target language utterances and the database schema; encoding the concatenated mixed representation of the target language utterances and the database schema, based on k-layer transformers; and generating SQL queries token-by-token based on the encoded concatenated mixed representation of the target language utterances and the database schema.

Abstract: A method of three-dimensional (3D)-Tree coding for neural network model compression, is performed by at least one processor, and includes reshaping a four-dimensional (4D) parameter tensor of a neural network into a 3D parameter tensor of the neural network, the 3D parameter tensor comprising a convolution kernel size, an input feature size, and an output feature size, partitioning the 3D parameter tensor along a plane that is formed by the input feature size and the output feature size into 3D coding tree units (CTU3Ds), partitioning each of the CTU3Ds into a plurality of 3D coding units (CU3Ds) recursively until a predetermined depth, using a quad-tree, and constructing a 3D tree for each of the plurality of CU3Ds, wherein the 3D tree for each of the plurality of CU3Ds is a 3D-Unitree.

Abstract: A method of decoding an encoded video bitstream using at least one processor, including obtaining a first flag indicating whether a constant picture size is used in a coded video sequence including a current picture; based on the first flag indicating that the constant picture size is used, decoding the current picture without performing reference picture resampling; based on the first flag indicating that the constant picture size is not used, obtaining a second flag indicating whether a conformance window size is signaled; based on the second flag indicating that the conformance window size is signaled: obtaining the conformance window size, determining a resampling ratio between the current picture and a reference picture based on the conformance window size, and performing the reference picture resampling on the current picture using the resampling ratio.

Abstract: A method, device, and computer-readable medium for decoding an encoded video bitstream using at least one processor, including obtaining a first flag indicating that a conformance window is present in a current picture; based on the first flag indicating that the conformance window is present, obtaining a second flag indicating whether the conformance window is used for reference picture resampling; based on the second flag indicating that the conformance window is used for the reference picture resampling, determining a resampling ratio between the current picture and a reference picture based on a conformance window size of the conformance window; based on the second flag indicating that the conformance window is not used for the reference picture resampling, determining the resampling ratio based on a resampling picture size; and performing the reference picture resampling on the current picture using the resampling ratio.

Abstract: A method of dynamic point cloud partition packing is by at least one processor and includes obtaining one or more region of interest (ROI) patches from an ROI of a point cloud, and attempting to pack, into one among tiles of a tile map, one among the obtained one or more ROI patches, in a tile scan order. The method further includes identifying whether the one among the one or more ROI patches is packed successfully into the one among the tiles, and based on the one among the one or more ROI patches being determined to be not packed successfully into the one among the tiles, chunking the one among the one or more ROI patches into multiple ROI patches.

Abstract: This disclosure relates to a transform kernel sharing in video encoding and decoding. For example, a method is disclosed for such transform kernel sharing. The method may include identifying a plurality of transform kernels, wherein each of the plurality of transform kernels comprises a set of basis vectors from low to high frequencies; N high-frequency basis vectors of two or more of the plurality of transform kernels are shared, N being a positive integer; and low-frequency basis vectors of the two or more of the plurality of the transform kernels other than the N high-frequency basis vectors are individualized. The method may further include extracting a data block from a video bitstream; selecting a transform kernel from the plurality of transform kernels based on information associated with the data block; and applying the transform kernel to at least a portion of the data block to generate a transformed block.

Abstract: A method of signaling an intra prediction mode used to encode a current block in an encoded video bitstream includes generating a first most probable mode (MPM) list corresponding to a zero reference line of the current block, wherein the first MPM list includes a first plurality of intra prediction modes; generating a second MPM list corresponding to one or more non-zero reference lines of the current block, wherein the second MPM list includes a second plurality of intra prediction modes, the second plurality of intra prediction modes including a subset of the first plurality of intra prediction modes; signaling a reference line index indicating a reference line used to encode the current block; and signaling an intra mode index indicating the intra prediction mode from among the first MPM list and the second MPM list.

Abstract: A method of video encoding includes determining that a coded video bitstream conforms to one of a Main 10 still picture profile or a Main 4:4:4 10 still picture profile and generating profile information that indicates that each of the image slices is to be intra coded and indicates the one of the Main 10 still picture profile or the Main 4:4:4 10 still picture profile. The method further includes constraining only one picture to be included in the coded video bitstream according to the one of the Main 10 still picture profile or the Main 4:4:4 10 still picture profile. The method also includes performing intra prediction on each of the image slices, and encoding the picture based on the intra prediction and according to the one of the Main 10 still picture profile or the Main 4:4:4 10 still picture profile to form the coded video bitstream.

Abstract: Systems, methods, and devices for managing media storage and delivery, including obtaining information about a three-dimensional (3D) scene; obtaining, from the information, a parameter indicating that viewport adaptation is enabled; rendering the 3D scene, wherein the 3D scene includes at least one two-dimensional (2D) video to be reproduced within the 3D scene; obtaining a current viewport of a user; determining whether the at least one 2D video is inside of a range of the current viewport; and adjusting a bitrate of the at least one 2D video based on a result of the determining.

Abstract: Methods and apparatuses for performing cross-component intra prediction, including: receiving a coded bitstream; obtaining, from the coded bitstream, a syntax element indicating a downsampling filter used for a cross-component intra prediction mode; obtaining a plurality of reconstructed sample values of a first component which are associated with a pixel of a second component based on the downsampling filter; determining a pixel value of a downsampled pixel of the first component, based on the plurality of reconstructed sample values; determining a pixel value of the pixel of the second component based on the pixel value of the downsampled pixel of the first component; and reconstructing a picture based on the pixel value of the pixel of the second component.

Abstract: Systems, methods, and devices for managing media storage and delivery, including obtaining, by a media access function (MAF), a glTF file corresponding to a scene; determining that the glTF file has a CBOR format; converting the glTF file into a converted glTF file having a JSON format using a first CBOR parser function implemented by the MAF; and obtaining media content corresponding to the scene based on the converted glTF file.

Abstract: A method of video decoding includes acquiring a current and identifying, for a current block included in the current picture, a reference block included in a reference picture that is different from the current picture, where the current block is divided into a plurality of sub-blocks (CBSBs), and the reference block has a plurality of sub-blocks (RBSBs). The method includes, determining whether the reference picture for the RBSB is the current picture, and in response to determining that the reference picture for the RBSB is the current picture, determining a coding mode of the RBSB as an intra mode. The method further includes, in response to determining that the reference picture for the RBSB is not the current picture determining a motion vector predictor for the one of the CBSBs based on whether the coding mode of the corresponding RBSB is one of the intra mode and the inter mode.