Abstract: Aspects of the disclosure include methods and apparatuses for video coding. One of the apparatuses includes processing circuitry that receives a bitstream of a current block in a current picture. The current block is coded with a directional nearest neighbor prediction (DNNP) mode. The processing circuitry selects a prediction value for a sample in the current block from a top-left value, a top value, or a left value based on one or more difference values between respective paired values of (i) the top-left value associated with a top-left reference sample that is a top-left neighbor of the current block, (ii) the top value associated with a top reference sample that is a top neighbor of the sample in the current block, and (iii) the left value associated with a left reference sample that is a left neighbor of the sample in the current block. The processing circuitry reconstructs the current block using the selected prediction value for the sample in the current block.

Abstract: A method and apparatus for encoding or decoding a video sequence includes applying a Cross-Component Linear Model (CCLM) to a video sequence, and applying an interpolation filter in the Cross-Component Linear Model (CCLM), wherein the interpolation filter is dependent upon a YUV format of the video sequence.

Abstract: A technique for encoding video for machine vision and human/machine hybrid vision, including receiving image data. The technique may also include detecting a plurality of bounding boxes associated with a plurality of objects of interest in a frame of the image data and detecting a frame-level bounding box for the frame based on coordinates of the plurality of bounding boxes. Then, the technique may include encoding the frame-level bounding box using a first bitrate.

Abstract: An unsupervised text to speech system utilizing a lexicon to map input text to the phoneme sequence, which is expanded to the frame-level forced alignment with a speaker-dependent duration model. An alignment mapping module that converts the forced alignment to the unsupervised alignment (UA). Afterword, a Conditional Disentangled Sequential Variational Auto-encoder (C-DSVAE), serving as the self-supervised TTS AM, takes the predicted UA and a target speaker embedding to generate the mel spectrogram, which is ultimately converted to waveform with a neural vocoder.

Abstract: A video bitstream comprising a current picture of a video is received. A first group of samples and a second group of samples in the current picture are determined. A first geometric transform is determined for the first group of samples in the current picture and a second geometric transform is determined for the second group of samples in the current picture. The first geometric transform is configured to adjust an orientation of the first group of samples in the current picture. The second geometric transform is different from the first geometric transform and configured to adjust an orientation of the second group of samples in the current picture. The picture is reconstructed, where the first group of samples is reconstructed based on the determined first geometric transform and the second group of samples is reconstructed based on the determined second geometric transform.

Abstract: A method of video encoding includes receiving a merge sharing region including a plurality of coding blocks, constructing a shared merge candidate list for the merge sharing region, and encoding a current inter coded coding block in the merge sharing region based on the shared merge candidate list. The method also includes determining whether to update a history-based motion vector prediction (HMVP) table with motion information of the current inter coded coding block based on whether the current inter coded coding block is inter coded with a merge/skip mode. The method further includes updating the HMVP table with the motion information of the current inter coded coding block when the HMVP table is determined to be updated with the motion information of the current inter coded coding block.

Abstract: Methods and systems are provided for decoding at least one video stream. A method includes receiving a first network abstraction layer (NAL) unit of a first slice of a coded picture and a second VCL NAL unit of a second slice of the coded picture, the first VCL NAL unit having a first VCL NAL unit type and the second VCL NAL unit having a second VCL NAL unit type that is different from the first VCL NAL unit type, and decoding the coded picture, the decoding including determining a picture type of the coded picture based on the first VCL NAL unit type of the first VCL NAL unit and the second VCL NAL unit type of the second VCL NAL unit, or based on an indicator, received by the at least one processor, indicating that the coded picture includes mixed VCL NAL unit types.

Abstract: A method of training a model for query generation, the method performed by at least one processor and including receiving a training instance query corresponding to a dialogue history. The method further including generating a first static view of the model based on a number of common words between the training instance query and the dialogue history. The method further including generating a second static view of the model based on one or more tokens not covered by the dialogue history, the one or more tokens corresponding to one or more query words. The method further including generating a dynamic view of the model based on a score operation that compares a candidate query generated from the model with a target query. The method further including training the model based at least on the first static view, the second static view, and the dynamic view.

Abstract: A method and apparatus for encoding a video stream using video point cloud coding, the decoding including obtaining an input point cloud; dividing the input point cloud into a plurality of chunks, including a first chunk including a first plurality of points and a second chunk including a second plurality of points; generating a first plurality of patches based on the first plurality of points; generating a second plurality of patches based on the second plurality of points; packing the first plurality of patches and the second plurality of patches into an image; and generating the video stream based on the image.

Abstract: A method is provided. The method includes generating, by a 5th generation media streaming (5GMS) application provider, an edge configuration resource including at least one edge enabler client (EEC) capability specification, transmitting, by the 5GMS application provider, a request for provisioning an edge application server (EAS) to operate as a 5GMS application server (AS), the request including the edge configuration resource, and selecting, by the 5GMS application provider, the EAS to operate as the 5GMS AS based on the EAS being capable of performing the at least one EEC capability specification included in the edge configuration resource.

Abstract: Systems and methods for decoding a coded video stream are provided. A method includes receiving a coded video stream that includes an access unit, including a picture; signaling a first flag that indicates whether the access unit includes either or neither one from among an intra random access point (IRAP) picture and a gradual decoding refresh (GDR) picture; signaling a second flag that indicates whether the picture is the IRAP picture; and decoding the picture, as a current picture, based on the signaling of the first flag and the second flag, wherein a value of the first flag and a value of the second flag are aligned.

Abstract: An apparatus for video decoding includes processing circuitry. The processing circuitry can be configured to receive data of a current block coded with an intra block copy (IBC) mode in a bitstream. A block vector of the current block can be determined based on a history-based block vector prediction (HBVP) table that includes one or more entries each corresponding to a previously decoded block. Each entry can include a block vector of the corresponding previously decoded block and a location of the corresponding previously decoded block. The current block can be reconstructed based on the determined block vector of the current block.

Abstract: A method and apparatus for neural network based cross component prediction with scaling factors during encoding or decoding of an image frame or a video sequence, which may include training a deep neural network (DNN) cross component prediction (CCP) model with at least one or more scaling factors, wherein the at least one or more scaling factors are learned by optimizing a rate-distortion loss based on an input video sequence comprising a luma component, and reconstructing a chroma component based on the luma component using the trained DNN CCP model with the at least one or more scaling factors for chroma prediction. The trained DNN CCP may be updated for chroma prediction of the input video sequence using the one or more scaling factors, and performing chroma prediction of the input video sequence using the updated DNN CCP model with the one or more scaling factors.

Abstract: Aspects of the disclosure provide methods and apparatuses for audio processing. In some examples, an apparatus for media processing includes processing circuitry. The processing circuitry receives first 3 degrees of freedom (3 DoF) information associated with a first media content for a scene in a media application. The first 3 DoF information includes a first revolution orientation for describing the first media content on a first sphere centered at a user of the media application. The processing circuitry determines that a rendering platform for rendering the first media content is a six degrees of freedom (6 DoF) platform, and calculates, first spatial location information of the first media content based on the first revolution orientation and first parameters of the first sphere. The first spatial location information is used in first 6 DoF information associated with the first media content for rendering the first media content on the 6 DoF platform.

Abstract: A method, computer program, and computer system for encoding or decoding video data, and indicating, with a syntax element, types of slices for all slices of a coded picture, the syntax element being coded using an unsigned integer.

Abstract: An apparatus for video decoding includes receiving and processing circuitry. The circuitry is configured to receive a bitstream including a syntax element associated with a parent coding unit (CU) in a picture indicating the parent CU is partitioned into a predefined set of child CUs without performing a recursive tree-structure-based partitioning, and process the child CUs according to the indication of the syntax element to reconstruct the picture. In an embodiment, at least two subdivisions need to be performed when the parent CU is partitioned using the recursive tree-structure-based partitioning in order to obtain the same set of child CUs. In an embodiment, at least one of the child CUs has a size larger than a minimum allowed CU size for partitioning the parent CU and includes no syntax element to indicate whether the at least one of the child CUs is to be further subdivided.

Abstract: An apparatus for video decoding includes processing circuitry. The circuitry can be configured to receive a current block that is affine coded and included in a current coding tree unit (CTU), and determine an inherited affine candidate based on regular motion information of two minimum blocks in a rightmost column of minimum blocks of a left neighboring CTU of the current CTU when the current block is adjacent to a left boundary of the current CTU.

Abstract: Systems and methods for improved delta angle signaling for blocks in video compression are provided. A method includes encoding a bitstream that includes a picture. The encoding includes obtaining a nominal angle of a current block of the picture for intra prediction; obtaining a nominal angle of at least one neighboring block of the current block for intra prediction; determining whether to signal all allowed delta angles of the nominal angle of the current block, or only a subset of the allowed delta angles of the nominal angle of the current block, based on a comparison between the nominal angle of the current block and the nominal angle of the at least one neighboring block; and signaling, within the bitstream, all the allowed delta angles or the subset of the allowed delta angles of the nominal angle of the current block based on the determining.

Abstract: In a method of video decoding at a video decoder, a coded video bitstream is received. The coded video bitstream includes a first high level syntax (HLS) element indicating whether a second HLS element is included in the coded video bitstream. The second HLS element indicates whether explicit multiple transform selection (MTS) for intra coding is enabled. Whether an implicit MTS is enabled for a current block is determined responsive to (i) the first HLS element indicating that the second HLS element is included in the coded video bitstream, (ii) the second HLS element indicating that the explicit MTS for intra coding is disabled, and (iii) a prediction mode of the current block is an intra prediction mode. Further, the current block is reconstructed based on whether the implicit MTS is enabled.

Abstract: According to an embodiment, a method of selecting a Rice parameter for encoding a video bitstream using at least one processor includes obtaining an absolute level corresponding to a current transform block; determining whether transform skip is enabled; generating a lookup variable based on the absolute level and the determination of whether the transform skip is enabled; obtaining the Rice parameter from a lookup table based on the lookup variable; and encoding a residual subblock based on the Rice parameter.