Abstract: A multimodal video generation framework (MMVID) that benefits from text and images provided jointly or separately as input. Quantized representations of videos are utilized with a bidirectional transformer with multiple modalities as inputs to predict a discrete video representation. A new video token trained with self-learning and an improved mask-prediction algorithm for sampling video tokens is used to improve video quality and consistency. Text augmentation is utilized to improve the robustness of the textual representation and diversity of generated videos. The framework incorporates various visual modalities, such as segmentation masks, drawings, and partially occluded images. In addition, the MMVID extracts visual information as suggested by a textual prompt.

Abstract: An encoding apparatus, decoding apparatus, and coding methods are provided. A method of decoding including receiving, by a decoder, a bitstream from an encoder, scanning, using the decoder, the bitstream to identify a first flag corresponding to a string of index values in a block other than a last string and a second flag corresponding to the last string of index values from the block, determining, by the decoder, that a context model used to encode the first flag is the same as the context model used to encode the second flag, and generating, by the decoder, a video frame using the context model.

Abstract: Embodiments are provided for compressing a color index map in video coding applications including screen content images. An embodiment method includes obtaining, at a video codec device, an image block, and generating a color index map comprising a plurality of entries and representing the image block. Each one of the entries is assigned a color index indicating a respective color. The method further includes assigning, in a correct prediction map, a first bit-value for each one of the entries that is predictable by a neighboring entry in the color index map, and a second bit-value for each one of the entries that is unpredictable by any neighboring entry in the color index map. Further, an actual value from the color index map for the each one of the entries that is unpredictable by any neighboring entry is added in a sequence of non-predictable color indices.

Abstract: An encoding apparatus, decoding apparatus, and coding methods are provided.

Abstract: Embodiments are provided for compressing a color index map in video coding applications including screen content images. An embodiment method includes obtaining, at a video codec device, an image block, and generating a color index map comprising a plurality of entries and representing the image block. Each one of the entries is assigned a color index indicating a respective color. The method further includes assigning, in a correct prediction map, a first bit-value for each one of the entries that is predictable by a neighboring entry in the color index map, and a second bit-value for each one of the entries that is unpredictable by any neighboring entry in the color index map. Further, an actual value from the color index map for the each one of the entries that is unpredictable by any neighboring entry is added in a sequence of non-predictable color indices.