Peng Yin

TL;DR: A 540-billion parameter, densely activated, Transformer language model, which is called PaLM achieves breakthrough performance, outperforming the state-of-the-art on a suite of multi-step reasoning tasks, and outperforming average human performance on the recently released BIG-bench benchmark.

TL;DR: A new scheme to jointly optimize motion estimation and mode decision is proposed and results show that up to 90% complexity reduction while maintaining coding efficiency.

TL;DR: In this paper, a scalable video encoder includes an encoder (100) for encoding at least two views corresponding to multi-view video content by, encoding a particular view of the at least 2 views as a base layer, and encoding each of at least one other view of 2D views as an enhancement layer using a prediction from a lower layer corresponding to at least 1 of the particular view and 2D view.

TL;DR: In this article, the adaptive tree-based frame partitioning is used for encoding video data, where partitions are obtained from a combination of top-down tree partitioning and bottom-up tree joining.

TL;DR: The U NIFIED SKG framework is proposed, which unifies 21 SKG tasks into a text-to-text format, aiming to promote systematic SKG research, instead of being exclu-sive to a single task, domain, or dataset.