Talking Head reenactment aims to enable a face in a source image to animate motions in a driving frame. Existing warping-based methods generally utilize keypoints or landmarks as motion representations. However, the keypoints and landmarks inevitably contain conflicting facial structure that mislead cross-identity reenactment. In this paper, we propose a talking head generation method that aims to mitigate the structural differences for identity-preserving by predicting structure-adapted keypoints. The driving keypoints are adjusted by a proposed adaptive structure normalization module that aligns the statistics of the driving structural features with those of the source. Moreover, to provide paired samples for the cross-identity reenactment, we propose a well-designed cycle training pipeline by two steps, source to driving and reversed driving to another source from two videos. Extensive experiments demonstrate that our approach achieves an improvement of approximately 5% over state-of-the-art methods in identity preservation metric in cross-identity talking head reenactment.

Global Storm Resolving Models (GSRMs) is crucial for understanding extreme weather events under the climate change background. In this study, we optimize Global-Regional Integrated Forecast System (GRIST), which is a unified weather-climate modeling system designed for research and operation, for the next-generation Sunway supercomputer, incorporating AI-enhanced physics suite, OpenMP-based parallelization, and mixed-precision optimizations to enhance both efficiency and performance portability, as well as the unified modeling capability. Our experiments successfully capture significant events during the "23.7" extreme rainfall over northern China influenced by super Typhoon Doksuri, at 1km resolution. Notably, our work scales to 34 million cores, enabling simulation speeds at 491 SDPD (3km) and 181 SDPD (1km).

The dense motion semantics in talking-head videos can be encoded as sparse keypoints for low-bitrate semantic source coding. Previous methods extracted keypoints that describe fixed part semantics from faces, typically at the eyes, nose, and mouth. However, these fixed keypoints cannot be adaptively adjusted according to varied videos, limiting the efficiency of source coding. In this paper, we propose adaptive keypoints that perceptively express facial movements for flexible talking-head semantic source coding. The superiority of the adaptive keypoints is theoretically substantiated through likelihood functions. To achieve adaptive keypoint extraction, we designed a detector with a transformer architecture and regression layers, allowing keypoints sampled from the global context to not be confined to fixed areas of the face, breaking the conventional understanding of keypoints. Additionally, we can adjust the bitrate according to the number of keypoints, achieving flexible source coding. Extensive experiments demonstrate that our semantic source coding approach achieves better rate-distortion performance than existing state-of-the-art methods.

The continuously advancing image generation technology has been utilized for high-quality video reconstruction using low-bitrate feature representation. The motion semantic representations provided by existing models exhibit significant redundancy, indicating that their potential as video compression tools is still to be fully explored. In this work, we propose a motion semantic enhancement model called MSEM for ultra-low-bitrate talking-head video compression, aiming at improving semantic extraction effectiveness and compactness. Specifically, we enhance semantic extraction accuracy by introducing a deformable feature estimator with flexible receptive field shapes. Based on the straight-through gradient estimation, we construct a semantic encoding space that contains more compact semantic representations with low redundancy. Extensive experiments clearly demonstrate that i) compared to mainstream semantic compression models, our method has stronger semantic feature extraction capabilities benefiting from a more reasonable semantic feature impact range, and ii) our method provides an average bitrate reduction for the same visual quality of more than $50 \%$ compared to VVC.

The joint velocity jump for redundant robots in the presence of locked-joint failures is discussed in this paper. First, the analytical formula of the optimal joint velocity with minimum jump is derived, and its specific expressions for both all joint failure and certain single joint failure are presented. Then, the jump difference between the minimum jump solution and the least-norm velocity solution is mathematically analyzed, and the influence factors on this difference are also discussed. Based on this formula, a new fault tolerant algorithm with the minimum jump is proposed. Finally simulation examples are implemented with a planar 3R robot and a 4R spatial robot, and an experimental study is also done. Study results indicate that the new algorithm proposed in this paper is well suited for real time implementation, and can further reduce the joint velocity jump thereby improving the motion stability of redundant robots in fault tolerant operations. Also, the fewer the possible failed joints are, the more obvious the effect of this new algorithm is.