Text-guided motion editing enables high-level semantic control and iterative modifications beyond traditional keyframe animation. Existing methods rely on limited pre-collected training triplets (original motion, edited motion, and instruction), which severely hinders their versatility in diverse editing scenarios. We introduce MotionCutMix, an online data augmentation technique that dynamically generates training triplets by blending body part motions based on input text. While MotionCutMix effectively expands the training distribution, the compositional nature introduces increased randomness and potential body part incoordination. To model such a rich distribution, we present Mo-tionReFit, an auto-regressive diffusion model with a motion coordinator. The auto-regressive architecture facilitates learning by decomposing long sequences, while the motion coordinator mitigates the artifacts of motion composition. Our method handles both spatial and temporal motion edits directly from high-level human instructions, without relying on additional specifications or Large Language Models (LLMs). Through extensive experiments, we show that MotionReFit achieves state-of-the-art performance in text-guided motion editing. Ablation studies further verify that MotionCutMix significantly improves the model’s generalizability while maintaining training convergence.

Light field (LF) image data potentially involves a lot of sensitive information about users. Its transmission channel breaches could compromise user privacy and implicate illegal activities. Therefore, the confidentiality and integrity of LF image data transmission are crucial. However, most of the existing watermarking techniques may not adequately consider the confidentiality and integrity authentication of LF image data transmission. To address this problem, this article employs Generic Radial Harmonic Fourier Moments in Radon space (GRHFMR) to propose a robust zero-watermarking scheme of the LF image, called LFIZW-GRHFMR. Specifically, the radial harmonic Fourier coefficients of sub-aperture images (SAIs) of LF image are calculated by taking into full consideration the characteristics of the GRHFMR variable weight basis function, and then the corresponding watermarks are combined to generate zero-watermarks with stronger robustness. For yielding more watermarking information and enhancing security authentication, the 32 key SAIs of LF image at a sampling rate of 0.5 are selected to act with GRHFMR. Meanwhile, the key SAIs are converted as video streaming with high efficiency video coding for transmission to improve the data transmission efficiency. Extensive experimental results demonstrate that the proposed LFIZW-GRHFMR outperforms the latest watermarking methods.

Despite the various privacy protection methods that are available through medical services platforms, it is still challenging for patients to achieve a desirable level of privacy protection during image sharing. Therefore, this paper proposes a privacy protection mechanism, called PPM-SEM, for the secure sharing of electronic patient records (EPRs) and medical images in telemedicine; it includes two stages: privacy preparation and privacy protection and reconstruction. In the first stage, a dual watermark (i.e., an image watermark) is generated by combining the patient's EPRs with an image, which can be utilized to ensure the security of patient identity data (i.e., a text watermark).Inthe second stage, a modal transformation network is constructed by training the dual watermark together as an additional channel. This network is called watermark-CycleGAN (W-CycleGAN), which can address the privacy and security issues concerning medical images and provide a double protection mechanism for EPRs. Experimental results demonstrate that only the recovery network with the correct key can restore high-quality medical images. In addition, the patient's EPRs can be fully extracted; i.e., 100% accuracy can be maintained. It is noted that the nonpaired recovery network can also recover visually meaningful medical images, thereby realizing privacy protection for patients in telemedicine scenarios.