Text-based 3D human motion editing is a critical yet challenging task in computer vision and graphics. While training-free approaches have been explored, the recent release of the MotionFix dataset, which includes source-text-motion triplets, has opened new avenues for training, yielding promising results. However, existing methods struggle with precise control, often leading to misalignment between motion semantics and language instructions. In this paper, we introduce a related task — motion similarity prediction — and propose a multi-task training paradigm, where we train the model jointly on motion editing and motion similarity prediction to foster the learning of semantically meaningful representations. To complement this task, we design an advanced Diffusion-Transformer-based architecture that separately handles motion similarity prediction and motion editing. Extensive experiments demonstrate the state-of-the-art performance of our approach in both editing alignment and fidelity. Project URL: https://github.com/lzhyu/SimMotionEdit.

Abstract Can we make virtual characters in a scene interact with their surrounding objects through simple instructions? Is it possible to synthesize such motion plausibly with a diverse set of objects and instructions? Inspired by these questions, we present the first framework to synthesize the full‐body motion of virtual human characters performing specified actions with 3D objects placed within their reach. Our system takes textual instructions specifying the objects and the associated ‘intentions’ of the virtual characters as input and outputs diverse sequences of full‐body motions. This contrasts existing works, where full‐body action synthesis methods generally do not consider object interactions, and human‐object interaction methods focus mainly on synthesizing hand or finger movements for grasping objects. We accomplish our objective by designing an intent‐driven full‐body motion generator, which uses a pair of decoupled conditional variational auto‐regressors to learn the motion of the body parts in an autoregressive manner. We also optimize the 6‐DoF pose of the objects such that they plausibly fit within the hands of the synthesized characters. We compare our proposed method with the existing methods of motion synthesis and establish a new and stronger state‐of‐the‐art for the task of intent‐driven motion synthesis.

The supply of electricity via power plants is critical to the operation of many critical infrastructure systems in modern society. Natural hazards can disrupt the power supply, cause power outages that can halt economic growth, and impede emergency response until power is restored. The proposed work aims to predict the landslides likelihood in these critical infrastructure locations in the Northeastern USA using integrated databases of explanatory variables and machine learning algorithms. First, data related to landslides are obtained and merged, including topographic, soil moisture, and precipitation-related data. Five regression algorithms, namely: Random Forest, Extreme Gradient Boosting (XGBoost), K-Nearest Neighbor regression (KNN), Linear Support Vector Regressor (SVR), and Linear regression, are utilized to predict the landslide probability and evaluated on the dataset. The accuracy of the models is assessed by using statistical metrics such as mean absolute error (MAE), mean squared error (MSE), and root mean squared error (RMSE). The study results show that Random Forest outperformed other models with the mutual information feature selection method. It achieved an MSE of 0.0011 with mutual information-based feature selection and an MSE of 0.00157 without feature selection. KNN regressor outperformed the other models with an MSE of 0.00139 with correlation-based information selection. The proposed landslide identification model with Random Forest algorithm shows outstanding robustness and great potential in tackling the landslide likelihood prediction by employing ML algorithms.

"How can we animate 3D-characters from a movie script or move robots by simply telling them what we would like them to do?" "How unstructured and complex can we make a sentence and still generate plausible movements from it?" These are questions that need to be answered in the long-run, as the field is still in its infancy. Inspired by these problems, we present a new technique for generating compositional actions, which handles complex input sentences. Our output is a 3D pose sequence depicting the actions in the input sentence. We propose a hierarchical two-stream sequential model to explore a finer joint-level mapping between natural language sentences and 3D pose sequences corresponding to the given motion. We learn two manifold representations of the motion, one each for the upper body and the lower body movements. Our model can generate plausible pose sequences for short sentences describing single actions as well as long complex sentences describing multiple sequential and compositional actions. We evaluate our proposed model on the publicly available KIT Motion-Language Dataset containing 3D pose data with human-annotated sentences. Experimental results show that our model advances the state-of-the-art on text-based motion synthesis in objective evaluations by a margin of 50%. Qualitative evaluations based on a user study indicate that our synthesized motions are perceived to be the closest to the ground-truth motion captures for both short and compositional sentences.