Related papers: Motion-Scenario Decoupling for Rat-Aware Video Pos…

Deep learning models have achieved state-of-the- art performance in recognizing human activities, but often rely on utilizing background cues present in typical computer vision datasets that predominantly have a stationary camera. If these…

This paper proposes an integrated approach for the safe and efficient control of mobile robots in dynamic and uncertain environments. The approach consists of two key steps: one-shot multimodal motion prediction to anticipate motions of…

3D Human motion generation is pivotal across film, animation, gaming, and embodied intelligence. Traditional 3D motion synthesis relies on costly motion capture, while recent work shows that 2D videos provide rich, temporally coherent…

Existing automatic approaches for 3D virtual character motion synthesis supporting scene interactions do not generalise well to new objects outside training distributions, even when trained on extensive motion capture datasets with diverse…

Video portrait segmentation (VPS), aiming at segmenting prominent foreground portraits from video frames, has received much attention in recent years. However, simplicity of existing VPS datasets leads to a limitation on extensive research…

Cross-modal transfer learning is used to improve multi-modal classification models (e.g., for human activity recognition in human-robot collaboration). However, existing methods require paired sensor data at both training and inference,…

We propose a new architecture for the learning of predictive spatio-temporal motion models from data alone. Our approach, dubbed the Dropout Autoencoder LSTM, is capable of synthesizing natural looking motion sequences over long time…

Developing a safe and efficient collision avoidance policy for multiple robots is challenging in the decentralized scenarios where each robot generate its paths without observing other robots' states and intents. While other distributed…

Scene-graph generation involves creating a structural representation of the relationships between objects in a scene by predicting subject-object-relation triplets from input data. Existing methods show poor performance in detecting…

Representing diverse and plausible future trajectories is critical for motion forecasting in autonomous driving. However, efficiently capturing these trajectories in a compact set remains challenging. This study introduces a novel approach…

Dynamic mode decomposition (DMD) has recently become a popular tool for the non-intrusive analysis of dynamical systems. Exploiting Proper Orthogonal Decomposition (POD) as a dimensionality reduction technique, DMD is able to approximate a…

Dynamic Mode Decomposition (DMD) is a numerical method that seeks to fit timeseries data to a linear dynamical system. In doing so, DMD decomposes dynamic data into spatially coherent modes that evolve in time according to exponential…

Generative models for audio-conditioned dance motion synthesis map music features to dance movements. Models are trained to associate motion patterns to audio patterns, usually without an explicit knowledge of the human body. This approach…

Accurate estimation of 3D human motion from monocular video requires modeling both kinematics (body motion without physical forces) and dynamics (motion with physical forces). To demonstrate this, we present SimPoE, a Simulation-based…

Automated animal behavior analysis relies on long-term, interpretable individual trajectories; however, multi-animal tracking in space science experimental videos remains highly challenging due to weak appearance cues, low-quality imaging,…

Collision-free navigation in cluttered environments with static and dynamic obstacles is essential for many multi-robot tasks. Dynamic obstacles may also be interactive, i.e., their behavior varies based on the behavior of other entities.…

We present DynamicPose, a retraining-free 6D pose tracking framework that improves tracking robustness in fast-moving camera and object scenarios. Previous work is mainly applicable to static or quasi-static scenes, and its performance…

Cooperatively avoiding collision is a critical functionality for robots navigating in dense human crowds, failure of which could lead to either overaggressive or overcautious behavior. A necessary condition for cooperative collision…

Expressive representation of pose sequences is crucial for accurate motion modeling in human motion prediction (HMP). While recent deep learning-based methods have shown promise in learning motion representations, these methods tend to…

In the realm of object pose estimation, scenarios involving both dynamic objects and moving cameras are prevalent. However, the scarcity of corresponding real-world datasets significantly hinders the development and evaluation of robust…