paper-with-me

홈 › Papers

Application of Graph Convolutions in a Lightweight Model for Skeletal Human Motion Forecasting

2021-10-10 · Luca Hermes, Barbara Hammer, Malte Schilling

Prediction of movements is essential for successful cooperation with intelligent systems. We propose a model that integrates organized spatial information as given through the moving body's skeletal structure. This inherent structure is exploited in our model through application of Graph Convolutions and we demonstrate how this allows leveraging the structured spatial information into competitive predictions that are based on a lightweight model that requires a comparatively small number of parameters.

📄 PDF Abstract BibTeX arXiv:2110.04810

Code (1)

LucaHermes/lightweight-motion-forecasting 공식 구현 tf

Tasks

Motion Forecasting

Similar Papers 제목 키워드 기반

TrouSPI-Net: Spatio-temporal attention on parallel atrous convolutions and U-GRUs for skeletal pedestrian crossing prediction

2021-09-02 · Joseph Gesnouin, Steve Pechberti, Bogdan Stanciulescu, Fabien Moutarde

Understanding the behaviors and intentions of pedestrians is still one of the main challenges for vehicle autonomy, as accurate predictions of their intentions can guarantee their safety and driving comfort of vehicles. …

Lightweight 3D Human Pose Estimation Network Training Using Teacher-Student Learning

2020-01-15 · Dong-Hyun Hwang, Suntae Kim, Nicolas Monet, Hideki Koike 외

We present MoVNect, a lightweight deep neural network to capture 3D human pose using a single RGB camera. To improve the overall performance of the model, we apply the teacher-student learning method based knowledge dist…

3D Human Pose Estimation3D Pose EstimationKnowledge DistillationPose Estimation

Spatio-Temporal Pyramid Graph Convolutions for Human Action Recognition and Postural Assessment

2019-12-07 · Behnoosh Parsa, Athma Narayanan, Behzad Dariush

Recognition of human actions and associated interactions with objects and the environment is an important problem in computer vision due to its potential applications in a variety of domains. The most versatile methods c…

Action RecognitionTemporal Action Localization

Evolving Skeletons: Motion Dynamics in Action Recognition

2025-01-05 · Jushang Qiu, Lei Wang

Skeleton-based action recognition has gained significant attention for its ability to efficiently represent spatiotemporal information in a lightweight format. Most existing approaches use graph-based models to process s…

Action RecognitionHypergraph representationsSkeleton Based Action Recognition

Robustness study of the bio-inspired musculoskeletal arm robot based on the data-driven iterative learning algorithm

2025-11-08 · Jianbo Yuan, Jing Dai, Yerui Fan, Yaxiong Wu 외 arxiv

The human arm exhibits remarkable capabilities, including both explosive power and precision, which demonstrate dexterity, compliance, and robustness in unstructured environments. Developing robotic systems that emulate …