Zobrazeno 1 - 10
of 232
pro vyhledávání: '"LIU, Xueyi"'
Maritime vessel maneuvers, characterized by their inherent complexity and indeterminacy, requires vessel trajectory prediction system capable of modeling the multi-modality nature of future motion states. Conventional stochastic trajectory prediction
Externí odkaz:
http://arxiv.org/abs/2410.09550
We explore the dexterous manipulation transfer problem by designing simulators. The task wishes to transfer human manipulations to dexterous robot hand simulations and is inherently difficult due to its intricate, highly-constrained, and discontinuou
Externí odkaz:
http://arxiv.org/abs/2404.07988
Autor:
Liu, Xueyi, Yi, Li
Publikováno v:
ICLR 2024
In this work, we tackle the challenging problem of denoising hand-object interactions (HOI). Given an erroneous interaction sequence, the objective is to refine the incorrect hand trajectory to remove interaction artifacts for a perceptually realisti
Externí odkaz:
http://arxiv.org/abs/2402.14810
Aspect-based sentiment classification is a crucial problem in fine-grained sentiment analysis, which aims to predict the sentiment polarity of the given aspect according to its context. Previous works have made remarkable progress in leveraging atten
Externí odkaz:
http://arxiv.org/abs/2308.11447
Publikováno v:
International Conference on Computer Vision (ICCV) 2023
We study the problem of few-shot physically-aware articulated mesh generation. By observing an articulated object dataset containing only a few examples, we wish to learn a model that can generate diverse meshes with high visual fidelity and physical
Externí odkaz:
http://arxiv.org/abs/2308.10898
Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance
Category-level articulated object pose estimation aims to estimate a hierarchy of articulation-aware object poses of an unseen articulated object from a known category. To reduce the heavy annotations needed for supervised learning methods, we presen
Externí odkaz:
http://arxiv.org/abs/2302.14268
Graph instance contrastive learning has been proved as an effective task for Graph Neural Network (GNN) pre-training. However, one key issue may seriously impede the representative power in existing works: Positive instances created by current method
Externí odkaz:
http://arxiv.org/abs/2206.11959
Publikováno v:
In Journal of Environmental Chemical Engineering December 2024 12(6)
Publikováno v:
In Food Packaging and Shelf Life December 2024 46
Training a generalizable 3D part segmentation network is quite challenging but of great importance in real-world applications. To tackle this problem, some works design task-specific solutions by translating human understanding of the task to machine
Externí odkaz:
http://arxiv.org/abs/2203.06558