Zobrazeno 1 - 10
of 526
pro vyhledávání: '"Li Jiahe"'
Time Series Classification (TSC) encompasses two settings: classifying entire sequences or classifying segmented subsequences. The raw time series for segmented TSC usually contain Multiple classes with Varying Duration of each class (MVD). Therefore
Externí odkaz:
http://arxiv.org/abs/2408.00041
3D Gaussian Splatting (3DGS) creates a radiance field consisting of 3D Gaussians to represent a scene. With sparse training views, 3DGS easily suffers from overfitting, negatively impacting rendering. This paper introduces a new co-regularization per
Externí odkaz:
http://arxiv.org/abs/2405.12110
Radiance fields have demonstrated impressive performance in synthesizing lifelike 3D talking heads. However, due to the difficulty in fitting steep appearance changes, the prevailing paradigm that presents facial motions by directly modifying point a
Externí odkaz:
http://arxiv.org/abs/2404.15264
With advancements in domain generalized stereo matching networks, models pre-trained on synthetic data demonstrate strong robustness to unseen domains. However, few studies have investigated the robustness after fine-tuning them in real-world scenari
Externí odkaz:
http://arxiv.org/abs/2403.07705
DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization
Radiance fields have demonstrated impressive performance in synthesizing novel views from sparse input views, yet prevailing methods suffer from high training costs and slow inference speed. This paper introduces DNGaussian, a depth-regularized frame
Externí odkaz:
http://arxiv.org/abs/2403.06912
Learning 3D shape representation with dense correspondence for deformable objects is a fundamental problem in computer vision. Existing approaches often need additional annotations of specific semantic domain, e.g., skeleton poses for human bodies or
Externí odkaz:
http://arxiv.org/abs/2308.12590
This paper presents ER-NeRF, a novel conditional Neural Radiance Fields (NeRF) based architecture for talking portrait synthesis that can concurrently achieve fast convergence, real-time rendering, and state-of-the-art performance with small model si
Externí odkaz:
http://arxiv.org/abs/2307.09323
Network embedding, a graph representation learning method illustrating network topology by mapping nodes into lower-dimension vectors, is challenging to accommodate the ever-changing dynamic graphs in practice. Existing research is mainly based on no
Externí odkaz:
http://arxiv.org/abs/2306.08967
Event camera shows great potential in 3D hand pose estimation, especially addressing the challenges of fast motion and high dynamic range in a low-power way. However, due to the asynchronous differential imaging mechanism, it is challenging to design
Externí odkaz:
http://arxiv.org/abs/2303.02862
Autor:
Li, Ming, Xu, Xiangyu, Fan, Hehe, Zhou, Pan, Liu, Jun, Liu, Jia-Wei, Li, Jiahe, Keppo, Jussi, Shou, Mike Zheng, Yan, Shuicheng
Existing methods of privacy-preserving action recognition (PPAR) mainly focus on frame-level (spatial) privacy removal through 2D CNNs. Unfortunately, they have two major drawbacks. First, they may compromise temporal dynamics in input videos, which
Externí odkaz:
http://arxiv.org/abs/2301.03046