Výsledky vyhledávání - "ZHANG, RUIXIN"

Report

Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perception

Autor: Chen, Haoming, Zhang, Zhizhong, Qu, Yanyun, Zhang, Ruixin, Tan, Xin, Xie, Yuan

An effective pre-training framework with universal 3D representations is extremely desired in perceiving large-scale dynamic scenes. However, establishing such an ideal framework that is both task-generic and label-efficient poses a challenge in unif

Externí odkaz: http://arxiv.org/abs/2405.07201

Zobrazit plný text záznamu

Report

SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation

Autor: Chen, Sichen, Zhang, Yingyi, Huang, Siming, Yi, Ran, Fan, Ke, Zhang, Ruixin, Chen, Peixian, Wang, Jun, Ding, Shouhong, Ma, Lizhuang

Recently, transformer-based methods have achieved state-of-the-art prediction quality on human pose estimation(HPE). Nonetheless, most of these top-performing transformer-based models are too computation-consuming and storage-demanding to deploy on e

Externí odkaz: http://arxiv.org/abs/2404.03518

Zobrazit plný text záznamu

Report

RPG-Palm: Realistic Pseudo-data Generation for Palmprint Recognition

Autor: Shen, Lei, Jin, Jianlong, Zhang, Ruixin, Li, Huaen, Zhao, Kai, Zhang, Yingyi, Zhang, Jingyun, Ding, Shouhong, Zhao, Yang, Jia, Wei

Palmprint recently shows great potential in recognition applications as it is a privacy-friendly and stable biometric. However, the lack of large-scale public palmprint datasets limits further research and development of palmprint recognition. In thi

Externí odkaz: http://arxiv.org/abs/2307.14016

Zobrazit plný text záznamu

Report

Coordinating Cross-modal Distillation for Molecular Property Prediction

Autor: Zhang, Hao, Zhang, Nan, Zhang, Ruixin, Shen, Lei, Zhang, Yingyi, Liu, Meng

In recent years, molecular graph representation learning (GRL) has drawn much more attention in molecular property prediction (MPP) problems. The existing graph methods have demonstrated that 3D geometric information is significant for better perform

Externí odkaz: http://arxiv.org/abs/2211.16712

Zobrazit plný text záznamu

Report

ECO-TR: Efficient Correspondences Finding Via Coarse-to-Fine Refinement

Autor: Tan, Dongli, Liu, Jiang-Jiang, Chen, Xingyu, Chen, Chao, Zhang, Ruixin, Shen, Yunhang, Ding, Shouhong, Ji, Rongrong

Modeling sparse and dense image matching within a unified functional correspondence model has recently attracted increasing research interest. However, existing efforts mainly focus on improving matching accuracy while ignoring its efficiency, which

Externí odkaz: http://arxiv.org/abs/2209.12213

Zobrazit plný text záznamu