Zobrazeno 1 - 10
of 1 600
pro vyhledávání: '"Wang, WenJia"'
While motion generation has made substantial progress, its practical application remains constrained by dataset diversity and scale, limiting its ability to handle out-of-distribution scenarios. To address this, we propose a simple and effective base
Externí odkaz:
http://arxiv.org/abs/2412.04343
Autor:
Wang, Wenjia, Pan, Liang, Dou, Zhiyang, Liao, Zhouyingcheng, Lou, Yuke, Yang, Lei, Wang, Jingbo, Komura, Taku
Simulating long-term human-scene interaction is a challenging yet fascinating task. Previous works have not effectively addressed the generation of long-term human scene interactions with detailed narratives for physics-based animation. This paper in
Externí odkaz:
http://arxiv.org/abs/2411.19921
``Distribution shift'' is the main obstacle to the success of offline reinforcement learning. A learning policy may take actions beyond the behavior policy's knowledge, referred to as Out-of-Distribution (OOD) actions. The Q-values for these OOD acti
Externí odkaz:
http://arxiv.org/abs/2410.20312
Autor:
Mahara, Arpan, Khan, Md Rezaul Karim, Rishe, Naphtali D., Wang, Wenjia, Sadjadi, Seyed Masoud
Road Extraction is a sub-domain of Remote Sensing applications; it is a subject of extensive and ongoing research. The procedure of automatically extracting roads from satellite imagery encounters significant challenges due to the multi-scale and div
Externí odkaz:
http://arxiv.org/abs/2410.14836
Autor:
Du, Wenjie, Wang, Jun, Qian, Linglong, Yang, Yiyuan, Ibrahim, Zina, Liu, Fanxing, Wang, Zepu, Liu, Haoxin, Zhao, Zhiyuan, Zhou, Yingjie, Wang, Wenjia, Ding, Kaize, Liang, Yuxuan, Prakash, B. Aditya, Wen, Qingsong
Effective imputation is a crucial preprocessing step for time series analysis. Despite the development of numerous deep learning algorithms for time series imputation, the community lacks standardized and comprehensive benchmark platforms to effectiv
Externí odkaz:
http://arxiv.org/abs/2406.12747
In offline reinforcement learning (RL), it is necessary to manage out-of-distribution actions to prevent overestimation of value functions. Policy-regularized methods address this problem by constraining the target policy to stay close to the behavio
Externí odkaz:
http://arxiv.org/abs/2405.20555
This study introduces a methodology integrating Zero Trust Architecture (ZTA) principles and Transparent Shaping into an AWS-hosted Online File Manager (OFM) application, enhancing security without substantial code modifications. We evaluate our appr
Externí odkaz:
http://arxiv.org/abs/2405.01412
Autor:
Li, Simiao, Zhang, Yun, Li, Wei, Chen, Hanting, Wang, Wenjia, Jing, Bingyi, Lin, Shaohui, Hu, Jie
Knowledge distillation (KD) is a promising yet challenging model compression technique that transfers rich learning representations from a well-performing but cumbersome teacher model to a compact student model. Previous methods for image super-resol
Externí odkaz:
http://arxiv.org/abs/2404.02573
Autor:
Zhang, Qingwen, Wang, Wenjia
Calibration refers to the statistical estimation of unknown model parameters in computer experiments, such that computer experiments can match underlying physical systems. This work develops a new calibration method for imperfect computer models, Sob
Externí odkaz:
http://arxiv.org/abs/2404.00630
In implicit collaborative filtering, hard negative mining techniques are developed to accelerate and enhance the recommendation model learning. However, the inadvertent selection of false negatives remains a major concern in hard negative sampling, a
Externí odkaz:
http://arxiv.org/abs/2403.19276