Zobrazeno 1 - 10
of 6 587
pro vyhledávání: '"Tang, Tao"'
In this work, we present a hybrid numerical method for solving evolution partial differential equations (PDEs) by merging the time finite element method with deep neural networks. In contrast to the conventional deep learning-based formulation where
Externí odkaz:
http://arxiv.org/abs/2409.02810
Autor:
Huang, Zhijian, Tang, Tao, Chen, Shaoxiang, Lin, Sihao, Jie, Zequn, Ma, Lin, Wang, Guangrun, Liang, Xiaodan
Data-driven approaches for autonomous driving (AD) have been widely adopted in the past decade but are confronted with dataset bias and uninterpretability. Inspired by the knowledge-driven nature of human driving, recent approaches explore the potent
Externí odkaz:
http://arxiv.org/abs/2408.13890
Infrared small target sequences exhibit strong similarities between frames and contain rich contextual information, which motivates us to achieve sequential infrared small target segmentation (IRSTS) with minimal data. Inspired by the success of Segm
Externí odkaz:
http://arxiv.org/abs/2408.04823
We study how the posterior contraction rate under a Gaussian process (GP) prior depends on the intrinsic dimension of the predictors and smoothness of the regression function. An open question is whether a generic GP prior that does not incorporate k
Externí odkaz:
http://arxiv.org/abs/2407.09286
Marking the Pace: A Blockchain-Enhanced Privacy-Traceable Strategy for Federated Recommender Systems
Federated recommender systems have been crucially enhanced through data sharing and continuous model updates, attributed to the pervasive connectivity and distributed computing capabilities of Internet of Things (IoT) devices. Given the sensitivity o
Externí odkaz:
http://arxiv.org/abs/2406.04702
Autor:
Zhou, Lijun, Tang, Tao, Hao, Pengkun, He, Zihang, Ho, Kalok, Gu, Shuo, Hou, Wenbo, Hao, Zhihui, Sun, Haiyang, Zhan, Kun, Jia, Peng, Lang, Xianpeng, Liang, Xiaodan
3D multiple object tracking (MOT) plays a crucial role in autonomous driving perception. Recent end-to-end query-based trackers simultaneously detect and track objects, which have shown promising potential for the 3D MOT task. However, existing metho
Externí odkaz:
http://arxiv.org/abs/2406.02147
Autor:
Ma, Enhui, Zhou, Lijun, Tang, Tao, Zhang, Zhan, Han, Dong, Jiang, Junpeng, Zhan, Kun, Jia, Peng, Lang, Xianpeng, Sun, Haiyang, Lin, Di, Yu, Kaicheng
Using generative models to synthesize new data has become a de-facto standard in autonomous driving to address the data scarcity issue. Though existing approaches are able to boost perception models, we discover that these approaches fail to improve
Externí odkaz:
http://arxiv.org/abs/2406.01349
Autor:
Luo, Renqiang, Tang, Tao, Xia, Feng, Liu, Jiaying, Xu, Chengpei, Zhang, Leo Yu, Xiang, Wei, Zhang, Chengqi
Recent advancements in machine learning and deep learning have brought algorithmic fairness into sharp focus, illuminating concerns over discriminatory decision making that negatively impacts certain individuals or groups. These concerns have manifes
Externí odkaz:
http://arxiv.org/abs/2405.09543
Self-attention mechanism is the key of the Transformer but often criticized for its computation demands. Previous token pruning works motivate their methods from the view of computation redundancy but still need to load the full network and require s
Externí odkaz:
http://arxiv.org/abs/2404.05657
Autor:
Tang, Tao, Wang, Guangrun, Lao, Yixing, Chen, Peng, Liu, Jie, Lin, Liang, Yu, Kaicheng, Liang, Xiaodan
Neural implicit fields have been a de facto standard in novel view synthesis. Recently, there exist some methods exploring fusing multiple modalities within a single field, aiming to share implicit features from different modalities to enhance recons
Externí odkaz:
http://arxiv.org/abs/2402.17483