Zobrazeno 1 - 10
of 131
pro vyhledávání: '"Wang, Zhepeng"'
Autor:
Wang, Zhepeng, Bao, Runxue, Wu, Yawen, Taylor, Jackson, Xiao, Cao, Zheng, Feng, Jiang, Weiwen, Gao, Shangqian, Zhang, Yanfu
Pretrained large language models (LLMs) have revolutionized natural language processing (NLP) tasks such as summarization, question answering, and translation. However, LLMs pose significant security risks due to their tendency to memorize training d
Externí odkaz:
http://arxiv.org/abs/2409.13853
Achieving accurate and reliable gaze predictions in complex and diverse environments remains challenging. Fortunately, it is straightforward to access diverse gaze datasets in real-world applications. We discover that training these datasets jointly
Externí odkaz:
http://arxiv.org/abs/2409.04766
This report presents our team's 'PCIE_EgoHandPose' solution for the EgoExo4D Hand Pose Challenge at CVPR2024. The main goal of the challenge is to accurately estimate hand poses, which involve 21 3D joints, using an RGB egocentric video image provide
Externí odkaz:
http://arxiv.org/abs/2406.12219
This report presents our team's 'PCIE_LAM' solution for the Ego4D Looking At Me Challenge at CVPR2024. The main goal of the challenge is to accurately determine if a person in the scene is looking at the camera wearer, based on a video where the face
Externí odkaz:
http://arxiv.org/abs/2406.12211
Autor:
Wang, Zhepeng, Sheng, Yi, Koirala, Nirajan, Basu, Kanad, Jung, Taeho, Lu, Cheng-Chang, Jiang, Weiwen
Benefiting from cloud computing, today's early-stage quantum computers can be remotely accessed via the cloud services, known as Quantum-as-a-Service (QaaS). However, it poses a high risk of data leakage in quantum machine learning (QML). To run a QM
Externí odkaz:
http://arxiv.org/abs/2404.13475
Publikováno v:
IEEE Transactions on Geoscience and Remote Sensing, vol. 61, 2023, pp. 1-12
LiDAR-camera fusion can enhance the performance of 3D object detection by utilizing complementary information between depth-aware LiDAR points and semantically rich images. Existing voxel-based methods face significant challenges when fusing sparse v
Externí odkaz:
http://arxiv.org/abs/2401.02702
Seismic full waveform inversion (FWI) is a widely used technique in geophysics for inferring subsurface structures from seismic data. And InversionNet is one of the most successful data-driven machine learning models that is applied to seismic FWI. H
Externí odkaz:
http://arxiv.org/abs/2310.09667
Establishing the correspondences between newly acquired points and historically accumulated data (i.e., map) through nearest neighbors search is crucial in numerous robotic applications. However, static tree data structures are inadequate to handle l
Externí odkaz:
http://arxiv.org/abs/2309.08315
Autor:
Huang, Kaer, Sun, Bingchuan, Chen, Feng, Zhang, Tao, Xie, Jun, Li, Jian, Twombly, Christopher Walter, Wang, Zhepeng
In recent years, dominant Multi-object tracking (MOT) and segmentation (MOTS) methods mainly follow the tracking-by-detection paradigm. Transformer-based end-to-end (E2E) solutions bring some ideas to MOT and MOTS, but they cannot achieve a new state
Externí odkaz:
http://arxiv.org/abs/2308.01622
Quantum computing presents a promising approach for machine learning with its capability for extremely parallel computation in high-dimension through superposition and entanglement. Despite its potential, existing quantum learning algorithms, such as
Externí odkaz:
http://arxiv.org/abs/2307.09771