Zobrazeno 1 - 10
of 8 165
pro vyhledávání: '"XUE, Jing"'
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology, 2024
Most facial expression recognition (FER) models are trained on large-scale expression data with centralized learning. Unfortunately, collecting a large amount of centralized expression data is difficult in practice due to privacy concerns of facial i
Externí odkaz:
http://arxiv.org/abs/2501.01816
Augmentation Matters: A Mix-Paste Method for X-Ray Prohibited Item Detection under Noisy Annotations
Automatic X-ray prohibited item detection is vital for public safety. Existing deep learning-based methods all assume that the annotations of training X-ray images are correct. However, obtaining correct annotations is extremely hard if not impossibl
Externí odkaz:
http://arxiv.org/abs/2501.01733
The surprising inversion of the orbital- and magnetic-order transition temperatures in the RVO3 series with increasing the rare-earth radius makes the series unique among orbitally-ordered materials. Here, augmenting dynamical mean-field theory with
Externí odkaz:
http://arxiv.org/abs/2411.16351
Autor:
Wang, Hai, Xue, Jing-Hao
Preserving boundary continuity in the translation of 360-degree panoramas remains a significant challenge for existing text-driven image-to-image translation methods. These methods often produce visually jarring discontinuities at the translated pano
Externí odkaz:
http://arxiv.org/abs/2409.08397
Positive-unlabeled (PU) learning aims to train a classifier using the data containing only labeled-positive instances and unlabeled instances. However, existing PU learning methods are generally hard to achieve satisfactory performance on trifurcate
Externí odkaz:
http://arxiv.org/abs/2405.20970
Existing 3D occupancy networks demand significant hardware resources, hindering the deployment of edge devices. Binarized Neural Networks (BNN) offer substantially reduced computational and memory requirements. However, their performance decreases no
Externí odkaz:
http://arxiv.org/abs/2405.17037
We address prevailing challenges of the brain-powered research, departing from the observation that the literature hardly recover accurate spatial information and require subject-specific models. To address these challenges, we propose UMBRAE, a unif
Externí odkaz:
http://arxiv.org/abs/2404.07202
Autor:
Li, Jin-Xin, Feng, Xue-Jing, Zhang, Ying-Ying, Liu, Jing-Xue, Qin, Lu, Zhu, Zun-Lue, Zhao, Xing-Dong, Wang, Liang-Liang
We systematically investigate unconventional superfluid phases of fermionic dipolar particles lying in a double-wire setup with laser-assisted interwire tunneling. Our numerical simulations, based on the nonlocal Kohn-Sham Bogoliubov-de Gennes equati
Externí odkaz:
http://arxiv.org/abs/2404.03230
Visible-infrared person re-identification (VI-ReID) aims to retrieve images of the same persons captured by visible (VIS) and infrared (IR) cameras. Existing VI-ReID methods ignore high-order structure information of features while being relatively d
Externí odkaz:
http://arxiv.org/abs/2312.07853
Most existing GAN inversion methods either achieve accurate reconstruction but lack editability or offer strong editability at the cost of fidelity. Hence, how to balance the distortioneditability trade-off is a significant challenge for GAN inversio
Externí odkaz:
http://arxiv.org/abs/2312.07079