Zobrazeno 1 - 10
of 5 353
pro vyhledávání: '"ZHENG, JIN"'
The development of person search techniques has been greatly promoted in recent years for its superior practicality and challenging goals. Despite their significant progress, existing person search models still lack the ability to continually learn f
Externí odkaz:
http://arxiv.org/abs/2410.19239
Class incremental learning (CIL) aims to learn a model that can not only incrementally accommodate new classes, but also maintain the learned knowledge of old classes. Out-of-distribution (OOD) detection in CIL is to retain this incremental learning
Externí odkaz:
http://arxiv.org/abs/2407.06045
Autor:
Zheng, Jin-Hao, Wang, Qin-Qin, Feng, Lan-Tian, Ding, Yu-Yang, Xu, Xiao-Ye, Ren, Xi-Feng, Li, Chuan-Feng, Guo, Guang-Can
The advancing maturity of photonic integrated circuit (PIC) fabrication technology enables the high integration of an increasing number of optical components onto a single chip. With the incremental circuit complexity, the calibration of active phase
Externí odkaz:
http://arxiv.org/abs/2407.02207
3D Gaussian Splatting (3DGS) creates a radiance field consisting of 3D Gaussians to represent a scene. With sparse training views, 3DGS easily suffers from overfitting, negatively impacting rendering. This paper introduces a new co-regularization per
Externí odkaz:
http://arxiv.org/abs/2405.12110
Autor:
Liu, Jian, Sun, Wei, Yang, Hui, Zeng, Zhiwen, Liu, Chongpei, Zheng, Jin, Liu, Xingyu, Rahmani, Hossein, Sebe, Nicu, Mian, Ajmal
Object pose estimation is a fundamental computer vision problem with broad applications in augmented reality and robotics. Over the past decade, deep learning models, due to their superior accuracy and robustness, have increasingly supplanted convent
Externí odkaz:
http://arxiv.org/abs/2405.07801
Radiance fields have demonstrated impressive performance in synthesizing lifelike 3D talking heads. However, due to the difficulty in fitting steep appearance changes, the prevailing paradigm that presents facial motions by directly modifying point a
Externí odkaz:
http://arxiv.org/abs/2404.15264
Existing prompt learning methods have shown certain capabilities in Out-of-Distribution (OOD) detection, but the lack of OOD images in the target dataset in their training can lead to mismatches between OOD images and In-Distribution (ID) categories,
Externí odkaz:
http://arxiv.org/abs/2404.03248
With advancements in domain generalized stereo matching networks, models pre-trained on synthetic data demonstrate strong robustness to unseen domains. However, few studies have investigated the robustness after fine-tuning them in real-world scenari
Externí odkaz:
http://arxiv.org/abs/2403.07705
DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization
Radiance fields have demonstrated impressive performance in synthesizing novel views from sparse input views, yet prevailing methods suffer from high training costs and slow inference speed. This paper introduces DNGaussian, a depth-regularized frame
Externí odkaz:
http://arxiv.org/abs/2403.06912
Publikováno v:
49th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, pp. 6545-6549
Stock trend classification remains a fundamental yet challenging task, owing to the intricate time-evolving dynamics between and within stocks. To tackle these two challenges, we propose a graph-based representation learning approach aimed at predict
Externí odkaz:
http://arxiv.org/abs/2401.05430