Zobrazeno 1 - 10
of 337
pro vyhledávání: '"Yang, Zhijing"'
Modern visual recognition models often display overconfidence due to their reliance on complex deep neural networks and one-hot target supervision, resulting in unreliable confidence scores that necessitate calibration. While current confidence calib
Externí odkaz:
http://arxiv.org/abs/2407.06844
Recently, commonsense learning has been a hot topic in image-text matching. Although it can describe more graphic correlations, commonsense learning still has some shortcomings: 1) The existing methods are based on triplet semantic similarity measure
Externí odkaz:
http://arxiv.org/abs/2311.05425
We aim at incorporating explicit shape information into current 3D organ segmentation models. Different from previous works, we formulate shape learning as an in-painting task, which is named Masked Label Mask Modeling (MLM). Through MLM, learnable m
Externí odkaz:
http://arxiv.org/abs/2308.08775
This paper seeks to address the dense labeling problems where a significant fraction of the dataset can be pruned without sacrificing much accuracy. We observe that, on standard medical image segmentation benchmarks, the loss gradient norm-based metr
Externí odkaz:
http://arxiv.org/abs/2308.01189
Accurately predicting anesthetic effects is essential for target-controlled infusion systems. The traditional (PK-PD) models for Bispectral index (BIS) prediction require manual selection of model parameters, which can be challenging in clinical sett
Externí odkaz:
http://arxiv.org/abs/2308.01929
Autor:
Cao, Faxian, Cheng, Yongqiang, Khan, Adil Mehmood, Yang, Zhijing, Chang, S. M. Ahsan Kazmiand Yingxiu
Uncertainty in timing information pertaining to the start time of microphone recordings and sources' emission time pose significant challenges in various applications, such as joint microphones and sources localization. Traditional optimization metho
Externí odkaz:
http://arxiv.org/abs/2307.07096
The capability of video super-resolution (VSR) to synthesize high-resolution (HR) video from ideal datasets has been demonstrated in many works. However, applying the VSR model to real-world video with unknown and complex degradation remains a challe
Externí odkaz:
http://arxiv.org/abs/2305.14669
In an era where asynchronous environments pose challenges to traditional self-positioning methods, we propose a new transformation to the existing paradigm. Traditionally, time of arrival (TOA) measurements require both microphone and source signals,
Externí odkaz:
http://arxiv.org/abs/2305.11397
This study comes as a timely response to mounting criticism of the information bottleneck (IB) theory, injecting fresh perspectives to rectify misconceptions and reaffirm its validity. Firstly, we introduce an auxiliary function to reinterpret the ma
Externí odkaz:
http://arxiv.org/abs/2305.11387
Autor:
Chen, Junyang, Xian, Xiaoyu, Yang, Zhijing, Chen, Tianshui, Lu, Yongyi, Shi, Yukai, Pan, Jinshan, Lin, Liang
Pose transfer aims to transfer a given person into a specified posture, has recently attracted considerable attention. A typical pose transfer framework usually employs representative datasets to train a discriminative model, which is often violated
Externí odkaz:
http://arxiv.org/abs/2303.10945