Filters








1,142 Hits in 2.3 sec

Disentangled Image Matting [article]

Shaofan Cai, Xiaoshuai Zhang, Haoqiang Fan, Haibin Huang, Jiangyu Liu, Jiaming Liu, Jiaying Liu, Jue Wang, Jian Sun
2019 arXiv   pre-print
Most previous image matting methods require a roughly-specificed trimap as input, and estimate fractional alpha values for all pixels that are in the unknown region of the trimap. In this paper, we argue that directly estimating the alpha matte from a coarse trimap is a major limitation of previous methods, as this practice tries to address two difficult and inherently different problems at the same time: identifying true blending pixels inside the trimap region, and estimate accurate alpha
more » ... es for them. We propose AdaMatting, a new end-to-end matting framework that disentangles this problem into two sub-tasks: trimap adaptation and alpha estimation. Trimap adaptation is a pixel-wise classification problem that infers the global structure of the input image by identifying definite foreground, background, and semi-transparent image regions. Alpha estimation is a regression problem that calculates the opacity value of each blended pixel. Our method separately handles these two sub-tasks within a single deep convolutional neural network (CNN). Extensive experiments show that AdaMatting has additional structure awareness and trimap fault-tolerance. Our method achieves the state-of-the-art performance on Adobe Composition-1k dataset both qualitatively and quantitatively. It is also the current best-performing method on the alphamatting.com online evaluation for all commonly-used metrics.
arXiv:1909.04686v1 fatcat:lri2hzyp45d5jd35ffhey36xqi

Graph Force Learning [article]

Ke Sun, Jiaying Liu, Shuo Yu, Bo Xu, Feng Xia
2021 arXiv   pre-print
Features representation leverages the great power in network analysis tasks. However, most features are discrete which poses tremendous challenges to effective use. Recently, increasing attention has been paid on network feature learning, which could map discrete features to continued space. Unfortunately, current studies fail to fully preserve the structural information in the feature space due to random negative sampling strategy during training. To tackle this problem, we study the problem
more » ... feature learning and novelty propose a force-based graph learning model named GForce inspired by the spring-electrical model. GForce assumes that nodes are in attractive forces and repulsive forces, thus leading to the same representation with the original structural information in feature learning. Comprehensive experiments on benchmark datasets demonstrate the effectiveness of the proposed framework. Furthermore, GForce opens up opportunities to use physics models to model node interaction for graph learning.
arXiv:2103.04344v1 fatcat:yfywxe2nq5eqzasok5pmwbg2ry

Boundary value problems for fractional differential equations

Zhigang Hu, Wenbin Liu, Jiaying Liu
2014 Boundary Value Problems  
In this paper we study the existence of solutions of nonlinear fractional differential equations at resonance. By using the coincidence degree theory, some results on the existence of solutions are obtained. MSC: 34A08; 34B15
doi:10.1186/s13661-014-0176-5 fatcat:tggvbnughrgzfpppsgn3mlv3wq

A Comprehensive Benchmark for Single Image Compression Artifacts Reduction [article]

Jiaying Liu, Dong Liu, Wenhan Yang, Sifeng Xia, Xiaoshuai Zhang, Yuanying Dai
2019 arXiv   pre-print
Liu, S. Chang, Q. Ling, Y. Yang, and T. S.  ... 
arXiv:1909.03647v1 fatcat:yujaixpevzeadi7zfh7ap6t7jq

Deep Retinex Decomposition for Low-Light Enhancement [article]

Chen Wei, Wenjing Wang, Wenhan Yang, Jiaying Liu
2018 arXiv   pre-print
Retinex model is an effective tool for low-light image enhancement. It assumes that observed images can be decomposed into the reflectance and illumination. Most existing Retinex-based methods have carefully designed hand-crafted constraints and parameters for this highly ill-posed decomposition, which may be limited by model capacity when applied in various scenes. In this paper, we collect a LOw-Light dataset (LOL) containing low/normal-light image pairs and propose a deep Retinex-Net learned
more » ... on this dataset, including a Decom-Net for decomposition and an Enhance-Net for illumination adjustment. In the training process for Decom-Net, there is no ground truth of decomposed reflectance and illumination. The network is learned with only key constraints including the consistent reflectance shared by paired low/normal-light images, and the smoothness of illumination. Based on the decomposition, subsequent lightness enhancement is conducted on illumination by an enhancement network called Enhance-Net, and for joint denoising there is a denoising operation on reflectance. The Retinex-Net is end-to-end trainable, so that the learned decomposition is by nature good for lightness adjustment. Extensive experiments demonstrate that our method not only achieves visually pleasing quality for low-light enhancement but also provides a good representation of image decomposition.
arXiv:1808.04560v1 fatcat:2ivsyi2ilzbvpp7im5upsigcz4

Temporal Bilinear Networks for Video Action Recognition [article]

Yanghao Li, Sijie Song, Yuqi Li, Jiaying Liu
2018 arXiv   pre-print
Temporal modeling in videos is a fundamental yet challenging problem in computer vision. In this paper, we propose a novel Temporal Bilinear (TB) model to capture the temporal pairwise feature interactions between adjacent frames. Compared with some existing temporal methods which are limited in linear transformations, our TB model considers explicit quadratic bilinear transformations in the temporal domain for motion evolution and sequential relation modeling. We further leverage the
more » ... bilinear model in linear complexity and a bottleneck network design to build our TB blocks, which also constrains the parameters and computation cost. We consider two schemes in terms of the incorporation of TB blocks and the original 2D spatial convolutions, namely wide and deep Temporal Bilinear Networks (TBN). Finally, we perform experiments on several widely adopted datasets including Kinetics, UCF101 and HMDB51. The effectiveness of our TBNs is validated by comprehensive ablation analyses and comparisons with various state-of-the-art methods.
arXiv:1811.09974v1 fatcat:vvpgecnfezcarpv43d7vo7kpky

Demystifying Neural Style Transfer [article]

Yanghao Li, Naiyan Wang, Jiaying Liu, Xiaodi Hou
2017 arXiv   pre-print
Neural Style Transfer has recently demonstrated very exciting results which catches eyes in both academia and industry. Despite the amazing results, the principle of neural style transfer, especially why the Gram matrices could represent style remains unclear. In this paper, we propose a novel interpretation of neural style transfer by treating it as a domain adaptation problem. Specifically, we theoretically show that matching the Gram matrices of feature maps is equivalent to minimize the
more » ... mum Mean Discrepancy (MMD) with the second order polynomial kernel. Thus, we argue that the essence of neural style transfer is to match the feature distributions between the style images and the generated images. To further support our standpoint, we experiment with several other distribution alignment methods, and achieve appealing results. We believe this novel interpretation connects these two important research fields, and could enlighten future researches.
arXiv:1701.01036v2 fatcat:mxjuftjjonafxhwzvoyeua6mwi

The Histaminergic System in Neuropsychiatric Disorders

Li Cheng, Jiaying Liu, Zhong Chen
2021 Biomolecules  
Histamine does not only modulate the immune response and inflammation, but also acts as a neurotransmitter in the mammalian brain. The histaminergic system plays a significant role in the maintenance of wakefulness, appetite regulation, cognition and arousal, which are severely affected in neuropsychiatric disorders. In this review, we first briefly describe the distribution of histaminergic neurons, histamine receptors and their intracellular pathways. Next, we comprehensively summarize recent
more » ... experimental and clinical findings on the precise role of histaminergic system in neuropsychiatric disorders, including cell-type role and its circuit bases in narcolepsy, schizophrenia, Alzheimer's disease, Tourette's syndrome and Parkinson's disease. Finally, we provide some perspectives on future research to illustrate the curative role of the histaminergic system in neuropsychiatric disorders.
doi:10.3390/biom11091345 pmid:34572558 pmcid:PMC8467868 fatcat:jwepauu375gv5na7awpnvjtldi

The tetrapod fauna of the upper Permian Naobaogou Formation of China: 3. Jiufengia jiai gen. et sp. nov., a large akidnognathid therocephalian

Jun Liu, Fernando Abdala
2019 PeerJ  
We present here a new large therocephalian, Jiufengia jiai gen. et sp. nov., represented by a partial skull with mandibles and part of the postcranial skeleton.  ...  ACKNOWLEDGEMENTS We thank the field team that worked at Daqingshan in 2011 (Jia Zhen-Yan, Li Lu, Li Xing-wen and Liu Yu-feng).  ...  Photo credit: Jun Liu. Full-size  DOI: 10.7717/peerj.6463/fig-8 Figure 9 9 Figure 9 Holotype of Jiufengnathus jiai (IVPP V 23877) from the Naobaogou Formation of China.  ... 
doi:10.7717/peerj.6463 pmid:30809450 pmcid:PMC6388668 fatcat:nvz5ndy6ojdtfp5ndr6ypoqmxq

Symmetry-Aware Transformer-based Mirror Detection [article]

Tianyu Huang, Bowen Dong, Jiaying Lin, Xiaohui Liu, Rynson W.H. Lau, Wangmeng Zuo
2022 arXiv   pre-print
Liu et al. [18] proposed to fuse depth information with attention mechanisms. Pang et al. [25] integrated RGB and depth through densely connected structures. Liu et al.  ... 
arXiv:2207.06332v1 fatcat:d6s33ttfvbeg3a2hib54zbwhci

Progressive Depth Learning for Single Image Dehazing [article]

Yudong Liang, Bin Wang, Jiaying Liu, Deyu Li, Sanping Zhou, Wenqi Ren
2021 arXiv   pre-print
The formulation of the hazy image is mainly dominated by the reflected lights and ambient airlight. Existing dehazing methods often ignore the depth cues and fail in distant areas where heavier haze disturbs the visibility. However, we note that the guidance of the depth information for transmission estimation could remedy the decreased visibility as distances increase. In turn, the good transmission estimation could facilitate the depth estimation for hazy images. In this paper, a deep
more » ... nd model that iteratively estimates image depths and transmission maps is proposed to perform an effective depth prediction for hazy images and improve the dehazing performance with the guidance of depth information. The image depth and transmission map are progressively refined to better restore the dehazed image. Our approach benefits from explicitly modeling the inner relationship of image depth and transmission map, which is especially effective for distant hazy areas. Extensive results on the benchmarks demonstrate that our proposed network performs favorably against the state-of-the-art dehazing methods in terms of depth estimation and haze removal.
arXiv:2102.10514v1 fatcat:f22dxkhkszdo5mn3w3ibwqo3eq

Revisit Visual Representation in Analytics Taxonomy: A Compression Perspective [article]

Yueyu Hu, Wenhan Yang, Haofeng Huang, Jiaying Liu
2021 arXiv   pre-print
Visual analytics have played an increasingly critical role in the Internet of Things, where massive visual signals have to be compressed and fed into machines. But facing such big data and constrained bandwidth capacity, existing image/video compression methods lead to very low-quality representations, while existing feature compression techniques fail to support diversified visual analytics applications/tasks with low-bit-rate representations. In this paper, we raise and study the novel
more » ... of supporting multiple machine vision analytics tasks with the compressed visual representation, namely, the information compression problem in analytics taxonomy. By utilizing the intrinsic transferability among different tasks, our framework successfully constructs compact and expressive representations at low bit-rates to support a diversified set of machine vision tasks, including both high-level semantic-related tasks and mid-level geometry analytic tasks. In order to impose compactness in the representations, we propose a codebook-based hyperprior, which helps map the representation into a low-dimensional manifold. As it well fits the signal structure of the deep visual feature, it facilitates more accurate entropy estimation, and results in higher compression efficiency. With the proposed framework and the codebook-based hyperprior, we further investigate the relationship of different task features owning different levels of abstraction granularity. Experimental results demonstrate that with the proposed scheme, a set of diversified tasks can be supported at a significantly lower bit-rate, compared with existing compression schemes.
arXiv:2106.08512v1 fatcat:zlgg4l5uczgorgk2ozwgorkbja

Modality Compensation Network: Cross-Modal Adaptation for Action Recognition [article]

Sijie Song, Jiaying Liu, Yanghao Li, Zongming Guo
2020 arXiv   pre-print
(Corresponding author: Jiaying Liu.)  ...  Liu et al. [44] jointly learned the regression and classification network with multi-modal data for action detection.  ... 
arXiv:2001.11657v1 fatcat:xcmed5yqx5bwrjpqzxsyguo7ga

Progressive residual learning for single image dehazing [article]

Yudong Liang, Bin Wang, Jiaying Liu, Deyu Li, Yuhua Qian, Wenqi Ren
2021 arXiv   pre-print
Jiaying Liu is with the Institute of Computer Science and Technology, Peking University, Beijing, China.  ... 
arXiv:2103.07973v1 fatcat:tomuvkmhnvfzhjm46zdrqhmxxy

Semi-Supervised Learning for Mars Imagery Classification and Segmentation [article]

Wenjing Wang, Lilang Lin, Zejia Fan, Jiaying Liu
2022 arXiv   pre-print
With the progress of Mars exploration, numerous Mars image data are collected and need to be analyzed. However, due to the imbalance and distortion of Martian data, the performance of existing computer vision models is unsatisfactory. In this paper, we introduce a semi-supervised framework for machine vision on Mars and try to resolve two specific tasks: classification and segmentation. Contrastive learning is a powerful representation learning technique. However, there is too much information
more » ... verlap between Martian data samples, leading to a contradiction between contrastive learning and Martian data. Our key idea is to reconcile this contradiction with the help of annotations and further take advantage of unlabeled data to improve performance. For classification, we propose to ignore inner-class pairs on labeled data as well as neglect negative pairs on unlabeled data, forming supervised inter-class contrastive learning and unsupervised similarity learning. For segmentation, we extend supervised inter-class contrastive learning into an element-wise mode and use online pseudo labels for supervision on unlabeled areas. Experimental results show that our learning strategies can improve the classification and segmentation models by a large margin and outperform state-of-the-art approaches.
arXiv:2206.02180v1 fatcat:e6supf3fwrafpk5f75ckjarl4u
« Previous Showing results 1 — 15 out of 1,142 results