Výsledky vyhledávání - "IEEE Transactions on Pattern Analysis and Machine Intelligence"

Res2Net: A New Multi-Scale Backbone Architecture Autor Gao, Shang-Hua, Cheng, Ming-Ming, Zhao, Kai, Zhang, Xin-Yu, Yang, Ming-Hsuan, Torr, Philip

“…Representing features at multiple scales is of great importance for numerous vision tasks. Recent advances in backbone convolutional neural networks (CNNs)…”
Získat plný text

KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D Autor Liao, Yiyi, Xie, Jun, Geiger, Andreas

“…For the last few decades, several major subfields of artificial intelligence including computer vision, graphics, and robotics have progressed largely…”
Získat plný text

Residual Dense Network for Image Restoration Autor Zhang, Yulun, Tian, Yapeng, Kong, Yu, Zhong, Bineng, Fu, Yun

“…Recently, deep convolutional neural network (CNN) has achieved great success for image restoration (IR) and provided hierarchical features at the same time…”
Získat plný text

YOLACT++ Better Real-Time Instance Segmentation Autor Bolya, Daniel, Zhou, Chong, Xiao, Fanyi, Lee, Yong Jae

“…We present a simple, fully-convolutional model for real-time (<inline-formula><tex-math notation="LaTeX">>30</tex-math>…”
Získat plný text

Maximum Density Divergence for Domain Adaptation Autor Li, Jingjing, Chen, Erpeng, Ding, Zhengming, Zhu, Lei, Lu, Ke, Shen, Heng Tao

“…Unsupervised domain adaptation addresses the problem of transferring knowledge from a well-labeled source domain to an unlabeled target domain where the two…”
Získat plný text

ZeroNAS: Differentiable Generative Adversarial Networks Search for Zero-Shot Learning Autor Yan, Caixia, Chang, Xiaojun, Li, Zhihui, Guan, Weili, Ge, Zongyuan, Zhu, Lei, Zheng, Qinghua

“…In recent years, remarkable progress in zero-shot learning (ZSL) has been achieved by generative adversarial networks (GAN). To compensate for the lack of…”
Získat plný text

A Survey on Label-Efficient Deep Image Segmentation: Bridging the Gap Between Weak Supervision and Dense Prediction Autor Shen, Wei, Peng, Zelin, Wang, Xuehui, Wang, Huayu, Cen, Jiazhong, Jiang, Dongsheng, Xie, Lingxi, Yang, Xiaokang, Tian, Qi

Získat plný text

Multi-Task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition Autor Luvizon, Diogo C., Picard, David, Tabia, Hedi

“…Human pose estimation and action recognition are related tasks since both problems are strongly dependent on the human body representation and analysis…”
Získat plný text

Universal Adversarial Attack on Attention and the Resulting Dataset DAmageNet Autor Chen, Sizhe, He, Zhengbao, Sun, Chengjin, Yang, Jie, Huang, Xiaolin

“…Adversarial attacks on deep neural networks (DNNs) have been found for several years. However, the existing adversarial attacks have high success rates only…”
Získat plný text

Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation Autor Sun, Deqing, Yang, Xiaodong, Liu, Ming-Yu, Kautz, Jan

“…We investigate two crucial and closely-related aspects of CNNs for optical flow estimation: models and training. First, we design a compact but effective CNN…”
Získat plný text

Exploiting Surroundedness for Saliency Detection: A Boolean Map Approach Autor Jianming Zhang, Sclaroff, Stan

“…We demonstrate the usefulness of surroundedness for eye fixation prediction by proposing a Boolean Map based Saliency model (BMS). In our formulation, an image…”
Získat plný text

MRA-Net: Improving VQA Via Multi-Modal Relation Attention Network Autor Peng, Liang, Yang, Yang, Wang, Zheng, Huang, Zi, Shen, Heng Tao

“…Visual Question Answering (VQA) is a task to answer natural language questions tied to the content of visual images. Most recent VQA approaches usually apply…”
Získat plný text

Eye Movement Analysis for Activity Recognition Using Electrooculography Autor Bulling, Andreas, Ward, Jamie A, Gellersen, Hans, Tröster, Gerhard

“…In this work, we investigate eye movement analysis as a new sensing modality for activity recognition. Eye movement data were recorded using an…”
Získat plný text

A Novel Linelet-Based Representation for Line Segment Detection Autor Nam-Gyu Cho, Yuille, Alan, Seong-Whan Lee

“…This paper proposes a method for line segment detection in digital images. We propose a novel linelet-based representation to model intrinsic properties of…”
Získat plný text

Minutia Cylinder-Code: A New Representation and Matching Technique for Fingerprint Recognition Autor Cappelli, Raffaele, Ferrara, Matteo, Maltoni, Davide

“…In this paper, we introduce the Minutia Cylinder-Code (MCC): a novel representation based on 3D data structures (called cylinders), built from minutiae…”
Získat plný text

Sparse and Dense Hybrid Representation via Dictionary Decomposition for Face Recognition Autor Jiang, Xudong, Lai, Jian

“…Sparse representation provides an effective tool for classification under the conditions that every class has sufficient representative training samples and…”
Získat plný text

Simultaneous Tensor Decomposition and Completion Using Factor Priors Autor Yi-Lei Chen, Chiou-Ting Hsu, Liao, Hong-Yuan Mark

“…The success of research on matrix completion is evident in a variety of real-world applications. Tensor completion, which is a high-order extension of matrix…”
Získat plný text

A Least-Squares Framework for Component Analysis Autor De la Torre, F.

“…Over the last century, Component Analysis (CA) methods such as Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), Canonical Correlation…”
Získat plný text

Multi-Modality Deep Restoration of Extremely Compressed Face Videos Autor Zhang, Xi, Wu, Xiaolin

“…Arguably the most common and salient object in daily video communications is the talking head, as encountered in social media, virtual classrooms,…”
Získat plný text

Flexible Clustered Multi-Task Learning by Learning Representative Tasks Autor Zhou, Qiang, Zhao, Qi

“…Multi-task learning (MTL) methods have shown promising performance by learning multiple relevant tasks simultaneously, which exploits to share useful…”
Získat plný text