Multiple Riemannian Kernel Hashing for Large-Scale Image Set Classification and Retrieval [0.03%]
基于多黎曼核 hashing的大规模图像集分类和检索方法
Xiaobo Shen,Wei Wu,Xiaxin Wang et al.
Xiaobo Shen et al.
Conventional image set methods typically learn from small to medium-sized image set datasets. However, when applied to large-scale image set applications such as classification and retrieval, they face two primary challenges: 1) effectively...
Shuo Wang,Jinda Lu,Haiyang Xu et al.
Shuo Wang et al.
Few-shot learning (FSL) aims at recognizing a novel object under limited training samples. A robust feature extractor (backbone) can significantly improve the recognition performance of the FSL model. However, training an effective backbone...
Dynamic Spatio-Temporal Graph Reasoning for VideoQA With Self-Supervised Event Recognition [0.03%]
具有自监督事件识别的视频问答中的动态时空图推理
Jie Nie,Xin Wang,Runze Hou et al.
Jie Nie et al.
Video question answering (VideoQA) requires the ability of comprehensively understanding visual contents in videos. Existing VideoQA models mainly focus on scenarios involving a single event with simple object interactions and leave event-c...
Learning Kernel-Modulated Neural Representation for Efficient Light Field Compression [0.03%]
基于核调制神经表示的高效光场压缩方法
Jinglei Shi,Yihong Xu,Christine Guillemot
Jinglei Shi
Light fields capture 3D scene information by recording light rays emitted from a scene at various orientations. They offer a more immersive perception, compared with classic 2D images, but at the cost of huge data volumes. In this paper, we...
Learning to Discover Knowledge: A Weakly-Supervised Partial Domain Adaptation Approach [0.03%]
弱監督下的部分领域自适应学习方法
Mengcheng Lan,Min Meng,Jun Yu et al.
Mengcheng Lan et al.
Domain adaptation has shown appealing performance by leveraging knowledge from a source domain with rich annotations. However, for a specific target task, it is cumbersome to collect related and high-quality source domains. In real-world sc...
5-D Epanechnikov Mixture-of-Experts in Light Field Image Compression [0.03%]
用于光场图像压缩的5D Epanechnikov专家混合模型
Boning Liu,Yan Zhao,Xiaomeng Jiang et al.
Boning Liu et al.
In this study, we propose a modeling-based compression approach for dense/lenslet light field images captured by Plenoptic 2.0 with square microlenses. This method employs the 5-D Epanechnikov Kernel (5-D EK) and its associated theories. Ow...
Single-Subject Deep-Learning Image Reconstruction With a Neural Optimization Transfer Algorithm for PET-Enabled Dual-Energy CT Imaging [0.03%]
具有神经优化传输算法的单例深度学习图像重建PET启用的双能量CT成像
Siqi Li,Yansong Zhu,Benjamin A Spencer et al.
Siqi Li et al.
Combining dual-energy computed tomography (DECT) with positron emission tomography (PET) offers many potential clinical applications but typically requires expensive hardware upgrades or increases radiation doses on PET/CT scanners due to a...
Image Quality Assessment: Measuring Perceptual Degradation via Distribution Measures in Deep Feature Spaces [0.03%]
基于深度特征空间中分布度量的图像质量评价方法研究感知退化
Xingran Liao,Xuekai Wei,Mingliang Zhou et al.
Xingran Liao et al.
This study aims to develop advanced and training-free full-reference image quality assessment (FR-IQA) models based on deep neural networks. Specifically, we investigate measures that allow us to perceptually compare deep network features a...
Qiankun Liu,Yichen Li,Yuqi Jiang et al.
Qiankun Liu et al.
The ability to detect and track the dynamic objects in different scenes is fundamental to real-world applications, e.g., autonomous driving and robot navigation. However, traditional Multi-Object Tracking (MOT) is limited to track objects b...
Self-Supervised Representation Learning With Spatial-Temporal Consistency for Sign Language Recognition [0.03%]
基于时空一致性的自监督表示学习的手语识别方法
Weichao Zhao,Wengang Zhou,Hezhen Hu et al.
Weichao Zhao et al.
Recently, there have been efforts to improve the performance in sign language recognition by designing self-supervised learning methods. However, these methods capture limited information from sign pose data in a frame-wise learning manner,...