UniParser: Multi-Human Parsing With Unified Correlation Representation Learning [0.03%]
UniParser：统一相关性表示学习的多人关键点解析模型
Jiaming Chu,Lei Jin,Yinglei Teng et al.
Jiaming Chu et al.
Multi-human parsing is an image segmentation task necessitating both instance-level and fine-grained category-level information. However, prior research has typically processed these two types of information through distinct branch types an...
Convex Hull Prediction for Adaptive Video Streaming by Recurrent Learning [0.03%]
基于循环学习的自适应视频流凸包预测方法研究
Somdyuti Paul,Andrey Norkin,Alan C Bovik
Somdyuti Paul
Adaptive video streaming relies on the construction of efficient bitrate ladders to deliver the best possible visual quality to viewers under bandwidth constraints. The traditional method of content dependent bitrate ladder selection requir...
Disentangled Sample Guidance Learning for Unsupervised Person Re-Identification [0.03%]
一种无监督行人重识别的解耦样本引导学习方法
Haoxuanye Ji,Le Wang,Sanping Zhou et al.
Haoxuanye Ji et al.
Unsupervised person re-identification (Re-ID) is challenging due to the lack of ground truth labels. Most existing methods employ iterative clustering to generate pseudo labels for unlabeled training data to guide the learning process. Howe...
Xi Yang,Huanling Liu,Nannan Wang et al.
Xi Yang et al.
The potential vulnerability of deep neural networks and the complexity of pedestrian images, greatly limits the application of person re-identification techniques in the field of smart security. Current attack methods often focus on generat...
Target Before Shooting: Accurate Anomaly Detection and Localization Under One Millisecond via Cascade Patch Retrieval [0.03%]
未雨绸缪：基于级联补丁检索的毫秒级精准异常检测与定位方法
Hanxi Li,Jianfei Hu,Bo Li et al.
Hanxi Li et al.
In this work, by re-examining the "matching" nature of Anomaly Detection (AD), we propose a novel AD framework that simultaneously enjoys new records of AD accuracy and dramatically high running speed. In this framework, the anomaly detecti...
Unified and Real-Time Image Geo-Localization via Fine-Grained Overlap Estimation [0.03%]
基于细粒度重叠估计的统一实时图像地理定位方法
Ze Song,Xudong Kang,Xiaohui Wei et al.
Ze Song et al.
Image geo-localization aims to locate a query image from source platform (e.g., drones, street vehicle) by matching it with Geo-tagged reference images from the target platforms (e.g., different satellites). Achieving cross-modal or cross-v...
Zhengqiang Zhang,Ruihuang Li,Shi Guo et al.
Zhengqiang Zhang et al.
Online video super-resolution (online-VSR) highly relies on an effective alignment module to aggregate temporal information, while the strict latency requirement makes accurate and efficient alignment very challenging. Though much progress ...
Learning a Non-Locally Regularized Convolutional Sparse Representation for Joint Chromatic and Polarimetric Demosaicking [0.03%]
联合色度和偏振解马赛克的非局部正则化卷积稀疏表示学习方法
Yidong Luo,Junchao Zhang,Jianbo Shao et al.
Yidong Luo et al.
Division of focal plane color polarization camera becomes the mainstream in polarimetric imaging for it directly captures color polarization mosaic image by one snapshot, so image demosaicking is an essential task. Current color polarizatio...
Modeling of Multiple Spatial-Temporal Relations for Robust Visual Object Tracking [0.03%]
鲁棒视觉目标跟踪中多重时空关系的建模方法研究
Shilei Wang,Zhenhua Wang,Qianqian Sun et al.
Shilei Wang et al.
Recently, one-stream trackers have achieved parallel feature extraction and relation modeling through the exploitation of Transformer-based architectures. This design greatly improves the performance of trackers. However, as one-stream trac...
HeightFormer: Explicit Height Modeling without Extra Data for Camera-only 3D Object Detection in Bird's Eye View [0.03%]
高度设计形式者：无需额外数据的相机仅三维物体检测中的显式高度建模
Yiming Wu,Ruixiang Li,Zequn Qin et al.
Yiming Wu et al.
Vision-based Bird's Eye View (BEV) representation is an emerging perception formulation for autonomous driving. The core challenge is to construct BEV space with multi-camera features, which is a one-to-many ill-posed problem. Diving into a...