Predicting diverse human motions given a sequence of historical poses has received increasing attention. Despite rapid progress, existing work captures the multi-modal nature of human motions primarily through likelihood-based sampling, where the mode collapse has been widely observed. In this paper, we propose a simple yet effective approach that disentangles randomly sampled codes with a deterministic learnable component named anchors to promote sample precision and diversity. Anchors are further factorized into spatial anchors and temporal anchors, which provide attractively interpretable control over spatial-temporal disparity. In principle, our spatial-temporal anchor-based sampling (STARS) can be applied to different motion predictors. Here we propose an interaction-enhanced spatial-temporal graph convolutional network (IE-STGCN) that encodes prior knowledge of human motions (e.g., spatial locality), and incorporate the anchors into it. Extensive experiments demonstrate that our approach outperforms state of the art in both stochastic and deterministic prediction, suggesting it as a unified framework for modeling human motions. Our code and pretrained models are available at https://github.com/Sirui-Xu/STARS.
Guided Table Structure Recognition through Anchor Optimization
German Research Center for Artificial Intelligence(德国人工智能研究中心);University of Kaiserslautern(凯泽斯劳滕大学);Mindgrage;Luleå University of Technology(吕勒奥理工大学);Bilojix Soft Technologies(Bilojix软件技术公司)
Anchor-free 3D Single Stage Detector with Mask-Guided Attention for Point Cloud
Zhejiang University(浙江大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);Inception Institute of Artificial Intelligence(起源人工智能研究院)
Gaussian Guided IoU: A Better Metric for Balanced Learning on Object Detection
Huazhong University of Science and Technology(华中科技大学)
对于大多数基于锚点的检测器,Intersection over Union(IoU)被广泛用于在训练期间为锚点分配目标。然而,IoU对锚点中心与真值框中心的接近程度关注不够。这导致两个问题:(1)大多数细长物体只分配一个锚点,导致训练过程中对细长物体的监督信息不足,影响细长物体的表现;(2)IoU不能准确地表示锚点中心特征的感受野与物体的对齐程度。因此,在训练过程中,一些特征的感受野对准更好的对象是失踪,而一些特征的感受野对准较差的对象被采用。这损害了模型的定位精度。为了解决这些问题,我们首先设计了高斯引导的IoU(GGIoU),它更加关注锚点中心与真值盒中心的接近程度。在此基础上,提出了GGIoU均衡学习方法,包括GGIoU引导的分配策略和GGIoU均衡的定位损失。该方法可以为每个细长物体分配多个锚点,并将训练过程偏向于与物体对齐的特征。在PASCAL VOC和MS COCO等主流测试平台上的大量实验表明,GGIoU均衡学习可以解决上述问题,并显著提高目标检测模型的性能,尤其是定位精度。
AGE-MIL: Anchor-Guided Evidence Learning for Patient-Level Prediction
School of Computer Science and Technology, Xi’an Jiaotong University(西安交通大学计算机科学与技术学院);Department of Oncology, University of Cambridge(剑桥大学肿瘤学系);Xiangya School of Medicine, Central South University(中南大学湘雅医学院)
Enhancing Multi-Camera People Tracking with Anchor-Guided Clustering and Spatio-Temporal Consistency ID Re-Assignment
University of Washington(华盛顿大学);Electronics and Telecommunications Research Institute(电子与电信研究所);National Center for High-Performance Computing(国家高性能计算中心)
提出一种结合锚定引导聚类与时空一致性的多摄像机多人员跟踪方法,在CVPR AI City Challenge 2023上以95.36% IDF1获第一名。
GeoSearcher: Anchor-Guided Progressive Reasoning for Remote Sensing Visual Grounding with Process Supervision
Key Laboratory of Target Cognition and Application Technology (TCAT), Chinese Academy of Sciences(中国科学院目标认知与应用技术重点实验室);School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences(中国科学院大学电子电气与通信工程学院)
AG-VAS: Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Casivision(中科视语);Weiqiao-UCAS Science and Technology Park(魏桥国科科技园)
TrAME: Trajectory-Anchored Multi-View Editing for Text-Guided 3D Gaussian Splatting Manipulation
School of Information Science and Technology, University of Science and Technology of China(中国科学技术大学信息科学技术学院);Space AI, Li Auto(理想汽车空间人工智能部门);Department of Automation, Tsinghua University(清华大学自动化系)
HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene
Institute of Computing Technology, Chinese Academy of Sciences, ICT(中国科学院计算技术研究所);University of Chinese Academy of Sciences, UCAS(中国科学院大学);The University of Queensland(昆士兰大学);Jiangsu University(江苏大学)
CG-SSD: Corner Guided Single Stage 3D Object Detection from LiDAR Point Cloud
Wuhan University(武汉大学)
目前,基于锚点或无锚点的三维目标检测模型均采用中心分配器策略来推断三维边界框。然而,在现实场景中,激光雷达只能获取有限的物体表面点云,而物体的中心点是不存在的。通过聚集不完整的表面点云来获取目标,会带来方向和尺寸估计精度的损失。针对这一问题,本文提出了一种角点引导无锚点单级三维目标检测模型(CG-SSD),该模型首先利用由残差层和子流形稀疏卷积层组成的三维稀疏卷积骨干网络构建鸟瞰图(BEV)特征,然后利用精简的U型网络进行更深层次的特征挖掘;其次,提出了一种新的角点引导辅助模块(CGAM),将角点监控信号纳入神经网络。CGAM被明确地设计和训练来检测部分可见和不可见的角点,以获得更准确的对象特征表示,特别是对于小的或部分被遮挡的对象;最后,来自骨干网络和CGAM模块的深度特征被连接并馈送到头部模块,以预测场景中对象的分类和3D边界框。实验结果表明,CG-SSD在ONCE基准测试中使用单帧点云数据进行监督式3D目标检测,达到了最先进的性能,具有62.77%mAP。此外,在ONCE和Waymo Open Dataset上的实验表明,CGAM可以扩展到大多数基于锚点的模型,这些模型使用BEV特征来检测对象,作为插件,并带来+1.17%-+14.27%AP的改进。
AIParsing: Anchor-free Instance-level Human Parsing
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);Georgia Tech Shenzhen Institute, Tianjin University(天津大学佐治亚理工深圳学院);Sun Yat-sen University(中山大学);Futurewei Technologies(未来技术公司);Tsinghua University(清华大学)
PIU: Proximity-guided Identity Unlearning in ID-Conditioned Diffusion Models
University of Ljubljana, Faculty of Computer and Information Science(卢布尔雅那大学计算机与信息科学系);University of Ljubljana, Faculty of Electrical Engineering(卢布尔雅那大学电子工程系)
MAP-Diff: Multi-Anchor Guided Diffusion for Progressive 3D Whole-Body Low-Dose PET Denoising
School of Engineering, Zurich University of Applied Sciences, CH;Bioengineering Department;Imperial-X, Imperial College London, UK;DAMTP, University of Cambridge, UK;Lucerne University Teaching;Research Hospital, CH;Lung Institute, Imperial College London, UK;Cardiovascular Research Centre, Royal Brompton Hospital, UK;School of Biomedical Engineering \& Imaging Sciences, King's College London, UK;Yau Mathematical Sciences Center, Tsinghua University, CN
Skeleton-Guided Sparse Anchors for Rotated Instance Segmentation in Cell Microscopy
Aier Institute of Digital Ophthalmology and Visual Science(爱尔数字眼科学与视觉科学研究所);Changsha Aier Eye Hospital(长沙爱尔眼科医院);Shanghai Jiao Tong University(上海交通大学);Nanyang Technological University(南洋理工大学);Obstetrics and Gynecology Hospital, Institute of Reproduction and Development, Fudan University(复旦大学附属妇产科医院 生殖与发育研究院)
ARTEMIS: Agent-guided Reliability-aware Temporal Mask Evolution for Imperfectly Supervised Video Polyp Segmentation
Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Southeast University, Ministry of Education(东南大学教育部新一代人工智能技术及其跨学科应用重点实验室);Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)(穆罕默德·本·扎耶德人工智能大学);School of Medicine, Case Western Reserve University(凯斯西储大学医学院)
Weakly Supervised Temporal Sentence Grounding via Positive Sample Mining
University of Science and Technology of China(中国科学技术大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Beihang University(北京航空航天大学);State Key Laboratory for Novel Software Technology(国家软件创新科技重点实验室);Nanjing University(南京大学);Shenzhen Key Laboratory of Computer Vision and Pattern Recognition(深圳计算机视觉与模式识别重点实验室);Shenzhen Institute of Advanced Technology(深圳先进技术研究院);Chinese Academy of Sciences(中国科学院)