AMiner平台由清华大学计算机系研发,拥有我国完全自主知识产权。平台包含了超过2.3亿学术论文/专利和1.36亿学者的科技图谱,提供学者评价、专家发现、智能指派、学术地图等科技情报专业化服务。系统2006年上线,吸引了全球220个国家/地区1000多万独立IP访问,数据下载量230万次,年度访问量超过1100万,成为学术搜索和社会网络挖掘研究的重要数据和实验平台。
【1】Instance Localization for Self-supervised Detection Pretraining(实例本地化的自我监督检测预训练)
论文链接:https://www.aminer.cn/pub/602cf50891e011c3e8f66bdd?conf=cvpr2021
【2】General Instance Distillation for Object Detection(目标检测的一般实例蒸馏)
论文链接:https://www.aminer.cn/pub/6040b1fa91e011a0653f071c?conf=cvpr2021
【3】Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection(语义关系推理在射程稳定的少镜头目标检测中的应用)
论文链接:https://www.aminer.cn/pub/603f7e2691e011cacfbda525?conf=cvpr2021
【4】UP-DETR: Unsupervised Pre-training for Object Detection with Transformers(UP-DETR:使用变压器进行目标检测的无监督预训练)
论文链接:https://www.aminer.cn/pub/5fb6418191e0116363c2c6a9?conf=cvpr2021
【5】Depth from Camera Motion and Object Detection(摄像机运动和目标检测的深度)
论文链接:https://www.aminer.cn/pub/603f692691e011cacfbda372?conf=cvpr2021
【1】Temporal-Relational CrossTransformers for Few-Shot Action Recognition(用于少镜头动作识别的时空关系交叉变换器)
论文链接:https://www.aminer.cn/pub/600560d591e0118e0cce22ec/?conf=cvpr2021
【2】Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack(了解对抗性攻击下基于骨架的动作识别的鲁棒性)
论文链接:https://www.aminer.cn/pub/60489e7291e0115491a5cbb0/?conf=cvpr2021
【3】ACTION-Net: Multipath Excitation for Action Recognition(ACTION-Net: 动作识别的多径激励)
论文链接:https://www.aminer.cn/pub/604f3c3b91e01127d2b6e92f/?conf=cvpr2021
【1】Style-based Point Generator with Adversarial Rendering for Point Cloud Completion(基于样式的点生成器与对抗式渲染的点云完成)
论文链接:https://www.aminer.cn/pub/6040b8fd91e011a0653f07df/?conf=cvpr2021
【2】PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Paths(PMP-Net:通过学习多步点移动路径完成点云计算)
论文链接:https://www.aminer.cn/pub/5fcf615591e011f4c80badad/?conf=cvpr2021
【3】Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding(Cycle4Completion: 使用缺失区域编码的周期转换进行未配对的点云补全)
论文链接:https://www.aminer.cn/pub/605082cb91e0111e1cd46a8d/?conf=cvpr2021
【4】Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges(城市尺度三维点云的语义分割:数据集、基准和挑战)
论文链接:https://www.aminer.cn/pub/5f57664991e011f4c3d5dce1/?conf=cvpr2021
【5】SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration(SpinNet: 为3D点云注册学习一个通用表面描述符)
论文链接:https://www.aminer.cn/pub/5fbe707091e011e6e11b3e75?conf=cvpr2021
【6】MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization(MultiBodySync: 通过3D扫描同步进行多体分割和运动估计)
论文链接:https://www.aminer.cn/pub/6006b19891e0111a1b6a227f?conf=cvpr2021
【7】Diffusion Probabilistic Models for 3D Point Cloud Generation(三维点云生成的扩散概率模型)
论文链接:https://www.aminer.cn/pub/603f689d91e011cacfbda368?conf=cvpr2021
AMiner,一个具有认知智能的学术搜索引擎:https://www.aminer.cn/
#AMiner# #论文#