学习和了解更多
人工智能,数据分析,机器学习,深度学习
相关知识和资讯

我要一步一步往上爬,在最高点乘着叶片往前飞...

极简教程

简单点,说话的方式简单点...

scikit-learn极简教程

作为Python语言下免费机器学习库,简单易学,文档完整,scikit-learn是许多同学入门的首选。

TensorFlow极简教程

TensorFlow是由谷歌开发和维护数据流编程系统,在机器学习领域被广泛应用。

PyTorch极简教程

PyTorch是由Facebook开发并维护的开源的Python机器学习库。

相关公司

开放数据

NLPCC数据集

The Conference on Natural Language Processing and Chinese Computing,会议提供了不同task的各个领域的数据集

ReferItGame

ReferItGame数据集包含 130,525 个表达式,用于引用 19,894 个自然场景图像中的 96,654 个对象。

LFW (Labeled Faces in the Wild)

LFW数据集包含了从网络上收集的13233张人脸图像。这个数据集包含了5749个身份和1680个拥有两个或更多图像的人。在标准的LFW评估协议中,验证精度报告在6000对脸。

Visual Question Answering (VQA)

视觉问答 (VQA)是一个包含关于图像的开放式问题的数据集。这些问题需要对视觉、语言和常识知识的理解才能回答。数据集的第一个版本于 2015 年 10 月发布。VQA v2.0于 2017 年 4 月发布。

UCF101

UCF101数据集是UCF50的扩展,由13,320个视频片段组成,分为101个类别。这101个类别可以分为5种类型(身体运动,人与人的互动,人与物的互动,演奏乐器和运动)。这些视频剪辑的总长度超过27小时。所有视频均来自YouTube,固定帧率为25fps,分辨率为320x240。

SQuAD

SQuAD 是斯坦福大学于2016年推出的数据集,一个阅读理解数据集,给定一篇文章,准备相应问题,需要算法给出问题的答案。此数据集所有文章选自维基百科,数据集的量为当今其他数据集(例如,WikiQA)的几十倍之多。一共有107,785问题,以及配套的 536 篇文章。

Natural Quetions

[Google 发布](https://ai.googleblog.com/2019/01/natural-questions-new-corpus-and.html)用于训练和评估开放领域(Open-domain)问答系统的大型[语料库](https://so.csdn.net/so/search?q=语料库&spm=1001.2101.3001.7020) Natural Questions(NQ)。该数据集包含了 30 万个自然产生的问题和对应的回答注释,每个回答都是人工从维基百科页面找到

Open Images

谷歌于2016年推出了Open Images,约900万张图像的协作版本,注释了数千个对象类别的标签。到了2018年,已更新到了Open Images V4,该版本总共包含了1540万个用于600个对象类别的边界框,使其成为拥有对象位置注释和30万多个可视关系注释的最大数据集。

ShapeNet

ShapeNet建立一个丰富的注释,大规模的3D形状数据集。为世界各地的研究人员提供这些数据,以支持计算机图形学、计算机视觉、机器人和其他相关学科的研究。

Charades

Charades数据集是为了对日常任务进行独特的洞察而收集的,比如喝咖啡,坐在椅子上穿鞋,或者依偎在沙发上的毯子上看着笔记本电脑上的东西。这使得计算机视觉算法能够从我们日常动态场景的真实和多样化的例子中学习。

View more

工具箱

云平台

相关论文

CoRGi: Content-Rich Graph Neural Networks with Attention

Kim J , Lamb A , Woodhead S , et al. CoRGi: Content-Rich Graph Neural Networks with Attention[J]. 2021.

Rumor Detection on Twitter with Claim-Guided Hierarchical Graph Attention Networks

H Lin, Ma J , Cheng M , et al. Rumor Detection on Twitter with Claim-Guided Hierarchical Graph Attention Networks[J]. 2021.

Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach

Wu Q , Yang C , Yan J . Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach[J]. 2021.

SGMNet: Scene Graph Matching Network for Few-Shot Remote Sensing Scene Classification

Zhang B , Feng S , Li X , et al. SGMNet: Scene Graph Matching Network for Few-Shot Remote Sensing Scene Classification[J]. 2021.

DeepABM: Scalable, efficient and differentiable agent-based simulations via graph neural networks

Chopra A , Gel E , Subramanian J , et al. DeepABM: Scalable, efficient and differentiable agent-based simulations via graph neural networks[J]. 2021.

An Efficient Machine Reading Comprehension Method Based on Attention Mechanism

Jin W , Yang G , Zhu H . An Efficient Machine Reading Comprehension Method Based on Attention Mechanism[C]// 2019 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communication

Knowledge-Based Method for Revising Misclassification on Learners’ Comprehension

Hiroshi, Murai. Knowledge-Based Method for Revising Misclassification on Learners' Comprehension[C]// 2017.

Superimposed Attention Mechanism-Based CNN Network for Reading Comprehension and Question Answering

Li M , Hou X , J Li, et al. Superimposed Attention Mechanism-Based CNN Network for Reading Comprehension and Question Answering[C]// 2019.

A Reading Comprehension Style Question Answering Model Based On Attention Mechanism

Xiao L , Wang N , Yang G . A Reading Comprehension Style Question Answering Model Based On Attention Mechanism[C]// 2018 IEEE 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP). IEEE, 2018.

Leveraging Knowledge Graph for Open-Domain Question Answering

Costa J O , Kulkarni A . Leveraging Knowledge Graph for Open-Domain Question Answering[C]// 2018 IEEE/WIC/ACM International Conference on Web Intelligence (WI). ACM, 2018.

Learning Multiple Layers of Features from Tiny Images

[R]. University of Toronto, 2009.

Image Captioning and Visual Question Answering Based on Attributes and External Knowledge

[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(6): 1367-1381.

Guiding the Long-Short Term Memory Model for Image Caption Generation

[C]. international conference on computer vision, 2015: 2407-2415.

Where to put the image in an image caption generator

[J]. Natural Language Engineering, 2018, 24(03): 467-489.

Rethinking the Inception Architecture for Computer Vision

[J]. computer vision and pattern recognition, 2016: 2818-2826.

ImageNet: A large-scale hierarchical image database

[C]. computer vision and pattern recognition, 2009: 248-255.

CIDEr: Consensus-based image description evaluation

[J]. computer vision and pattern recognition, 2015: 4566-4575.

METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments

[C]. meeting of the association for computational linguistics, 2005: 65-72.

ROUGE: A Package for Automatic Evaluation of Summaries

[C]. meeting of the association for computational linguistics, 2004: 74-81.

Bleu: a method for automatic evaluation of machine translation

[C]//Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 2002: 311-318.

View more

常用类目

我们致力于提供更丰富的学习笔记、行业信息、平台服务等内容,帮助更多的朋友,快速进入相关领域。