dreamer-cpu,github

-

action-recognition-in-still-images

Here I show how to recognize actions in still images well using Transfer Learning and Attention Mechanism

action-recognition-in-still-images-using-visual-scanpaths

Proposed an LSTM based context module that can learn the sequence of object proposals. A sequencer algorithm reorders the object proposals in the sequence provided by human gaze behaviour and before feeding to the LSTM, positional encoding is concatenated with each instance appearance feature. Proposed model is a concatenation of the residual ne

ailearning

AiLearning: 机器学习 - MachineLearning - ML、深度学习 - DeepLearning - DL、自然语言处理 NLP

awesome-spider

爬虫集合

books

"我的阅历"

cnsurvey

一份中文综述文章列表（自然语言处理&机器学习）

coursera-ml-andrewng-notes

吴恩达老师的机器学习课程个人笔记

daily_fresh_demo

生鲜购物网站

deep_ensemble_learning

Deep Ensemble Learning for Human Action Recognition in Still Images

deeplearning-papernotes

Summaries and notes on Deep Learning research papers

deeplearning_ai

吴恩达深度学习作业

deeplearning_ai_books

deeplearning.ai（吴恩达老师的深度学习课程笔记及资源）

dive-into-dl-pytorch

本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。

human-action-classification-with-still-images-using-cnn

In recent years, one of the most difficult problems in computer vision has been automatic human action and activity recognition. It is critical in a variety of artificial intelligence applications, including video surveillance, computer games, robotics, and human-computer interactions. Research into intelligent surveillance has resulted from the gr

human-action-recognition

Human action recognition in photographs / still images

human-action-recognition-har-in-images-using-deep-cnn

Human action recognition (HAR) using still images. we have develop a deep convolutional neural network (CNN) to identify the actions of a person from still images. The actions we are interested in is categorised in to 21 types belonging to 5 classes.