YouTube-8M: датасет, это как ImagNet только для видео!
4800 классов и 8 миллионов видео
YouTube-8M is a large-scale labeled video dataset that consists of 8 million YouTube video IDs and associated labels from a diverse vocabulary of 4800 visual entities. It also comes with precomputed state-of-the-art vision features from billions of frames, which fit on a single hard disk. This makes it possible to train video models from hundreds of thousands of video hours in less than a day on 1 GPU!
https://research.google.com/youtube8m/
http://arxiv.org/pdf/1609.08675v1.pdf
#dataset
4800 классов и 8 миллионов видео
YouTube-8M is a large-scale labeled video dataset that consists of 8 million YouTube video IDs and associated labels from a diverse vocabulary of 4800 visual entities. It also comes with precomputed state-of-the-art vision features from billions of frames, which fit on a single hard disk. This makes it possible to train video models from hundreds of thousands of video hours in less than a day on 1 GPU!
https://research.google.com/youtube8m/
http://arxiv.org/pdf/1609.08675v1.pdf
#dataset
Large Scale Movie Denoscription and Understanding Challenge (LSMDC), at ECCV 2016
The challenge will be presented at the "Joint 2nd Workshop on Storytelling with Images and Videos (VisStory) and Large Scale Movie Denoscription and Understanding Challenge (LSMDC 2016)" in conjunction with ECCV 2016, Amsterdam, The Netherlands.
The challenge will be presented at the "Joint 2nd Workshop on Storytelling with Images and Videos (VisStory) and Large Scale Movie Denoscription and Understanding Challenge (LSMDC 2016)" in conjunction with ECCV 2016, Amsterdam, The Netherlands.
Презентации с ML/DL секции Russian Supercomputing Days:
технологические аспекты от Mikhail Burtsev и Dmitry Korobchenko + обзор инвестиционной среды от Russia.AI
http://www.russia.ai/single-post/2016/10/10/Deep-Learning-%E2%80%93-Present-and-Future-of-AI-Slides-from-Russian-Supercomputing-Days-Conference
технологические аспекты от Mikhail Burtsev и Dmitry Korobchenko + обзор инвестиционной среды от Russia.AI
http://www.russia.ai/single-post/2016/10/10/Deep-Learning-%E2%80%93-Present-and-Future-of-AI-Slides-from-Russian-Supercomputing-Days-Conference
Обзор курсов по Deep Learning
Последнее время все больше и больше достижений в области искусственного интеллекта связано с инструментами глубокого обучения или deep learning. Мы решили разобраться, где же можно научиться необходимым навыкам, чтобы стать специалистом в этой области.
Последнее время все больше и больше достижений в области искусственного интеллекта связано с инструментами глубокого обучения или deep learning. Мы решили разобраться, где же можно научиться необходимым навыкам, чтобы стать специалистом в этой области.
Clockwork Convnets for Video Semantic Segmentation.
Adaptive video processing by incorporating data-driven clocks.
We define a novel family of "clockwork" convnets driven by fixed or adaptive clock signals that schedule the processing of different layers at different update rates according to their semantic stability. We design a pipeline schedule to reduce latency for real-time recognition and a fixed-rate schedule to reduce overall computation. Finally, we extend clockwork scheduling to adaptive video processing by incorporating data-driven clocks that can be tuned on unlabeled video.
https://arxiv.org/pdf/1608.03609v1.pdf
https://github.com/shelhamer/clockwork-fcn
http://www.gitxiv.com/posts/89zR7ATtd729JEJAg/clockwork-convnets-for-video-semantic-segmentation
#Caffe #video #Segmentation
Adaptive video processing by incorporating data-driven clocks.
We define a novel family of "clockwork" convnets driven by fixed or adaptive clock signals that schedule the processing of different layers at different update rates according to their semantic stability. We design a pipeline schedule to reduce latency for real-time recognition and a fixed-rate schedule to reduce overall computation. Finally, we extend clockwork scheduling to adaptive video processing by incorporating data-driven clocks that can be tuned on unlabeled video.
https://arxiv.org/pdf/1608.03609v1.pdf
https://github.com/shelhamer/clockwork-fcn
http://www.gitxiv.com/posts/89zR7ATtd729JEJAg/clockwork-convnets-for-video-semantic-segmentation
#Caffe #video #Segmentation
Multifaceted Feature Visualization.
Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks.
We can better understand deep neural networks by identifying which features each of their neurons have learned to detect. Here, we introduce an algorithm that explicitly uncovers the multiple facets of each neuron by producing a synthetic visualization of each of the types of images that activate a neuron. We also introduce regularization methods that produce state-of-the-art results in terms of the interpretability of images obtained by activation maximization.
https://github.com/Evolving-AI-Lab/mfv
https://arxiv.org/pdf/1602.03616v2.pdf
http://www.gitxiv.com/posts/Kqy2rHju5EsqpC32N/multifaceted-feature-visualization
Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks.
We can better understand deep neural networks by identifying which features each of their neurons have learned to detect. Here, we introduce an algorithm that explicitly uncovers the multiple facets of each neuron by producing a synthetic visualization of each of the types of images that activate a neuron. We also introduce regularization methods that produce state-of-the-art results in terms of the interpretability of images obtained by activation maximization.
https://github.com/Evolving-AI-Lab/mfv
https://arxiv.org/pdf/1602.03616v2.pdf
http://www.gitxiv.com/posts/Kqy2rHju5EsqpC32N/multifaceted-feature-visualization
Запись и презентация с вводного вебинара по DeepLearning от Александра Гончар для студентов СФ БашГУ.
https://www.youtube.com/watch?v=8pbQ9Pve8bo
https://www.linkedin.com/in/alex-honchar-4423b962
https://www.youtube.com/watch?v=8pbQ9Pve8bo
https://www.linkedin.com/in/alex-honchar-4423b962