Papers и статьи challenge

2019-04-15 16:34:08 Hello, everyone!

Hope you will like them!

https://arxiv.org/abs/1811.11080 (MobiFace: A Lightweight Deep Learning Face Recognition on Mobile Devices) #cnn #facerecognition #mobiledevices #computervison
https://arxiv.org/abs/1804.06655 (Deep Face Recognition: A Survey) #cnn #facerecognition #mobiledevices #computervison
https://arxiv.org/pdf/1902.03264.pdf (FSNet: Compression of Deep Convolutional Neural Networks by Filter Summary) #cnn #compression
https://arxiv.org/abs/1812.01187 (Bag of Tricks for Image Classification with Convolutional Neural Networks) #classification #cnn #computervison
https://arxiv.org/abs/1808.00158 (Speaker Recognition from Raw Waveform with SincNet) #voicerecognition #speech #cnn Open / Comment

2019-03-18 12:31:13 Bonjour, everyone! A few interesting articles for this week:

https://arxiv.org/abs/1903.00027 (Catalyst.RL: A Distributed Framework for Reproducible RL Research) #rl #reinforcedlearning
https://arxiv.org/abs/1806.01261 (Relational inductive biases, deep learning, and graph networks) #graphnetrwork #survey #bigwork
http://arxiv.org/abs/1903.05766 (Simulating Emergent Properties of Human Driving Behavior Using Multi-Agent Reward Augmented Imitation Learning) #rl #reinforcedlearning
https://arxiv.org/abs/1810.08559 (EdgeSpeechNets: Highly Efficient Deep Neural Networks for Speech Recognition on the Edge) #speechrecognition #cnn
https://arxiv.org/abs/1812.11894 (Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks) #cnn #ocr #fast Open / Comment

2019-03-04 13:57:28 Hello everyone! I was lost for a couple of months, but hope you will enjoy these papers:
#backinbuisness
https://arxiv.org/abs/1901.00596 (A Comprehensive Survey on Graph Neural Networks)
https://ieeexplore.ieee.org/document/8206316 (Lane-change social behavior generator for autonomous driving car by non-parametric regression in Reproducing Kernel Hilbert Space) #ReinforcementLearning
https://arxiv.org/abs/1803.10056 (Automated Speed and Lane Change Decision Making using Deep Reinforcement Learning) #ReinforcementLearning
https://arxiv.org/abs/1902.06838 (SC-FEGAN: Face Editing Generative Adversarial Network with User's Sketch and Color) #CNN #GAN
https://www.nature.com/articles/s41598-018-37359-z (Towards reconstructing intelligible speech from the human auditory cortex) #EGG #reconstruction #speechrecognition Open / Comment

2018-12-03 16:41:10 Hey! Happy winter, hope you all doing good! As usual, 3 of 5 :)

https://arxiv.org/abs/1801.06146 (Universal Language Model Fine-tuning for Text Classification) #nlp #texts
https://arxiv.org/abs/1802.00420 (Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples) #AdversarialAttack #Advirsarial #optimization
https://arxiv.org/abs/1803.01271 (An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling) #rnn #cnn #nerualnets
https://arxiv.org/abs/1804.08328 (Taskonomy: Disentangling Task Transfer Learning) #nerualnets #computervision #cnn
https://sacmehta.github.io/ESPNet/ (ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation) #cnn #gan #cnn Open / Comment

2018-11-27 17:20:47 Hello!

I've been running around. Choose at least 3 from:
https://github.com/shaohua0116/ICLR2019-OpenReviewData #conference #iclr

Almost Winter, yay! Have a good week :) Open / Comment

2018-11-19 20:47:58 Hello, have a good week!

At least two of five.
https://arxiv.org/abs/1811.00002 (WaveGlow: A Flow-based Generative Network for Speech Synthesis) #texttospeech #tts #nlp
https://arxiv.org/abs/1810.12890 (DropBlock: A regularization method for convolutional networks) #optimization #statistics
https://arxiv.org/abs/1808.07233 (Neural Architecture Optimization) #architecturesearch #cnn
https://arxiv.org/abs/1809.08809 (MobileFace: 3D Face Reconstruction with Efficient CNN Regression) #cnn #3d
https://arxiv.org/abs/1809.10394 (A parameter estimator based on Smoluchowski-Kramers approximation) #bruteforce #optimization Open / Comment

2018-11-12 15:44:16 Hello!
Back to the business! At least two of five.

https://arxiv.org/abs/1802.03620 (Optimal approximation of continuous functions by very deep ReLU networks∗) #optimization

https://arxiv.org/abs/1804.03160 (The Sound of Pixels) #computervision

https://arxiv.org/abs/1811.02155 (FloWaveNet : A Generative Flow for Raw Audio) #texttospeech #tts #nlp

https://arxiv.org/abs/1808.01244 (CornerNet: Detecting Objects as Paired Keypoints) #cnn #objectdetection #computervision

https://arxiv.org/abs/1709.02371 (PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume) #cnn #computervision Open / Comment

2018-11-06 13:14:22 Hello!

We will take a pause this week :) And I want to ask you some questions. It will be quick, please, fill this form:

https://goo.gl/forms/IDcsi9iA7GH7P0em1

Thanks in advance! Open / Comment

2018-10-29 20:37:15 Hello everyone!
A new bunch of papers, wish you a good week! At least 1 (end of the month) of 5.

https://arxiv.org/abs/1810.05424 (Real-time self-adaptive deep stereo)
https://arxiv.org/abs/1809.11096 (Large Scale GAN Training for High Fidelity Natural Image Synthesis)
http://proceedings.mlr.press/v80/athalye18a.html (Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples)
https://arxiv.org/abs/1810.05148 (Bayesian Convolutional Neural Networks with Many Channels are Gaussian Processes)
https://blog.prismalabs.ai/real-time-portrait-segmentation-on-smartphones-39c84f1b9e66 (Real-time Portrait Segmentation on Smartphones) Open / Comment

2018-10-22 22:33:47 Hello!

Have a nice week. Today I publish papers a bit late, but some of them are incredible, hope you will like it!

As usual, 3 of 5 are obligated.

https://arxiv.org/abs/1810.08575 (Supervising strong learners by amplifying weak experts)
https://arxiv.org/abs/1810.04937 (Location Dependency in Video Prediction)
https://devblogs.nvidia.com/mixed-precision-nlp-speech-openseq2seq/ (Mixed Precision Training for NLP and Speech Recognition with OpenSeq2Seq)
https://arxiv.org/abs/1710.10916 (StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks)
https://arxiv.org/abs/1809.10644 (Predictive Embeddings for Hate Speech Detection on Twitter) Open / Comment