No 1. 《ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices》
https://arxiv.org/abs/1707.01083
No 2. 《Learning Macromanagement in StarCraft from Replays using Deep Learning》
https://arxiv.org/abs/1707.03743
No 3. 《Creatism: A deep-learning photographer capable of creating professional work》
https://arxiv.org/abs/1707.03491
https://google.github.io/creatism/
No 4. 【合成奥巴马：语音唇形同步学习】
http://grail.cs.washington.edu/projects/AudioToObama/
No 5. 《Revisiting Unreasonable Effectiveness of Data in Deep Learning Era》
https://arxiv.org/abs/1707.02968
No 6. 《Optimization Methods for Supervised Machine Learning: From Linear Models to Deep Learning》
https://arxiv.org/abs/1706.10207
No 7. 《SMC Faster R-CNN: Toward a scene-specialized multi-object detector》
https://arxiv.org/abs/1706.10217
No 8. 《Fast Algorithms for Learning Latent Variables in Graphical Models》
https://arxiv.org/abs/1706.08936
No 9. 《Text Summarization Techniques: A Brief Survey》
https://arxiv.org/abs/1707.02268
No 10. 《Dual Path Networks》
https://arxiv.org/abs/1707.01629
No 11. 《NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles》
https://arxiv.org/abs/1707.03501
No 12. 《A Brief Survey of Text Mining: Classification, Clustering and Extraction Techniques》
https://arxiv.org/abs/1707.02919
No 13. 《SCAN: Learning Abstract Hierarchical Compositional Visual Concepts》
https://arxiv.org/abs/1707.03389
No 14. 《Deep Semantic Segmentation for Automated Driving: Taxonomy, Roadmap and Challenges》
https://arxiv.org/abs/1707.02432
No 15. 《Learning Loss Functions for Semi-supervised Learning via Discriminative Adversarial Networks》
https://arxiv.org/abs/1707.02198
No 16. 《Robust Face Tracking using Multiple Appearance Models and Graph Relational Learning》
https://arxiv.org/abs/1706.09806
No 17. 《CNN features are also great at unsupervised classification》
https://arxiv.org/abs/1707.01700
No 18. 《Convolutional Sequence to Sequence Learning》
https://s3.amazonaws.com/fairseq/papers/convolutional-sequence-to-sequence-learning.pdf
https://arxiv.org/abs/1705.03122
No 19. 《Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs(DVN)》
https://arxiv.org/abs/1703.04363
https://gyglim.github.io/deep-value-net/
https://github.com/gyglim/dvn
No 20. 《Community Discovery in Dynamic Networks: a Survey》
https://arxiv.org/abs/1707.03186
编辑：黄继彦
公众号底部菜单有惊喜哦！
企业，个人加入组织请查看“联合会”
往期精彩内容请查看“号内搜”
加入志愿者或联系我们请查看“关于我们”
