爱可可老师一周论文精选(2019.1.26)

No 1. 【让照片里的人物“走两步”:单张图片3D 角色动画合成】
No 2. 《Artificial Neural Networks》
No 3. 《A Survey of the Recent Architectures of Deep Convolutional Neural Networks》
No 4. 【深度卷积网络高效计算进展】
No 5. 《Attentive Neural Processes》
No 6. 【从图片到涂鸦:高品质涂鸦的自动生成(推断)】
No 7. 《Real-time Joint Object Detection and Semantic Segmentation Network for Automated Driving》
No 8. 《PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume》
No 9. 《CSGAN: Cyclic-Synthesized Generative Adversarial Networks for Image-to-Image Transformation》
No 10. 《Cross-lingual Language Model Pretraining》
No 11. 《Understanding Geometry of Encoder-Decoder CNNs》
No 12. 《Task representations in neural networks trained to perform many cognitive tasks | Nature Neuroscience》
No 13. 《Bayesian Learning of Neural Network Architectures》
No 14. 《AuxNet: Auxiliary tasks enhanced Semantic Segmentation for Automated Driving》
No 15. 《Passage Re-ranking with BERT》
No 16. 《Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors》
No 17. 《Good Similar Patches for Image Denoising》
No 18. 《Improved Selective Refinement Network for Face Detection》
No 19. 《A Performance Comparison of Loss Functions for Deep Face Recognition》
No 20. 《FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network》
No 21. 《Soft Rasterizer: Differentiable Rendering for Unsupervised Single-View Mesh Reconstruction》
No 22. 《A Random Walk Approach to First-Order Stochastic Convex Optimization》
No 23. 《Hierarchical Representations with Poincaré Variational Auto-Encoders》
No 24. 《Hierarchical Reinforcement Learning for Multi-agent MOBA Game》
No 25. 《Attention-aware Multi-stroke Style Transfer》
No 26. 《Consistent Optimization for Single-Shot Object Detection》
No 27. 《CT-GAN: Malicious Tampering of 3D Medical Imagery using Deep Learning》
No 28. 《DF-SLAM: A Deep-Learning Enhanced Visual SLAM System based on Deep Local Features》
No 29. 《WALL-E: An Efficient Reinforcement Learning Research Framework》
No 30. 《Understanding Multi-Step Deep Reinforcement Learning: A Systematic Study of the DQN Target》

发表评论

电子邮件地址不会被公开。 必填项已用*标注