papers | Deep Learning JP - Part 39

Decision Transformer: Reinforcement Learning via Sequence Modeling

Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron(ICML 2018)

RobustNet: Improving Domain Generalization in Urban- Scene Segmentation via Instance Selective Whitening

確率的推論と行動選択

Grasping Field: Learning Implicit Representations for Human Grasps

SiamMOT: Siamese Multi-Object Tracking

Fast and Slow Learning of Recurrent Independent Mechanisms

Are Pre-trained Convolutions Better than Pre-trained Transformers? (2021)

IMPROVING VOICE SEPARATION BY INCORPORATING END-TO-END SPEECH RECOGNITION

Pay Attention to MLPs （gMLP）

39 / 98« 先頭 «...10 20 30...37 383940 41...50 60 70...»最後 »