- [ICLR 2014] Network in Network
- [CVPR 2017] LCNN: Lookup-based Convolutional Neural Network
- [CVPR 2017] Top-down Visual Saliency Guided by Captions
- [CVPR 2016] Learning Deep Features for Discrminiative Localization
- [CVPR 2011] Iterative Quantization: A Procrustean Approach to Learning Binary Codes
- [CVPR 2017] Learning From Noisy Large-Scale Datasets With Minimal Supervision
- [ICCV 2016] Learning Deep Object Detectors from 3D Models
- [JMLR 2012] A Hybrid Neural Network-Latent Topic Model
- [ICML 2009] Online Dictionary Learning for Sparse Coding
- [JMLR 2008] Visualizing Data using t-SNE
- [arXiv 2017] VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
- [arXiv 2018] Completely Unsupervised Phoneme Recognition by Adversarially Learning Mapping Relationships from Audio Embeddings
- [arXiv 2018] ArcFace: Additive Angular Margin Loss for Deep Face Recognition
- [IVLR 2017] Neural Architecture Search with Reinforcement Learning