- Large-scale weakly-supervised pre-training for video action recognition(01/16/2020)
- HVU-Large Scale Holistic Video Understanding (The complete HVU dataset is not available yet)(03/18/2020)
- Online Model Distillation for Efficient Video Inference (Long Video Streams (LVS) Dataset) (03/18/2020)
- A Multigrid Method for Efficiently Training Video Models (03/19/2020)
- DeepVoxels: Learning Persistent 3D Feature Embeddings (03/22/2020)
- Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations (03/23/2020)
- Unsupervised Learning of Visual Representations using Videos (03/27/2020)
- Transitive Invariance for Self-supervised Visual Representation Learning (03/27/2020)
- SynSin: End-to-end View Synthesis from a Single Image (03/26/2020)
- A Theoretical Analysis of Contrastive Unsupervised Representation Learning
- Learning Features by Watching Objects Move [project page] (04/14/2020)
- 3D Photography using Context-aware Layered Depth Inpainting [project page] (04/15/2020)
- Contrastive Learning of Structured World Models (04/15/2020)
- HoloGAN: Unsupervised Learning of 3D Representations From Natural Images (04/15/2020)
- Monocular Neural Image Based Rendering with Continuous View Control (04/16/2020)
- On the Importance of Views in Unsupervised Representation Learning (04/25/2020)
- Supervised Contrastive Learning (04/29/2020)
- Audio-Visual Instance Discrimination with Cross-Modal Agreement (05/07/2020)
- Contrastive Learning of Structured World Models (05/15/2020)
- Object detectors emerge in deep scene CNNs, by Bolei Zhou et al.
- Understanding Black-box Predictions via Influence Functions, by Pang Wei Koh, Percy Liang
- Interpretation of Neural Networks is Fragile, by James Zou et al.
- Computational Models of Human Object and Scene Recognition, by Aude Oliva(03/14/2020)
- The functional architecture of the ventral temporal cortex and its role in categorization, by Kalanit Grill-Spector and Kevin S. Weiner(03/15/2020)
- Computational mechanisms underlying cortical responses to the affordance properties of visual scenes, by Michael F. Bonner and Russell A. Epstein
- Dynamics of scene representations in the human brain revealed by magnetoencephalography and deep neural networks, by Radoslaw Martin Cichy et al.
- Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence, by Radoslaw Martin Cichy et al.