CVPR2020 Pre-Conference Australia, June 7

Due to the extension of NeurlPS DDL , we change the Pre-conference date from June 6 to June 7.

Thanks for your understanding!

  • 09:00-09:10, Opening remarks and welcome

Neural Network Architecture

  • 09:10-09:30, Multi-Dimensional Pruning: A Unified Framework for Model Compression, Jinyang Guo

  • 09:30-09:50, Anisotropic Convolutional Networks for 3D Semantic Scene Completion, Peng Wang

  • 09:50-10:05, EcoNAS: Finding Proxies for Economical Neural Architecture Search, Dongzhan Zhou

  • 10:05-10:20, Memory-Efficient Hierarchical Neural Architecture Search for Image Denoising, Haokui Zhang

  • 10:20-10:35, Overcoming Multi-Model Forgetting in One-Shot NAS with Diversity Maximization, Miao Zhang

  • 10:35-10:50, Gated Channel Transformation for Visual Recognition, Zongxin Yang

  • 10:50-11:10, Break

Pattern Recognition

  • 11:10-11:30, Adaptive Subspaces for Few-Shot Learning, Piotr Koniusz

  • 11:30-11:50, Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition, Ziyu Liu

  • 11:50-12:05, Context Aware Graph Convolution for Skeleton-Based Action Recognition, Xikun Zhang

  • 12:05-12:20, Cops-Ref: A new Dataset and Task on Compositional Referring Expression Comprehension, Peng Wang

  • 12:20-12:35, On Positive-Unlabeled Classification in GAN, Tianyu Guo

  • 12:35-14:00, Break

Vision-Language

  • 14:00-14:20, ActBERT: Learning Global-Local Video-Text Representations , Linchao Zhu

  • 14:20-14:40, ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network, Yuliang Liu

  • 14:40-14:55, Vision-Language Navigation with Self-Supervised Auxiliary Tasks, Fengda Zhu

  • 14:55-15:10, Transferring Cross-domain Knowledge for Video Sign Language Recognition, Dongxu Li

  • 15:10-15:25, On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering, Xinyu Wang

  • 15:25-15:40, Break

Segmentation

  • 15:40-16:00, Interactive Object Segmentation with Inside-Outside Guidance , Yunchao Wei

  • 16:00-16:20, BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation, Hao Chen

  • 16:20-16:35, Memory Aggregation Networks for Efficient Interactive Video Object Segmentation, Jiaxu Miao

  • 16:35-16:50, Learning to Structure an Image with Few Colors, Yunzhong Hou

  • 16:50-17:05, Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondences, Xiaoshui Huang

  • 17:05-17:20, Weakly supervised saliency detection with scribble annotation, Jing Zhang

  • 17:20-17:30, Closing remarks