Seminar

Every Wednesday

7 May 2019

• [shifan] Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem [code]

16 May 2019

• [tianxiaowei] Character Region Awareness for Text Detection

6 June 2019

• [shifan] Learning to Synthesize Motion Blur
• [tianxiaowei] Shape Robust Text Detection with Progressive Scale Expansion Network [code]

19 June 2019

• [liangdong] Unsupervised Part-Based Disentangling of Object Shape and Appearance

25 June 2019

• [liangdong] SFNet: Learning Object-aware Semantic Correspondence

10 July 2019

• [zoucong] Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition

15 July 2019

• [zoucong] Attention-based Dropout Layer for Weakly Supervised Object Localization (CVPR2019 Oral)
• [zoucong] Kervolutional Neural Networks (CVPR2019 Oral)
• [tongxuezhi] Simplifying Graph Convolutional Networks，ICML 2019
• [tongxuezhi] Learning Discrete Structures for Graph Neural Networks，ICML 2019

23 July (19 Aug) 2019

• [lvfeixiao] Transformation Networks for Target-Oriented Sentiment Classifcation (ACL 2018)

22 Aug 2019

• [qijunkun] Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations (ICML 2019)
• [qijunkun] The Contextual Loss for Image Transformation with Non-aligned Data (ECCV 2018)

11 Sep 2019

• [shifan] Onion-Peel Networks for Deep Video Completion
• [shifan] Self-supervised Spatiotemporal Learning via Video Clip Order Prediction

30 Oct 2019

• [liangdong] Spectrally-normalized margin bounds for neural networks (NIPS 2017)
• [liangdong] Generalization Bounds for Neural Networks via Approximate Description Length (NIPS 2019)

6 Nov 2019

• [zoucong] Selective Sparse Sampling for Fine-grained Image Recognition
• [zoucong] Learning a Mixture of Granularity-Specific Experts for Fine-Grained
• [zoucong] Categorization Cross-X Learning for Fine-Grained Visual Categorization

20 Nov 2019

• [qijunkun] Improved precision and recall metric for assessing generative models (NeurIPS19)
• [qijunkun] Image-to-image translation via group-wise deep whitening-and-coloring transformation (CVPR19)
• [qijunkun] Multi-mapping image-to-image translation via learning disentanglement (NeurIPS19)

27 Nov 2019

• [lvfeixiao] Editing Text in the Wild
• [lvfeixiao] What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis