yiskw713/paper_summary

Issues

• Fastformer: Additive Attention Can Be All You Need

  #175 opened 3 years ago by yiskw713
  0

• Supervised Contrastive Learning

  #174 opened 3 years ago by yiskw713
  0

• You Only Look One-level Feature

  #173 opened 3 years ago by yiskw713
  0

• Jigsaw Clustering for Unsupervised Visual Representation Learning

  #172 opened 3 years ago by yiskw713
  0

• Self-supervised Motion Learning from Static Images

  #170 opened 3 years ago by yiskw713
  0

• Bootstrap your own latent: A new approach to self-supervised Learning

  #171 opened 3 years ago by yiskw713
  0

• q-SNE: Visualizing Data using q-Gaussian Distributed Stochastic Neighbor Embedding

  #169 opened 3 years ago by yiskw713
  0

• Differentiable Patch Selection for Image Recognition

  #168 opened 3 years ago by yiskw713
  0

• Adversarial Synthesis of Human Pose from Text

  #139 opened 5 years ago by yiskw713
  0

• Is 2D Heatmap Representation Even Necessary for Human Pose Estimation?

  #167 opened 3 years ago by yiskw713
  0

• Learning to Resize Images for Computer Vision Tasks

  #166 opened 4 years ago by yiskw713
  0

• ParseNet: Looking Wider to See Better

  #165 opened 4 years ago by yiskw713
  0

• MLP-Mixer: An all-MLP Architecture for Vision

  #164 opened 4 years ago by yiskw713
  0

• Pay Attention to MLPs

  #163 opened 4 years ago by yiskw713
  0

• Attentive Action and Context Factorization

  #162 opened 4 years ago by yiskw713
  0

• Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias

  #160 opened 4 years ago by yiskw713
  0

• Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning

  #158 opened 4 years ago by yiskw713
  0

• Pulling Actions out of Context: Explicit Separation for Effective Combination

  #159 opened 4 years ago by yiskw713
  0

• Video Super-resolution with Temporal Group Attention

  #157 opened 4 years ago by yiskw713
  0

• Flow2Stereo: Effective Self-Supervised Learning of Optical Flow and Stereo Matching

  #156 opened 4 years ago by yiskw713
  0

• Single-Stage Semantic Segmentation from Image Labels

  #155 opened 4 years ago by yiskw713
  0

• Improving Action Segmentation via Graph Based Temporal Reasoning

  #154 opened 5 years ago by yiskw713
  0

• Hidden Two-Stream Convolutional Networks for Action Recognition

  #152 opened 5 years ago by yiskw713
  0

• Adversarial Discriminative Attention for Robust Anomaly Detection

  #153 opened 5 years ago by yiskw713
  0

• ActionFlowNet: Learning Motion Representation for Action Recognition

  #151 opened 5 years ago by yiskw713
  0

• FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

  #150 opened 5 years ago by yiskw713
  0

• FlowNet: Learning Optical Flow with Convolutional Networks

  #149 opened 5 years ago by yiskw713
  0

• Interpolation Consistency Training for Semi-Supervised Learning

  #148 opened 5 years ago by yiskw713
  0

• MixMatch: A Holistic Approach to Semi-Supervised Learning

  #147 opened 5 years ago by yiskw713
  0

• Deep Networks with Stochastic Depth

  #146 opened 5 years ago by yiskw713
  0

• Self-training with Noisy Student improves ImageNet classification

  #145 opened 5 years ago by yiskw713
  0

• RandAugment: Practical automated data augmentation with a reduced search space

  #144 opened 5 years ago by yiskw713
  0

• AutoAugment: Learning Augmentation Policies from Data

  #143 opened 5 years ago by yiskw713
  0

• mixup: Beyond Empirical Risk Minimization

  #142 opened 5 years ago by yiskw713
  0

• CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features

  #141 opened 5 years ago by yiskw713
  0

• Improved Regularization of Convolutional Neural Networks with Cutout

  #140 opened 5 years ago by yiskw713
  0

• MirrorGAN: Learning Text-to-image Generation by Redescription

  #138 opened 5 years ago by yiskw713
  0

• Anomaly Detection in Video Sequence with Appearance-Motion Correspondence

  #137 opened 5 years ago by yiskw713
  0

• Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs

  #136 opened 5 years ago by yiskw713
  0

• Ablation-CAM: Visual Explanations for Deep Convolutional Network via Gradient-free Localization

  #135 opened 5 years ago by yiskw713
  0

• Temporal Interlacing Network

  #134 opened 5 years ago by yiskw713
  0

• RESOUND: Towards Action Recognition without Representation Bias

  #131 opened 5 years ago by yiskw713
  0

• REPAIR: Removing Representation Bias by Dataset Resampling

  #133 opened 5 years ago by yiskw713
  0

• X3D: Expanding Architectures for Efficient Video Recognition

  #132 opened 5 years ago by yiskw713
  0

• Why Can’t I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition

  #130 opened 5 years ago by yiskw713
  0

• Temporal Segment Networks: Towards Good Practices for Deep Action Recognition

  #129 opened 5 years ago by yiskw713
  0

• Temporally Grounding Language Queries in Videos by Contextual Boundary-aware Prediction

  #128 opened 5 years ago by yiskw713
  0

• Unsupervised Deep Metric Learning via Auxiliary Rotation Loss

  #127 opened 5 years ago by yiskw713
  0

• Deep Unsupervised Similarity Learning using Partially Ordered Sets

  #126 opened 5 years ago by yiskw713
  0

• MIC: Mining Interclass Characteristics for Improved Metric Learning

  #125 opened 5 years ago by yiskw713
  0