Paper Review
  • Intro
  • Paper Review
    • [2022 Spring] Paper Review
      • Template
      • AS-GCN
      • DevNet
      • Latent ODEs
      • G-Meta
      • graph based 3d multi person pose estimation using multi view images
      • FaceSight
      • FNC
      • CITIES
      • LILAC
      • Unsupervised Detection of Adversarial Examples with Model Explanations
      • When Vision Transformers Outperform Resnets without Pre-training or Strong Data Augmentations
      • flan
      • Sequential GCN for AL
      • DNNGP
      • SBG(Successive Behavior Graph)
      • Self-sup-Multi-View
      • CCM
      • TesNet
      • GRAND
      • GDE
      • PAIRED
      • XGradient
      • Review paper COIN
      • Hypergraph with DHT
      • E(n) Equivariant Graph Neural Networks
      • DataAug
      • Learning_Large_Neighborhood_Search_Policy_for_Integer_Programming
      • LooC
      • ESAN
      • RobustSSL
      • SlotMachines
      • TimeSeriesConfounder
      • RGB-D
      • Meta-learning Sparse Implicit Neural Representations
      • NIWT
      • VGRNN
      • PGNN
      • OCGAN
      • Points as queries: Weakly semi-supervised object detection by points
      • RSPO
      • PUP(Price-aware User Preference-modeling)
      • Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-superv
      • GATv2
      • ER-GNN
      • Coteaching+
      • PA-GNN
      • PFGNN
      • Tail-Net
      • Handling Distribution Shifts on Graphs: An Invariance Perspective
      • 3D Molecule generative model for structure-based drug design
      • Structural-Deep-Clustering-Network
      • EGI
      • GMLPs
      • Are Transformers More Robust Than CNNs?
      • AugMix
      • GraphTrafficForecasting
      • ImageAgumentation
      • Neural JPEG
      • Conformal_Time Series_Forecasting
      • CAA
      • Overcoming Catastrophic Forgetting in Graph Neural Networks
      • CaDM
      • When Does Contrastive Visual Representation Learning Work?
      • MAD
      • MAPDP
      • Mixup-Inference
      • Finite_element_networks
      • Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation
      • EvolveGraph
      • CausalVAE
      • Motivating Physical Activity via Competitive Human-Robot Interaction
      • STGG
  • How to contribute
    • How to contribute?
    • Review Format
  • KAIST ISysE
Powered by GitBook
On this page
  • 1. Problem Definition
  • 2. Motivation
  • 3. Method
  • 4. Experiment
  • Experiment setup
  • Result
  • 5. Conclusion
  • Author Information
  • 6. Reference & Additional materials
  1. Paper Review
  2. [2022 Spring] Paper Review

Template

1st author / title / conference-year(description)

Title of paper that you are going to write

1. Problem Definition

Please write the problem definition on here

2. Motivation

Please write the motivation of paper. The paper would tackle the limitations or challenges in each fields.

After writing the motivation, please write the discriminative idea compared to existing works briefly.

3. Method

Please write the methodology author have proposed. We recommend you to provide example for understanding it more easily.

4. Experiment

In this section, please write the overall experiment results. At first, write experiment setup that should be composed of contents.

Experiment setup

  • Dataset

  • baseline

  • Evaluation Metric

Result

Then, show the experiment results which demonstrate the proposed method. You can attach the tables or figures, but you don't have to cover all the results.

5. Conclusion

Please summarize the paper. It is free to write all you want. e.g, your opinion, take home message(오늘의 교훈), key idea, and etc.


Author Information

  • Author name

    • Affiliation

    • Research Topic

6. Reference & Additional materials

Please write the reference. If paper provides the public code or other materials, refer them.

  • Github Implementation

  • Reference

Previous[2022 Spring] Paper ReviewNextAS-GCN

Last updated 2 years ago