Contents

• Computer Vision
  • Classification
  • Object Detection
  • Segmentation
  • Generative Models
  • Face Recognition
  • Temporal Action Localization
  • Novel View Synthesis
• Natural Language Processing
  • Architecture
  • Parameter Efficient Fine-Tuning
• Vision-Language Models
• Speech Processing
  • Speech Synthesis
  • Voice Conversion
• Reinforcement Learning
• Explainable AI
• Adversarial Attack
• Self-Supervised Learning
• Miscellaneous
  • Recommendation Systems

Computer Vision

Classification

• LeNet-5(1998) [PDF/Code]

• AlexNet(2012) [PDF/Code]

• VGGNet(2014) [PDF/Code]

• GoogLeNet(2014) [PDF/Code]

• ResNet(2015) [PDF/Code]

• DenseNet(2017) [PDF/Code]

• MobileNetV1(2017) [PDF]

• MobileNetV2(2018) [PDF]

• MobileNetV3(2019) [PDF]

• EfficientNet(2019) [PDF/Code]

• Vision Transformer(2020) [PDF/Code]

• Swin Transformer(2021) [PDF/Code]

• EfficientNetV2(2021) [PDF/Code]

• CoAtNet(2021) [PDF/Code]

• Vision Mamba(2024) [PDF/Code]

Object Detection

• R-CNN(2013) [PDF/Code]

• SPPNet(2014) [PDF]

• Fast R-CNN(2014) [PDF/Code]

• Faster R-CNN(2015) [PDF]

• YOLOv1(2016) [PDF]

• SSD(2016) [PDF/Code]

• FPN(2017) [PDF/Code]

• YOLOv2(2017) [PDF]

• CornerNet(2019) [PDF]

• CenterNet(2019) [PDF]

• EfficientDet(2020) [PDF/Code]

• DETR(2020) [PDF/Code]

• Deformable DETR(2021) [PDF/Code]

• RT-DETR(2024) [PDF/Code]

Segmentation

• DeepLabV1(2014) [PDF/Code]

• FCN(2015) [PDF/Code]

• SegNet(2015) [PDF/Code]

• U-Net(2015) [PDF]

• DeepLabV2(2016) [PDF]

• DeepLabV3(2017) [PDF]

• Mask R-CNN(2017) [PDF]

• DeepLabV3+(2018) [PDF]

Generative Models

• VAE(2013) [PDF]

• GAN(2014) [PDF]

• CGAN(2014) [PDF]

• DCGAN(2015) [PDF]

• Pix2Pix(2016) [PDF]

• PGGAN(2017) [PDF]

• CycleGAN(2017) [PDF]

• SytleGAN(2014) [PDF]

• DDPM(2020) [PDF]

• DDIM(2020) [PDF]

Face Recognition

• DeepFace(2014) [PDF]

• FaceNet(2015) [PDF/Code]

• ArkFace(2018) [PDF]

Temporal Action Localization

• C3D(2015) [PDF]

• S-CNN(2016) [PDF]

• TAD(2017) [PDF]

• RTD-Net(2021) [PDF]

• E2E-TAD(2022) [PDF]

• TADTR(2022) [PDF]

• ReAct(2022) [PDF]

Novel View Synthesis

• NeRF(2020) [PDF]

Natural Language Processing

Architecture

• LSTM(1997) [PDF]

• Bi-LSTM(1997) [PDF]

• Seq2Seq(2014) [PDF]

• GRU(2014) [PDF]

• Attention(2014) [PDF]

• Transforemr(2017) [PDF]

• BERT(2018) [PDF]

• GPT(2018) [PDF]

• Mamba(2023) [PDF]

• Jamba(2024) [PDF/Code]

Parameter Efficient Fine-Tuning

• Adapter(2019) [PDF]

• Prefix-Tuning(2021) [PDF]

• LoRA(2021) [PDF]

• MAM Adapter(2022) [PDF/Code]

• QLoRA(2024) [PDF]

Vision-Language Models

• CLIP(2021) [PDF/Code]

• ALIGN(2021) [PDF]

• GLIP(2021) [PDF/Code]

• BLIP(2022) [PDF/Code]

• GLIPv2(2022) [PDF/Code]

Speech Processing

Speech Synthesis

• WaveNet(2016) [PDF]

• Tacotron(2017) [PDF]

• Tacotron2(2018) [PDF]

• FastSpeech(2019) [PDF]

• Transformer TTS(2019) [PDF]

• HiFi-GAN(2020) [PDF]

Voice Conversion

• AutoVC(2019) [PDF]

• DiffSVC(2021) [PDF]

Reinforcement Learning

• DQN(2013) [PDF]

Explainable AI

• LRP(2015) [PDF]

• CAM(2016) [PDF]

• Grad-CAM(2017) [PDF]

Adversarial Attack

• FGSM(2015) [PDF]

• CW Attack(2017) [PDF]

• PGD Training(2017) [PDF]

• Adversarial Patch(2018) [PDF]

• BPDA(2018) [PDF]

• Pixel DP(2019) [PDF/Code]

Self-Supervised Learning

• DeepCluster(2018) [PDF]

• NPID(2018) [PDF]

• SimCLR(2020) [PDF]

• MoCo(2020) [PDF]

• BYOL(2020) [PDF/Code]

• DINO(2021) [PDF/Code]

• MAE(2022) [PDF]

Miscellaneous

Recommendation Systems

• DNN for Youtube(2016) [PDF]