[1] Transformer is all you need: Awesome Visual-Transformer, BERT
[2] MLP is all you need: awesome-mlp-papers
[3] Vision Language Pre-training: awesome-pretrained-chinese-nlp-models, awesome-vision-language-pretraining-papers, awesome-programming-language-pretraining-papers, PyContrast, contrastive_learning_codes
[4] Video Inpainting: Awesome-Image-Inpainting
[1] Graph Neural Network: GNN, GNN, Graph Classification, Adversarial GNN, Deep GNN
[2] Video Analysis: Action Recognition, Temporal Action Detection, Temporal Action Localization
[3] Adversarial Attack: Adversarial Attack, Adversarial Learning, Robust ML, Graph Attack
[4] 3D Vision: Point Cloud, 3D Reconstruction
[5] AutoML: AutoML, Network Pruning, Network Compression, NAS
[6] Reinforcement Learning: RL, RL, Multiagent RL
[7] Transfer Learning: Transfer Learning, Zero Shot, Meta Learning
[8] GAN: GAN, GAN Applications
[9] Object Detection: Detection, Detection
[10] Object Tracking: Multiple Object Tracking, Tracking
[11] Pose Estimation: Human Pose Estimation, Hand Pose Estimation
[12] Segmentation: Semantic Segmentation
[13] Classification: Image Classification
[14] Vision-Language Navigation: Vision-Language Navigation, Self-Supervised Learning
[15] Super Resolution: Super Resolution
[16] Denoising: Image Denoising
[17] Anomaly Detection: Anomaly Detection
[18] Interpretability: Interpretability
[19] Trajectory Prediction: Trajectory-Prediction, Interaction Aware Trajectory Prediction
[20] OCR: image-text-localization-recognition, awesome-ocr
[21] Crowd Counting: Awesome-Crowd-Counting
[22] Video Analysis: Temporal Action Localization, Mulitple Object Tracking, Person ReID, Video Person ReID
[23] Visual Reasoning: Visual Reasoning
[24] Visual Grounding: Visual Grounding