Receptive Fields: Why 3x3 conv layer is the best?

Autoregressive Image Generation without Vector Quantization

Diffusion Models (DDPM & DDIM) - Easily explained!

GLIGEN (CVPR2023): Open-Set Grounded Text-to-Image Generation

The Entropy Enigma: Success and Failure of Entropy Minimization

Tent: Fully Test-time Adaptation by Entropy Minimization

VPD (ICCV2023): Unleashing Text-to-Image Diffusion Models for Visual Perception

TokenHMR (CVPR2024): Advancing Human Mesh Recovery witha Tokenized Pose Representation

SHViT (CVPR2024): Single-Head Vision Transformer with Memory Efficient Macro Design

InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation

FastV: An Image is Worth 1/2 Tokens After Layer 2

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

PoseGPT (ChatPose): Chatting about 3D Human Pose

MotionAGFormer (WACV2024): Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network

HD-GCN (ICCV2023): Skeleton-Based Action Recognition

ST-GCN: Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition

Graph Convolutional Networks (GCN): From CNN point of view

DINO: Self-Supervised Vision Transformers

MoCo (+ v2): Unsupervised learning in computer vision

ViTPose: 2D Human Pose Estimation

TrackFormer: Multi-Object Tracking with Transformers

MetaFormer is Actually What You Need for Vision

ConvNet beats Vision Transformers (ConvNeXt) Paper explained

Swin Transformer V2 - Paper explained

Masked Autoencoders (MAE) Paper Explained