[CVPR 2023] EfficientViT: Memory Efficient Vision Transformer With Cascaded Group Attention

EfficientViT Street Scene Segmentation Demo

AI model speeds up high-resolution computer vision | EfficientViT

[Ambient AI] Student Presentation - EfficientViT

GazeSAM Demo: Combining EfficientViT-SAM with Gaze Estimation

ViT论文逐段精读【论文精读】

Vision Transformers (ViT) Explained + Fine-tuning in Python

【学会聴講報告】CVPR2023からみるVision最先端トレンド

EfficientViT EfficientFormerV2 ICCV 2023

Momenta at CVPR 2023: How Data-Driven Flywheel Enables Scalable Path to Full Autonomy

Lecture 20 - Efficient Transformers | MIT 6.S965

EfficientML.ai Lecture 14 - Vision Transformer (MIT 6.5940, Fall 2023)

Discover the Hottest AI & LLM Projects: Unveiling Pykan, EfficientViT & More!

A ViT: Adaptive Tokens for Efficient Vision Transformer | CVPR 2022

TransVPR: Transformer Based Place Recognition With Multi Level Attention Aggregation | CVPR 2022

Neural Video Depth Stabilizer (Accepted by ICCV 2023)

Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment (CVPR'2023)

GenAI on the Edge Forum - Song Han: Visual Language Models for Edge AI 2.0

FasterViT: Fast Vision Transformers with Hierarchical Attention

[ICCV 2023] TextPSG: Panoptic Scene Graph Generation from Textual Descriptions