# High-Resolution Processing

C-RADIOv2 is a visual feature extraction model developed by NVIDIA, offering multiple size versions suitable for image understanding and dense visual tasks.

Vision model based on SigLIP image encoder, employing global average pooling, part of the PaliGemma project

Mini-InternVL2-DA-RS is a multimodal model optimized for the remote sensing image domain, based on the Mini-InternVL architecture. It has been fine-tuned through a domain adaptation framework and demonstrates excellent performance in remote sensing image understanding tasks.

TimeSformer-HR is a video action recognition model optimized for high-resolution videos and fine-tuned on the Kinetics-600 dataset.

A visual feature extraction model developed by NVIDIA for generating image embeddings, supporting downstream tasks such as image classification.

Aesthetic Shadow is a Vision Transformer model with 1.1 billion parameters, specifically designed for evaluating anime image quality.

A satellite image segmentation model based on the SegFormer architecture, specifically designed for urban area segmentation tasks

EfficientNet is a mobile-friendly pure convolutional model that uniformly scales depth/width/resolution dimensions through compound coefficients, trained on the ImageNet-1k dataset.

TimeSformer is a video classification model based on spatio-temporal attention mechanism, fine-tuned on the Something Something v2 dataset.

TimeSformer is a video understanding model based on spatiotemporal attention mechanisms, with its high-resolution variant specifically fine-tuned for the Kinetics-600 dataset.

TimeSformer is a video understanding model based on spatio-temporal attention mechanisms. This version is a high-resolution variant fine-tuned on the Something Something v2 dataset.

TimeSformer is a video understanding model based on spatio-temporal attention mechanisms, pre-trained and fine-tuned on the Kinetics-400 dataset.

BEiT is a model based on the Vision Transformer (ViT) architecture, pre-trained on ImageNet-21k through self-supervised learning and fine-tuned on the ADE20k dataset, specifically designed for image semantic segmentation tasks.

SegFormer is a Transformer-based semantic segmentation model fine-tuned on the Cityscapes dataset, suitable for road scene segmentation tasks.