# Video Action Recognition

This model is a fine-tuned version based on MCG-NJU/videomae-base-finetuned-kinetics, primarily used for video understanding tasks, achieving an accuracy of 91.38% on the evaluation set.

A video understanding model fine-tuned based on MCG-NJU/videomae-base-finetuned-kinetics, achieving 91.23% accuracy on the evaluation set

Video classification model fine-tuned on a subset of UCF101 based on the VideoMAE base model

A video action recognition model based on the VideoMAE architecture, fine-tuned on the Kinetics dataset with an accuracy of 92.25%

A video understanding model fine-tuned based on MCG-NJU/videomae-base-finetuned-kinetics, achieving an accuracy of 90.97% on the evaluation set

A video understanding model fine-tuned on a subset of the UCF101 action recognition dataset based on the VideoMAE base model

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

TimeSformer-HR is a high-resolution spatiotemporal Transformer model for video, fine-tuned on the Kinetics-400 dataset, suitable for video action recognition tasks.

TimeSformer is a Transformer-based video understanding model specifically optimized for temporal action recognition tasks.

TimeSformer is a video understanding model based on the Transformer architecture, specifically designed for video classification tasks.

TimeSformer is a Transformer-based video understanding model, specifically fine-tuned on the Kinetics-400 dataset.

A video action recognition model based on the ViViT architecture, fine-tuned specifically for CCTV surveillance scenarios, excelling in action recognition tasks.

A video classification model based on the VideoMAE architecture, fine-tuned specifically for shoplifting behavior detection

A video action recognition model based on the VideoMAE architecture, specifically fine-tuned for fall detection tasks

TimeSformer is a video understanding model based on spatial-temporal attention mechanism, fine-tuned on the Kinetics-400 dataset, suitable for video classification tasks.

This model is a video classification model fine-tuned based on facebook/timesformer-base-finetuned-k400, achieving an accuracy of 96.25% on the evaluation set.

A video action recognition model based on TimeSformer architecture, pre-trained on Kinetics-400 dataset and fine-tuned on UCF101 dataset

A video classification model based on the TimeSformer architecture, pre-trained on the Kinetics-400 dataset and fine-tuned on the UCF101 dataset, utilizing LoRA technology for continual learning.

A video action recognition model based on TimeSformer architecture, pre-trained on Kinetics-400 dataset and fine-tuned for Olympic sports subset

VideoMAE is a self-supervised pretrained video model based on Masked Autoencoder (MAE), fine-tuned on the Something-Something V2 dataset for video classification tasks.

A video classification model fine-tuned on a subset of UCF101 based on the VideoMAE base model

A video understanding model fine-tuned on a subset of UCF101 based on the VideoMAE base model, achieving 95.71% accuracy

A video classification model fine-tuned on a subset of UCF101 based on the VideoMAE base model, achieving 95.22% accuracy

Video action recognition model based on VideoMAE architecture, pre-trained on SSv2 dataset and further fine-tuned on RWF-2000 dataset

A video understanding model based on the VideoMAE architecture, fine-tuned on the RWF-2000 dataset for violence detection tasks

TimeSformer is a video classification model based on spatio-temporal attention mechanism, specifically designed for video understanding tasks.

TimeSformer is a video classification model based on spatio-temporal attention mechanism, specifically fine-tuned for the Kinetics-400 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.

Video action recognition model fine-tuned on UCF101 dataset based on VideoMAE Base model

Video classification model based on VideoMAE architecture, fine-tuned on a subset of UCF101 with an accuracy of 85.16%

TimeSformer is a video classification model based on spatio-temporal attention mechanisms, specifically designed for video understanding tasks.