This model is a fine-tuned version of the Inflated 3D Convnet model for action recognition, trained on the Kinetics-400 dataset.
The I3D (Inflated 3D Convnet) model is designed for video classification tasks. It extends 2D convolutions to 3D, enabling the model to capture spatiotemporal features from video frames.
The model can be used for action recognition in videos. It is particularly suited for tasks involving the classification of human activities.
The model was fine-tuned on the UCF101 dataset, which consists of 13,320 videos belonging to 101 action categories.
The model achieves an accuracy of 90% and a top-5 accuracy of 95% on the UCF101 test set.
1from transformers import pipeline
2
3model = pipeline("video-classification", model="Mouwiya/i3d-kinetics-400")
4
5# Example video path
6video_path = "path_to_your_video.mp4"
7
8# Perform video classification
9results = model(video_path)
10print(results)
