Timesformer Hr Finetuned K400
TimeSformer is a video understanding model based on spatio-temporal attention mechanisms, pre-trained and fine-tuned on the Kinetics-400 dataset.
Downloads 178
Release Time : 10/7/2022
Model Overview
This model is primarily used for video classification tasks, capable of classifying videos into one of 400 possible Kinetics-400 labels.
Model Features
Spatio-Temporal Attention Mechanism
Uses pure attention mechanisms to process spatial and temporal information in videos without convolutional operations.
High-Resolution Processing Capability
This variant supports high-resolution video input, enabling the capture of finer visual features.
Large-Scale Pre-Training
Pre-trained on the large-scale Kinetics-400 video dataset, offering strong generalization capabilities.
Model Capabilities
Video Classification
Action Recognition
Video Content Analysis
Use Cases
Video Content Understanding
Action Recognition
Identify human actions and behaviors in videos
Can recognize 400 different action categories
Video Classification
Classify and label video content
Featured Recommended AI Models
Š 2025AIbase