T

Timesformer Hr Finetuned Ssv2

Developed by facebook
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.
Downloads 550
Release Time : 10/7/2022

Model Overview

This model is used for video classification tasks and can classify videos into one of 174 possible Something Something v2 labels.

Model Features

Spatio-Temporal Attention Mechanism
Uses pure attention mechanisms to process spatio-temporal information in videos, eliminating the need for convolutional operations.
High-Resolution Processing Capability
This variant supports higher-resolution video inputs (448x448).
Video Understanding Capability
Optimized specifically for video classification tasks, capable of understanding spatio-temporal relationships in videos.

Model Capabilities

Video Classification
Spatio-Temporal Feature Extraction
High-Resolution Video Processing

Use Cases

Video Understanding
Action Recognition
Recognize human actions and behaviors in videos.
Performs well on the Something Something v2 dataset.
Video Content Analysis
Analyze video content and automatically classify it.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase