Deep-Feature-Flow
Deep Feature Flow for Video Recognition
About
Deep Feature Flow is a framework designed for video recognition, including tasks such as object detection and semantic segmentation. It utilizes a combination of heavy-weight image recognition networks on sparse key frames and a light-weight flow network to propagate recognition outputs across other frames. This end-to-end trained system is particularly effective for improving recognition accuracy and can leverage sparsely annotated video datasets.
Open Source Health
- Stars
- 1,314
- Forks
- 292
- License
- MIT
- Last commit
- 5 years ago
Resources & Links
Related Categories
Vendor
MSRA CVer
Computer vision fanatics from Microsoft Research Asia
Quick Links
Open Source
More by MSRA CVer
Related Products
MMAction
An open-source toolbox for action understanding based on PyTorch
Top category match
VideoPrism
Official repository for "VideoPrism: A Foundational Visual Encoder for Video Understanding" (ICML 2024)
Top category match
Temporal Segment Networks
Code & Models for Temporal Segment Networks (TSN) in ECCV 2016
Top category match
Cosmos Curator
Cosmos Curator is a powerful video curation system that processes, analyzes, and organizes video content using advanced AI models and distributed computing.
Top category match
Streaming Vlm
StreamingVLM: Real-Time Understanding for Infinite Video Streams
Top category match