video-cnn-feat
Video feature extractor
Extracts CNN features from video frames using pre-trained MXNet models
31 stars
4 watching
9 forks
Language: Python
last commit: over 3 years ago
Linked from 1 awesome list
Related projects:
| Repository | Description | Stars |
|---|---|---|
| | This repository provides code and models for a computer vision project that aims to improve the quality of videos by reducing motion blur. | 35 |
| | Evaluates and benchmarks large language models' video understanding capabilities | 121 |
| | This project demonstrates how to build and train a convolutional neural network (CNN) to recognize Chinese characters. | 200 |
| | PyTorch implementation of video captioning, combining deep learning and computer vision techniques. | 402 |
| | A tool for extracting features from videos using deep convolutional descriptors | 104 |
| | Provides an implementation of convolutional neural networks in MATLAB. | 98 |
| | Extracts frames from a video using ffmpeg. | 65 |
| | Reproduces results from the arxiv paper on clockwork convnets for video semantic segmentation using Caffe and Python | 141 |
| | Provides pre-trained models for Chinese natural language processing tasks using the XLNet architecture | 1,652 |
| | Trains a large Chinese language model on massive data and provides a pre-trained model for downstream tasks | 230 |
| | A Python implementation of a Convolutional Neural Network from scratch using NumPy for building CNNs from scratch | 577 |
| | This project provides a pre-trained video classification model that categorizes sports videos into their respective sports. | 23 |
| | A Keras implementation of MobileNetV2 with support for training and fine-tuning | 321 |
| | An MXNet implementation of a modified deep neural network architecture for image classification | 67 |
| | A PyTorch implementation of a compressed video action recognition system | 502 |