collaborative-experts
Video retrieval framework
A framework for improving video retrieval by leveraging multiple text encoders and their collaborative expertise.
Video embeddings for retrieval with natural language queries
337 stars
10 watching
55 forks
Language: Python
last commit: about 2 years ago
Linked from 1 awesome list
deep-neural-networksvideo-retrieval
Related projects:
Repository | Description | Stars |
---|---|---|
| Develops a deep learning framework for video retrieval using text and computer vision | 87 |
| A deep learning project that provides a video-text retrieval model and tools for training and evaluating it on the MSR-VTT dataset | 154 |
| A deep learning-based video search system using pre-trained models and datasets | 28 |
| An open-source implementation of the Mixture-of-Embeddings-Experts model in Pytorch for video-text retrieval tasks. | 118 |
| Develops a cross-modal architecture for video retrieval by combining multiple types of features from videos and text | 259 |
| Develops general video foundation models and related datasets for multimodal understanding and generation through generative and discriminative learning. | 1,467 |
| A neural network framework designed to make working with neural networks fast and flexible. | 1,303 |
| Develops a framework to deblur video by leveraging non-consecutively blurry frames and proposes an event fusion module for improving deblurring performance. | 35 |
| An abstraction layer between various deep learning frameworks and your program. | 149 |
| A framework for training neural models to rank data items based on relevance | 886 |
| A Python implementation of a graph neural network-based collaborative filtering framework for personalized recommendation systems | 812 |
| A collection of video analysis methods and datasets for research and development | 533 |
| Develops a method for long video understanding by optimizing memory usage | 550 |
| A C++ implementation of a deep learning framework designed for speed and modularity. | 59 |
| An artificial intelligence system designed to understand and describe long-form video content | 329 |