A multimodal architecture to build multimodal knowledge graphs with flexible multimodal feature extraction and dynamic multimodal concept generation.
Project description
MMKit-Features: Multimodal Feature Extraction Toolkit
Traditional knowledge graphs (KGs) are usually comprised of entities, relationships, and attributes. However, they are not designed to effectively store or represent multimodal data. This limitation prevents them from capturing and integrating information from different modes of data, such as text, images, and audio, in a meaningful and holistic way.
The MMKit-Features
project proposes a multimodal architecture to build multimodal knowledge graphs with flexible multimodal feature extraction and dynamic multimodal concept generation.
Project Goal
- To extract, store, and fuse various multimodal features from multimodal datasets efficiently;
- To achieve generative adversarial network(GAN)-based multimodal knowledge representation dynamically in multimodal knowledge graphs;
- To provide a common deep learning-based architecture to enhance multimodal knowledge reasoning in real life.
Installation
You can install this toolkit using our PyPi package.
pip install mmkit-features
Design Science Framework
Figure 1: Multimodal Computational Sequence
Figure 2: GAN-based Multimodal Concept Generation
Modalities
- Text/Language modality
- Image modality
- Video modality
- Audio modality
- Cross-modality among above
Usage
A toy example showing how to build a multimodal feature (MMF) library is here:
from mmkfeatures.fusion.mm_features_lib import MMFeaturesLib
from mmkfeatures.fusion.mm_features_node import MMFeaturesNode
import numpy as np
if __name__ == "__main__":
# 1. create an empty multimodal features library with root and dataset names
feature_lib = MMFeaturesLib(root_name="test features",dataset_name = "test_features")
# 2. set short names for each dimension for convenience
feature_lib.set_features_name(["feature1","feature2","feature3"])
# 3. set a list of content IDs
content_ids = ["content1","content2","content3"]
# 4. according to IDs, assign a group of features with interval to corresponding content ID
features_dict = {}
for id in content_ids:
mmf_node = MMFeaturesNode(id)
mmf_node.set_item("name",str(id))
mmf_node.set_item("features",np.array([[1,2,3]]))
mmf_node.set_item("intervals",np.array([[0,1]]))
features_dict[id] = mmf_node
# 5. set the library's data
feature_lib.set_data(features_dict)
# 6. save the features to disk for future use
feature_lib.save_data("test6_feature.csd")
# 7. check structure of lib file with the format of h5py
feature_lib.show_structure("test6_feature.csd")
# 8. have a glance of features content within the dataset
feature_lib.show_sample_data("test6_feature.csd")
# 9. Finally, we construct a simple multimodal knowledge base.
Further instructions on the toolkit refers to here.
Applications
Here are some examples of using our work in real life with codes and documents.
1. Multimodal Features Extractors
- Text Features Extraction
- Speech Features Extraction
- Image Features Extractoin
- Video Features Extraction
- Transformer-based Features Extraction
2. Multimodal Feature Library (MMFLib)
3. Multimodal Knowledge Bases
- Multimodal Birds Feature Library
- Multimodal Disease Coding Feature Library
- Multimodal ROCO Feature Library
4. Multimodal Indexing and Querying
Credits
The project includes some source codes from various open-source contributors. Here is a list of their contributions.
- A2Zadeh/CMU-MultimodalSDK
- aishoot/Speech_Feature_Extraction
- antoine77340/video_feature_extractor
- jgoodman8/py-image-features-extractor
- v-iashin/Video Features
License
The mmkit-features
project is provided by Donghua Chen with MIT license.
Citation
Please cite our project if the project is used in your research.
Chen, D. (2023). MMKit-Features: Multimodal Features Extraction Toolkit (Version 0.0.2) [Computer software]
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file mmkit-features-0.0.1a2.tar.gz
.
File metadata
- Download URL: mmkit-features-0.0.1a2.tar.gz
- Upload date:
- Size: 96.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.8.0 pkginfo/1.8.2 readme-renderer/34.0 requests/2.27.1 requests-toolbelt/0.9.1 urllib3/1.26.9 tqdm/4.63.0 importlib-metadata/4.11.3 keyring/23.5.0 rfc3986/2.0.0 colorama/0.4.4 CPython/3.9.11
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | a5946046183b33d1ac78164b80cc1082061606a444f95b245b8a3fc0d77688b9 |
|
MD5 | 5916c7326ae37ece0be19779bb82a3a5 |
|
BLAKE2b-256 | d5b77ae7495a33ba4f74cff978b531b236daf4120edd26c74a7cd87e6a9c2740 |
File details
Details for the file mmkit_features-0.0.1a2-py3-none-any.whl
.
File metadata
- Download URL: mmkit_features-0.0.1a2-py3-none-any.whl
- Upload date:
- Size: 125.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.8.0 pkginfo/1.8.2 readme-renderer/34.0 requests/2.27.1 requests-toolbelt/0.9.1 urllib3/1.26.9 tqdm/4.63.0 importlib-metadata/4.11.3 keyring/23.5.0 rfc3986/2.0.0 colorama/0.4.4 CPython/3.9.11
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 6c6a7dafa8c814f7876c3f33256a35ae6cd3cd222f3db2625e6360c3f959d2ca |
|
MD5 | 4937094ae35cb49b9a96b6aeaccb073a |
|
BLAKE2b-256 | ca26d4666d8c283a23156b192bcf4be57b1d4044373479f8f3c486b190bce080 |