horovod-ansibleCreate Horovod cluster easily using Ansible
Stars: ✭ 22 (-98.79%)
clip-guided-diffusionA CLI tool/python module for generating images from text using guided diffusion and CLIP from OpenAI.
Stars: ✭ 260 (-85.66%)
Modality-Transferable-MERModality-Transferable-MER, multimodal emotion recognition model with zero-shot and few-shot abilities.
Stars: ✭ 36 (-98.01%)
slpUtils and modules for Speech Language and Multimodal processing using pytorch and pytorch lightning
Stars: ✭ 17 (-99.06%)
LAVT-pytorchLAVT: Language-Aware Vision Transformer for Referring Image Segmentation
Stars: ✭ 16 (-99.12%)
MVGLTCyb 2018: Graph learning for multiview clustering
Stars: ✭ 26 (-98.57%)
NER-Multimodal-pytorchPytorch Implementation of "Adaptive Co-attention Network for Named Entity Recognition in Tweets" (AAAI 2018)
Stars: ✭ 42 (-97.68%)
docarrayThe data structure for unstructured data
Stars: ✭ 561 (-69.06%)
RSTNetRSTNet: Captioning with Adaptive Attention on Visual and Non-Visual Words (CVPR 2021)
Stars: ✭ 71 (-96.08%)
nemar[CVPR2020] Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation
Stars: ✭ 120 (-93.38%)
iMIXA framework for Multimodal Intelligence research from Inspur HSSLAB.
Stars: ✭ 21 (-98.84%)
lipnetLipNet with gluon
Stars: ✭ 16 (-99.12%)
img2datasetEasily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
Stars: ✭ 1,173 (-35.3%)
gakgGAKG is a multimodal Geoscience Academic Knowledge Graph (GAKG) framework by fusing papers' illustrations, text, and bibliometric data.
Stars: ✭ 21 (-98.84%)
mix-stageOfficial Repository for the paper Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach published in ECCV 2020 (https://arxiv.org/abs/2007.12553)
Stars: ✭ 22 (-98.79%)
MinkLocMultimodalMinkLoc++: Lidar and Monocular Image Fusion for Place Recognition
Stars: ✭ 65 (-96.41%)
Kaleido-BERT(CVPR2021) Kaleido-BERT: Vision-Language Pre-training on Fashion Domain.
Stars: ✭ 252 (-86.1%)
pykaleKnowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for interdisciplinary research, part of the 🔥PyTorch ecosystem
Stars: ✭ 381 (-78.99%)