5 results found Sort:

v-iashin
video_features v-iashin
91
466
mit
6
Extract video features from raw videos using multiple GPUs. We support RAFT flow frames as well as S3D, I3D, R(2+1)D, VGGish, CLIP, and TIMM models.
i3d s3d vit clip raft swin timm ig65m laion resnet vggish pytorch parallel r2plus1d multi-gpu optical-flow audio-features video-features visual-features feature-extraction
Created 2020-06-01
96 commits to master branch, last one 3 months ago
v-iashin
SpecVQGAN v-iashin
36
327
mit
8
Source code for "Taming Visually Guided Sound Generation" (Oral at the BMVC 2021)
gan vas bmvc audio video vqvae melgan pytorch vggsound multi-modal transformer video-features audio-generation evaluation-metrics video-understanding
Created 2021-10-17
22 commits to main branch, last one about a year ago
v-iashin
BMT v-iashin
56
223
mit
6
Source code for "Bi-modal Transformer for Dense Video Captioning" (BMVC 2020)
bmt i3d bmvc audio video bmvc20 pytorch transformer video-features bi-modal-encoder multimodal-fusion proposal-generator activitynet-captions bi-modal-transformer dense-video-captioning temporal-action-proposals
Created 2020-05-06
36 commits to master branch, last one about a year ago
linjieli222
HERO_Video_Feature_Extractor linjieli222
14
93
mit
3
Video Feature Extraction Code for EMNLP 2020 paper "HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training"
resnet pytorch slowfast video-features vision-and-language
Created 2020-12-01
17 commits to main branch, last one 3 years ago
tridivb
slowfast_feature_extractor tridivb
24
75
mit
3
Feature Extractor module for videos using the PySlowFast framework
video-features slowfast-networks feature-extraction
Created 2019-11-07
28 commits to master branch, last one 3 years ago