JacobChalk/TIM
Codebase for the paper: "TIM: A Time Interval Machine for Audio-Visual Action Recognition"
Python
Issues
- 4
Regarding the Two Annotation Sources
#33 opened by lin-nie - 1
pretrained_model can not be found
#32 opened by WannaSir - 14
recreate perception_test problems
#30 opened by WannaSir - 1
recreate problem on AVE
#29 opened by WannaSir - 1
perception test video_feature problem
#31 opened by WannaSir - 7
merge_features
#28 opened by hongminglin08 - 4
how to recreate the result
#26 opened by WannaSir - 2
extract perception_test audio feature problems
#27 opened by WannaSir - 2
video feature problem
#21 opened by WannaSir - 1
parameter problems
#25 opened by WannaSir - 1
EPIC_SOUNDS data problems
#23 opened by WannaSir - 1
can not find requirement.txt
#24 opened by WannaSir - 2
how to split the AVE data into train/test/val and i download the data from https://drive.google.com/open?id=1FjKwe79e0u96vdjIVwfRQ1V6SoDHe7kK
#18 opened by WannaSir - 3
parameters question
#19 opened by WannaSir - 4
Questions about training
#20 opened by ssp789 - 8
Input parameter setting
#17 opened by hongminglin08 - 2
Can not find the files
#16 opened by WannaSir - 2
Regarding merged EPIC-Kitchens features
#15 opened by Anirudh257 - 4
- 0
Can anyone reproduce the acc indicator in the paper? epic or percetion_test
#13 opened by rixejzvdl649 - 0
- 2
pretrained audio model
#8 opened by JMcarrot - 0
- 1
the data needed to train EPIC-KITCHENS
#9 opened by hongminglin08 - 4
use multiple GPUs
#7 opened by hongminglin08 - 8
Input parameter setting
#6 opened by hongminglin08 - 2
code error
#5 opened by hongminglin08 - 1
Unsupported num_class for Mixup
#4 opened by HaozheQi - 2
Video feature extraction error
#3 opened by hongminglin08 - 4
Query on running Omnivore model
#2 opened by FranklinLeong - 1
Pretrained models for quick test
#1 opened by HaozheQi