OpenNLPLab/AVSBench
[ECCV 2022] Official implementation of the paper: Audio-Visual Segmentation
PythonApache-2.0
Issues
- 0
Changing the data set
#27 opened by yjr44 - 1
Cannot find pretrained model
#26 opened by skychan - 1
- 2
Labeling noise?
#24 opened by ryohachiuma - 0
- 3
IoU & F1-score computation
#22 opened by Devin-Pi - 0
Could you please release your inference code?
#21 opened by txchen-USTC - 2
Pretrained Weights
#9 opened by abhigoku10 - 1
About data loading paths in config file
#20 opened by WaltPeter - 3
Raw video dataset
#19 opened by ryohachiuma - 2
What is the difference among Single Sound Source Segmentation (S4), Multiple Sound Source Segmentation (MS3), and Audio-Visual Semantic Segmentation (AVSS)?
#18 opened by Ako-r - 1
why choose the batch 4 rather than 1?
#17 opened by StormArcher - 2
What is the result of your AVSS setting?
#16 opened by haoyi-duan - 2
visual_backone frozen issue
#15 opened by Divine0719 - 1
about FREEZE_VISUAL_EXTRACTOR
#14 opened by Divine0719 - 10
- 2
Some questions for your setting
#13 opened by yyliu01 - 7
About training
#1 opened by CVUsers - 1
Class category for multi source data
#11 opened by cyh-0 - 1
Performance difference
#10 opened by DemonsHunter - 3
Bug report during execuating s4/train.sh "train.sh: line 5: spring.submit: command not found"
#7 opened by DemonsHunter - 1
- 4
Question on loss AVM-AV
#5 opened by HaoranChen - 1
what does ‘start’ mean in the meta.csv?
#4 opened by lxa9867 - 1
hardware and runtime
#3 opened by Neko9810 - 2
About Detect
#2 opened by CVUsers