nhtlongcs/AIC2022-VER
Text Query based Traffic Video Event Retrieval with Global-Local Fusion Embedding
Python
Issues
- 0
- 0
disable *nl_other_views* in post process steps
#60 opened by nhtlongcs - 0
Merge srl module
#59 opened by nhtlongcs - 1
Add inference scripts
#50 opened by nhtlongcs - 0
Add refinement script
#38 opened by nhtlongcs - 0
constant batch size in predictor - complex mode
#62 opened by nhtlongcs - 0
Update docker
#61 opened by nhtlongcs - 0
Add loss monitor
#44 opened by nhtlongcs - 2
Add meta classifer
#39 opened by nhtlongcs - 0
Improve baseline model
#40 opened by nhtlongcs - 0
Add EDA viz tool
#41 opened by nhtlongcs - 1
Fix constant image size in predictor
#42 opened by nhtlongcs - 0
Add relation graph extractor
#36 opened by kaylode - 0
- 0
Add CLIP module
#35 opened by kaylode - 0
Add inference script
#24 opened by kaylode - 0
Add stop turn detector
#30 opened by kaylode - 0
Update logging (vis)
#11 opened by nhtlongcs - 0
Add SRL extractor
#15 opened by nhtlongcs - 1
Add tracking/det vehicle extractor
#13 opened by nhtlongcs - 0
Update conda env
#20 opened by nhtlongcs - 0
- 0
Add AIC metrics
#12 opened by nhtlongcs - 0
Update result visualize (UI version)
#10 opened by nhtlongcs - 2
Fix metric
#2 opened by nhtlongcs - 0
- 0
add pytest
#4 opened by nhtlongcs