genbing99 / mtsn-spot-me-mae Goto Github PK
View Code? Open in Web Editor NEWMTSN: A Multi-Temporal Stream Network for Spotting Facial Macro- and Micro-Expression with Hard and Soft Pseudo-labels
MTSN: A Multi-Temporal Stream Network for Spotting Facial Macro- and Micro-Expression with Hard and Soft Pseudo-labels
请问训练代码怎么没有呢?
I've had a hard time trying to reproduce the results. Listed are what I've tried.
Reproduction ipynb:
CASME:
Micro result: TP:3 FP:137 FN:54 F1_score:0.0305
Macro result: TP:100 FP:206 FN:200 F1_score:0.3300
Overall result: TP:103 FP:343 FN:254 F1_score:0.2565
SAMMLV:
Cumulative result until subject 30:
Micro result: TP:10 FP:169 FN:149 F1_score:0.0592
Macro result: TP:97 FP:277 FN:246 F1_score:0.2706
Overall result: TP:107 FP:446 FN:395 F1_score:0.2028
Orig ipynb:
CASME:
Micro result: TP:5 FP:77 FN:52 F1_score:0.0719
Macro result: TP:108 FP:166 FN:192 F1_score:0.3763
Overall result: TP:113 FP:243 FN:244 F1_score:0.3170
SAMM:
Micro result: TP:12 FP:104 FN:147 F1_score:0.0873
Macro result: TP:88 FP:198 FN:255 F1_score:0.2798
Overall result: TP:100 FP:302 FN:402 F1_score:0.2212
As reported above, there's a huge gap between the reproduction result & orig. performance on CASME_sq, while the gap for SAMMLV dataset is much smaller.
I've also tried fixing the ransom seed=1, the result does not improve, and replacing the mix of hard&soft label loss by pure hard label loss improves results. Moreover, I notive there are many subtle differences between the orig. code & jupyter notebook, using spotting method in the orig. code produces very bad results:
Final result: TP:53, FP:320, FN:304
Precision = 0.1421
Recall = 0.0849
F1-Score = 0.1063
Replacing it by the spotting method in the jupyter notebook turns out better, with results:
Final result: TP:102, FP:299, FN:255
Precision = 0.2544
Recall = 0.1841
F1-Score = 0.2136
And I found a typo in the orig. code
MTSN-Spot-ME-MaE/spot_interval.py
Line 116 in 42c4c35
score_plot_micro[peak] > 0.95
should be score_plot_macro[peak] > 0.95
I'm trying to make some improvement on your work and take that as a baseline model, but I'm veru frustrated by the reproduction result. Any insight/help would be very precious to me.
您好,我尝试重新训练了您的代码,使用您的训练集,1/4做验证,但是发现f1-score非常低,和论文不符,请问可能是什么原因造成的呢?
Thanks for the great work. I noticed that there's only evaluation code for SAMM-Challenge and CAS(ME)^3, would you please also provide the counterpark for SAMM-LV and CAS(ME)^2 for reproduction on the F1-score results for those datasets?
Thanks for your work! After reading your paper, I found out that feature processing was only mentioned briefly. Specifically, the input size was reduced from 42 x 42 to 28 x 28. Did you process them as in previous work SoftNet(extract opt flow using TV-L1 and crop out 3 ROI regions) but only resized the feature to a smaller size?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.