WAT icon indicating copy to clipboard operation
WAT copied to clipboard

code for cvpr2022 paper "Weakly-supervised Action Transition Learning for Stochastic Human Motion Prediction"

Results 6 WAT issues
Sort by recently updated
recently updated
newest added

Hi, nice work. I was wondering if the main code for training the classifier could be released, I am trying to implement your method on a private 3d motion dataset....

Thanks so much for sharing the visualization code !!! When using your visualization code, it works well on the GRAB and NTU datasets. But on HumanAct12 and BABEL dataset, the...

Hi, thanks for your nice work! I have some questions about the evaluation step. I run the evaluation script: ``` CFG="grab_rnn" CFG_CLASS=grab_act_classifier GPU_IDX=0 TH=0.015 python eval_vae_act_stats_muti_seed.py --iter 500 --nk 10...

Hi, I was wondering if you could release the main code that evaluates the metric "ADE". Since the length of the sequence is different, how do you calculate the 'ADE'?...

Hi,Thanks for your nice work! I‘am running this project.I have some questions about the code. ` ====> Epoch: 181 Time: 168.94 TOTAL: 35.0043 MSE: 0.4555 DCT_smooth: 0.0667 Lastframe_smooth: 0.0574 KLD:...

I have noticed that in your paper you reported the result of predicting future motions given multiple action labels (e.g., Figure (4) 2nd row). I wonder how is this part...