Fabien Baradel

Hi @YinXiaojieCSDN, What do you mean by "maskRCNN__png"? Sorry but I do not understand what would you like to do? Do you want to do transfer learning on other datasets?...

Okay I have now a big picture of what you want to do, thanks. Yes the masks are not perfect because they are estimated and do not correspond to ground-truth...

Hi Nirat, Thanks for the interest in our work. You can find the line by line implementation about how to retrieve the bboxes/segmentations for each detected objects per frames [here](https://github.com/fabienbaradel/object_level_visual_reasoning/blob/master/loader/videodataset.py#L172)....

Hi @JackSparrow3 Thanks :) You can find the annotations here: https://fabienbaradel.github.io/masks_data/ We have used MaskRCNN pretrained on COCO. We did not train MaskRCNN on our datasets (VLOG, Something Something, EPIC)...

Hi @CxuS, I encourage you to work on Something-Something V2 because the video resolution is higher (minimum high/weight = 256). I have been using Something-Something v1 for this project and...

Thanks @NewCoderQ , but I am looking for the method presented in the paper "Motion Capture from Internet Videos" with multiple videos of the same event and uncalibrated/asynchronized cameras. And...

@mkocabas Could you give us more details about results from Table 2 in the paper? Did you train using the 3DPW training set in particular for the line 'Baseline (only...

Thanks a lot @mkocabas for your answer :)

Hi @longbowzhang @geopavlakos, Any news about this issue? It seems to decrease a lot the performance on MPII_INF_3DHP. If we use 'annot3' keypoints at test time the performance is: MPJPE:118.78...