search

PeihaoChen / RSPNet

Official Pytorch implementation for AAAI2021 paper (RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning)
36 stars 8 forks source link

The pre-training model of s3d-g model based on Imagenet and dynamics-400 data set? #4

Closed LiangSiyv closed 3 years ago

LiangSiyv commented 3 years ago

Where can I download the pre training model of s3d-g model based on Imagenet and dynamics-400 dataset? Or can you upload it to this repository? 请问哪里可以下载到基于ImageNet和Kinetics-400数据集的S3D-G模型的预训练模型？或者请问作者可以上传一下公开吗？

PeihaoChen commented 3 years ago

The ImageNet and Kinetics-400 fully supervised pretraining results for S3D-g models are taken from Table 2 in the paper "SpeedNet: Learning the Speediness in Videos". We are not clear how they achieve these results and we have not reproduced them.

LiangSiyv commented 3 years ago

Thanks