search

antoine77340 / video_feature_extractor

Easy to use video deep features extractor
Apache License 2.0
303 stars 70 forks source link

Question on output dimension #5

Closed weiyengs closed 4 years ago

weiyengs commented 4 years ago

Hi, great work there! I noticed that the dimension of the output is not fixed and depends on video length(eg. some are 33x2048, some are 12x2048, etc)

What's the best way to get them to a single dim(eg. 1x2048)?

Thanks!

antoine77340 commented 4 years ago

Depending on the length of the video, I guess temporally averaging the descriptors is a good choice for short video clip (ie less than 100). Otherwise you will need to aggregate the features using neural network approaches such as NetVLAD for example.

weiyengs commented 4 years ago

Depending on the length of the video, I guess temporally averaging the descriptors is a good choice for short video clip (ie less than 100). Otherwise you will need to aggregate the features using neural network approaches such as NetVLAD for example.

Hey thanks for the idea!