Towards accurate multi-person pose estimation in the wild

[HaoLiuHust]

Is this paper implemented in models?

[reedwm]

/CC @gpapan @jonathantompson

[gpapan]

Not yet, but we have tentative plans to add it in a few months from now.

[xzha8059]

Hi,gpapan,could you recommend some reference about the hough voting in your paper? I am very interested in your paper.

[steph-tan]

@gpapan hi, Is this paper's implementation added? Not sure if I had missed something..

[Axlef]

Up, this is a very exciting work and we would love to test it on tensorflow. Also do you have data about performance (inference speed) of the system ? You mentioned faster inference depending on the module (ResNet-50, input size, cropping size) but no numbers are provided. Do you think it can achieve real-time detection on an "average" machine ?

[thomaswienecke]

Are there any news about this?

[gpapan]

We have not yet open sourced the system. @Axlef : Yes, the ResNet-based system can run in real time on a machine with a modern GPU.

[ChinaCobby]

Hello, I have read your paper, but I do not understand the hough voting and the equation about it in the paper? Could you help me explain it? Thank you so much.

[chenyanyin]

Is this paper implemented in models now?

[ludns]

+1

[thomaswienecke]

+1

[tensorflowbutler]

Hi There, We are checking to see if you still need help on this, as this seems to be considerably old issue. Please update this issue with the latest information, code snippet to reproduce your issue and error you are seeing. If we don't hear from you in the next 7 days, this issue will be closed automatically. If you don't need help on this issue any more, please consider closing this.

[WarrenGreen]

We still want this.

[JulianAssmann]

Are there any updates? If I understand correctly, the tfjs-models library provides an implementation of this here, right?