Using Cross-Model EgoSupervision to Learn Cooperative Basketball Intention

Gedas Bertasius, Jianbo Shi; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2355-2363

Abstract


We present a first-person method for cooperative basketball intention prediction: we predict with whom the camera wearer will cooperate in the near future from unlabeled first-person images. This is a challenging task that requires inferring the camera wearer's visual attention, and decoding the social cues of other players. Our key observation is that a first-person view provides strong cues to infer the camera wearer's intentions. We exploit this observation via a new cross-model EgoSupervision learning scheme that allows us to predict with whom the camera wearer will cooperate, without using manually labeled intention labels. Our cross-model EgoSupervision operates by transforming the outputs of a pretrained pose-estimation network, into pseudo ground truth labels, which are then used as a supervisory signal to train a new network for a cooperative intention task. We evaluate our method, and show that it achieves similar or even better accuracy than the fully supervised methods do.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Bertasius_2017_ICCV,
author = {Bertasius, Gedas and Shi, Jianbo},
title = {Using Cross-Model EgoSupervision to Learn Cooperative Basketball Intention},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV) Workshops},
month = {Oct},
year = {2017}
}