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 weareru0027s 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 weareru0027s momentary visual attention, and his/her intentions. We exploit this observation by proposing a new cross-model EgoSupervision learning scheme that allows us to predict with whom the camera wearer will cooperate in the near future, 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. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/iccvw.2017.278 | ICCV Workshops |
Field | DocType | Citations |
Social cue,Computer science,Exploit,Ground truth,Visual attention,Artificial intelligence,Decoding methods,Machine learning,Basketball | Conference | 0 |
PageRank | References | Authors |
0.34 | 23 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jianbo Shi | 1 | 10207 | 1031.66 |
Gedas Bertasius | 2 | 169 | 10.38 |