Search Results for author:
Found 3 papers, 0 papers with code
PreTR: Spatio-Temporal Non-Autoregressive Trajectory Prediction Transformer
Finally, we justify our usage of the parallel decoding technique by showing that the trajectory prediction task can be better solved as a non-autoregressive task.
Is attention to bounding boxes all you need for pedestrian action prediction?
Interestingly, we showed that pre-training our Transformer model on the CP2A dataset and then fine-tuning it on the PIE dataset is beneficial for the action prediction task.
A dataset for complex activity recognition withmicro and macro activities in a cooking scenario
In this paper, we describe a new dataset for sensor-based activity recognition featuring macro and micro activities in a cooking scenario.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
