SimAug: Learning Robust Representations from Simulation for Trajectory Prediction
This paper studies the problem of predicting future trajectories of people in unseen cameras
of novel scenarios and views. We approach this problem through the real-data-free setting in …
of novel scenarios and views. We approach this problem through the real-data-free setting in …
[PDF][PDF] Simaug: Learning robust representations from 3d simulation for pedestrian trajectory prediction in unseen cameras
This paper focuses on the problem of predicting future trajectories of people in unseen
scenarios and camera views. We propose a method to efficiently utilize multi-view 3D …
scenarios and camera views. We propose a method to efficiently utilize multi-view 3D …
Multimodal Generation of Novel Action Appearances for Synthetic-to-Real Recognition of Activities of Daily Living
Domain shifts, such as appearance changes, are a key challenge in real-world applications
of activity recognition models, which range from assistive robotics and smart homes to driver …
of activity recognition models, which range from assistive robotics and smart homes to driver …
From Recognition to Prediction: Analysis of Human Action and Trajectory Prediction in Video
J Liang - arXiv preprint arXiv:2011.10670, 2020 - arxiv.org
With the advancement in computer vision deep learning, systems now are able to analyze
an unprecedented amount of rich visual information from videos to enable applications such …
an unprecedented amount of rich visual information from videos to enable applications such …
Nuisance-Label Supervision: Robustness Improvement by Free Labels
In this paper, we present a Nuisance-label Supervision (NLS) module, which can make
models more robust to nuisance factor variations. Nuisance factors are those irrelevant to a …
models more robust to nuisance factor variations. Nuisance factors are those irrelevant to a …