Search Results for author: Christopher Funk

Found 12 papers, 2 papers with code

Beyond Planar Symmetry: Modeling human perception of reflection and rotation symmetries in the wild

no code implementations ICCV 2017 Christopher Funk, Yanxi Liu

Humans take advantage of real world symmetries for various tasks, yet capturing their superb symmetry perception mechanism with a computational model remains elusive.

Symmetry Detection

From Kinematics To Dynamics: Estimating Center of Pressure and Base of Support from Video Frames of Human Motion

no code implementations2 Jan 2020 Jesse Scott, Christopher Funk, Bharadwaj Ravichandran, John H. Challis, Robert T. Collins, Yanxi Liu

To gain an understanding of the relation between a given human pose image and the corresponding physical foot pressure of the human subject, we propose and validate two end-to-end deep learning architectures, PressNet and PressNet-Simple, to regress foot pressure heatmaps (dynamics) from 2D human pose (kinematics) derived from a video frame.

From Image to Stability: Learning Dynamics from Human Pose

no code implementations ECCV 2020 Jesse Scott, Bharadwaj Ravichandran, Christopher Funk, Robert T. Collins, Yanxi Liu

We propose and validate two end-to-end deep learning architectures to learn foot pressure distribution maps (dynamics) from 2D or 3D human pose (kinematics).

Reconstructing Humpty Dumpty: Multi-feature Graph Autoencoder for Open Set Action Recognition

no code implementations12 Dec 2022 Dawei Du, Ameya Shringi, Anthony Hoogs, Christopher Funk

Our approach uses the reconstruction error to determine the novelty of the video since unknown classes are harder to put back together and thus have a higher reconstruction error than videos from known classes.

Open Set Action Recognition

Human Activity Recognition in an Open World

no code implementations23 Dec 2022 Derek S. Prijatelj, Samuel Grieggs, Jin Huang, Dawei Du, Ameya Shringi, Christopher Funk, Adam Kaufman, Eric Robertson, Walter J. Scheirer

Managing novelty in perception-based human activity recognition (HAR) is critical in realistic settings to improve task performance over time and ensure solution generalization outside of prior seen samples.

Human Activity Recognition

Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning

no code implementations ICCV 2023 Colorado J. Reed, Ritwik Gupta, Shufan Li, Sarah Brockman, Christopher Funk, Brian Clipp, Kurt Keutzer, Salvatore Candido, Matt Uyttendaele, Trevor Darrell

Large, pretrained models are commonly finetuned with imagery that is heavily augmented to mimic different conditions and scales, with the resulting models used for various tasks with imagery from a range of spatial scales.

Representation Learning

EscherNet 101

no code implementations7 Mar 2023 Christopher Funk, Yanxi Liu

A deep learning model, EscherNet 101, is constructed to categorize images of 2D periodic patterns into their respective 17 wallpaper groups.

Open Set Action Recognition via Multi-Label Evidential Learning

no code implementations CVPR 2023 Chen Zhao, Dawei Du, Anthony Hoogs, Christopher Funk

Existing methods for open-set action recognition focus on novelty detection that assumes video clips show a single action, which is unrealistic in the real world.

Action Detection Novelty Detection +1

Exploiting Structure for Optimal Multi-Agent Bayesian Decentralized Estimation

no code implementations20 Jul 2023 Christopher Funk, Ofer Dagan, Benjamin Noack, Nisar R. Ahmed

We then test our new non-monolithic CI algorithm on a large-scale target tracking simulation and show that it achieves a tighter bound and a more accurate estimate compared to the original monolithic CI.

Cannot find the paper you are looking for? You can Submit a new open access paper.