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.
no code implementations • 23 Dec 2022 • Dennis Melamed, Cameron Johnson, Chen Zhao, Russell Blue, Philip Morrone, Anthony Hoogs, Brian Clipp
This new challenge involves a new dataset and metrics indicating solution performance when damage is more local and limited than in xBD.
no code implementations • 12 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.
1 code implementation • 9 Nov 2022 • Daniel Davila, Dawei Du, Bryon Lewis, Christopher Funk, Joseph Van Pelt, Roderick Collins, Kellie Corona, Matt Brown, Scott McCloskey, Anthony Hoogs, Brian Clipp
In this paper, we present the Multi-view Extended Videos with Identities (MEVID) dataset for large-scale, video person re-identification (ReID) in the wild.
1 code implementation • 20 Jul 2022 • Zhiheng Li, Anthony Hoogs, Chenliang Xu
By training in an alternate manner, the discoverer tries to find multiple unknown biases of the classifier without any annotations of biases, and the classifier aims at unlearning the biases identified by the discoverer.
Ranked #1 on Out-of-Distribution Generalization on ImageNet-W
1 code implementation • CVPR 2022 • Rui Yu, Dawei Du, Rodney LaLonde, Daniel Davila, Christopher Funk, Anthony Hoogs, Brian Clipp
In this paper, we propose the Cascade Occluded Attention Transformer (COAT) for end-to-end person search.
no code implementations • 2 Dec 2020 • Kellie Corona, Katie Osterdahl, Roderic Collins, Anthony Hoogs
Our dataset is over 9300 hours of untrimmed, continuous video, scripted to include diverse, simultaneous activities, along with spontaneous background activity.
no code implementations • 27 Nov 2018 • Chengjiang Long, Arslan Basharat, Anthony Hoogs
First, an I3D network finds coarse-level matches between candidate duplicated frame sequences and the corresponding selected original frame sequences.
no code implementations • 5 Jun 2018 • Chirag Agarwal, Bo Dong, Dan Schonfeld, Anthony Hoogs
Instead of simply measuring a DNN's adversarial robustness in the input domain, as previous works, the proposed NSS is built on top of insightful mathematical understanding of the adversarial attack and gives a more explicit explanation of the robustness.
no code implementations • 27 Jan 2018 • Chengjiang Long, Roddy Collins, Eran Swears, Anthony Hoogs
We propose a novel method for predicting image labels by fusing image content descriptors with the social media context of each image.
no code implementations • CVPR 2014 • Eran Swears, Anthony Hoogs, Qiang Ji, Kim Boyer
Modeling interactions of multiple co-occurring objects in a complex activity is becoming increasingly popular in the video domain.
no code implementations • CVPR 2013 • Yiliang Xu, Sangmin Oh, Anthony Hoogs
We advance the state-of-the-art by a new model of measurement error in the line segment extraction and minimizing its impact on the vanishing point estimation.