Zobrazeno 1 - 10
of 385
pro vyhledávání: '"Hoogs, A."'
Autor:
Crall, Jon, Greenwell, Connor, Joy, David, Leotta, Matthew, Chaudhary, Aashish, Hoogs, Anthony
Learning from multiple sensors is challenging due to spatio-temporal misalignment and differences in resolution and captured spectra. To that end, we introduce GeoWATCH, a flexible framework for training models on long sequences of satellite images s
Externí odkaz:
http://arxiv.org/abs/2407.06337
Autor:
Ai, Lin, Kumarage, Tharindu, Bhattacharjee, Amrita, Liu, Zizhou, Hui, Zheng, Davinroy, Michael, Cook, James, Cassani, Laura, Trapeznikov, Kirill, Kirchner, Matthias, Basharat, Arslan, Hoogs, Anthony, Garland, Joshua, Liu, Huan, Hirschberg, Julia
The proliferation of Large Language Models (LLMs) poses challenges in detecting and mitigating digital deception, as these models can emulate human conversational patterns and facilitate chat-based social engineering (CSE) attacks. This study investi
Externí odkaz:
http://arxiv.org/abs/2406.12263
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. We propose a new method for open set action recognition and novelty detection via MUlti
Externí odkaz:
http://arxiv.org/abs/2303.12698
Autor:
Melamed, Dennis, Johnson, Cameron, Zhao, Chen, Blue, Russell, Morrone, Philip, Hoogs, Anthony, Clipp, Brian
The xView2 competition and xBD dataset spurred significant advancements in overhead building damage detection, but the competition's pixel level scoring can lead to reduced solution performance in areas with tight clusters of buildings or uninformati
Externí odkaz:
http://arxiv.org/abs/2212.13876
Most action recognition datasets and algorithms assume a closed world, where all test samples are instances of the known classes. In open set problems, test samples may be drawn from either known or unknown classes. Existing open set action recogniti
Externí odkaz:
http://arxiv.org/abs/2212.06023
Autor:
Davila, Daniel, Du, Dawei, Lewis, Bryon, Funk, Christopher, Van Pelt, Joseph, Collins, Roderick, Corona, Kellie, Brown, Matt, McCloskey, Scott, Hoogs, Anthony, Clipp, Brian
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. To our knowledge, MEVID represents the most-varied video person ReID dataset, spanning an ext
Externí odkaz:
http://arxiv.org/abs/2211.04656
Deep image classifiers have been found to learn biases from datasets. To mitigate the biases, most previous methods require labels of protected attributes (e.g., age, skin tone) as full-supervision, which has two limitations: 1) it is infeasible when
Externí odkaz:
http://arxiv.org/abs/2207.10077
Autor:
Yu, Rui, Du, Dawei, LaLonde, Rodney, Davila, Daniel, Funk, Christopher, Hoogs, Anthony, Clipp, Brian
The goal of person search is to localize a target person from a gallery set of scene images, which is extremely challenging due to large scale variations, pose/viewpoint changes, and occlusions. In this paper, we propose the Cascade Occluded Attentio
Externí odkaz:
http://arxiv.org/abs/2203.09642
We present the Multiview Extended Video with Activities (MEVA) dataset, a new and very-large-scale dataset for human activity recognition. Existing security datasets either focus on activity counts by aggregating public video disseminated due to its
Externí odkaz:
http://arxiv.org/abs/2012.00914
Videos can be manipulated by duplicating a sequence of consecutive frames with the goal of concealing or imitating a specific content in the same video. In this paper, we propose a novel coarse-to-fine framework based on deep Convolutional Neural Net
Externí odkaz:
http://arxiv.org/abs/1811.10762