no code implementations • 18 Dec 2023 • Md Ahmed Al Muzaddid, William J. Beksi
We show the efficacy of our approach on the task of tracking and counting infield cotton bolls.
1 code implementation • 5 Nov 2023 • Mohammad Samiul Arshad, William J. Beksi
Yet, such approaches often rely on distinguishing between the inside and outside of a surface in order to extract a zero level set when reconstructing the target.
no code implementations • 11 Sep 2023 • Jordan A. James, Heather K. Manching, Matthew R. Mattia, Kim D. Bowman, Amanda M. Hulse-Kemp, William J. Beksi
Concretely, we provide high-resolution images of citrus trees located in an area known to be highly affected by HLB, along with high-quality bounding box annotations of citrus fruit.
1 code implementation • ICCV 2023 • Mohammad Samiul Arshad, William J. Beksi
We utilize global 2D features to predict a coarse shape of the target object and then use it as a base for higher-resolution reconstruction.
no code implementations • 20 Nov 2022 • Zongyao Lyu, Nolan B. Gutierrez, William J. Beksi
Open-set recognition refers to the problem in which classes that were not seen during training appear at inference time.
no code implementations • 26 Oct 2022 • Mohammad Samiul Arshad, William J. Beksi
Yet, these methods rely on a discretized representation of the raw data, which loses important surface details and can lead to outliers in the reconstruction.
1 code implementation • 23 Oct 2022 • Quan H. Nguyen, William J. Beksi
To retrieve an image of a particular resolution, we apply a decoding function to a grid of locations each of which refers to the center of a pixel in the output image.
no code implementations • 15 May 2022 • Zongyao Lyu, Nolan B. Gutierrez, William J. Beksi
Despite achieving enormous success in predictive accuracy for visual classification problems, deep neural networks (DNNs) suffer from providing overconfident probabilities on out-of-distribution (OOD) data.
1 code implementation • 28 Feb 2022 • Md Ahmed Al Muzaddid, William J. Beksi
In this paper, we propose a novel variable rate deep compression architecture that operates on raw 3D point cloud data.
1 code implementation • 30 Jul 2021 • Nolan B. Gutierrez, William J. Beksi
Specifically, we explore how to effectively attend to contrasting receptive fields (RFs) where increasing the RFs of a network can be computationally expensive.
1 code implementation • 28 Jun 2021 • Zongyao Lyu, Nolan B. Gutierrez, William J. Beksi
In this paper, we introduce a new technique that combines two popular methods to estimate uncertainty in object detection.
1 code implementation • 19 Apr 2021 • Pritam Karmokar, Kashish Dhal, William J. Beksi, Animesh Chakravarthy
In this paper, we present a novel vision-based framework for tracking dynamic objects using guidance laws based on a rendezvous cone approach.
1 code implementation • 4 Mar 2021 • Christopher Collander, William J. Beksi, Manfred Huber
In this paper, we introduce a reinforcement learning approach utilizing a novel topology-based information gain metric for directing the next best view of a noisy 3D sensor.
1 code implementation • 12 Oct 2020 • Mohammad Samiul Arshad, William J. Beksi
In this paper, we introduce a novel conditional generative adversarial network that creates dense 3D point clouds, with color, for assorted classes of objects in an unsupervised manner.
no code implementations • 9 Jan 2020 • Aditya Rajguru, Christopher Collander, William J. Beksi
In this paper, we introduce a novel method to capture visual trajectories for navigating an indoor robot in dynamic settings using streaming image data.