Search Results - "Boult, Terrance"

Probability Models for Open Set Recognition by Scheirer, Walter J., Jain, Lalit P., Boult, Terrance E.

“…Real-world tasks in computer vision often touch upon open set recognition: multi-class recognition with incomplete knowledge of the world and many unknown…”
Get full text

The Extreme Value Machine by Rudd, Ethan M., Jain, Lalit P., Scheirer, Walter J., Boult, Terrance E.

“…It is often desirable to be able to recognize when inputs to a recognition function learned in a supervised manner correspond to classes unseen at training…”
Get full text

A Survey of Stealth Malware Attacks, Mitigation Measures, and Steps Toward Autonomous Open World Solutions by Rudd, Ethan M., Rozsa, Andras, Gunther, Manuel, Boult, Terrance E.

“…As our professional, social, and financial existences become increasingly digitized and as our government, healthcare, and military infrastructures rely more…”
Get full text

Toward Open Set Recognition by Scheirer, W. J., de Rezende Rocha, A., Sapkota, A., Boult, T. E.

“…To date, almost all experimental evaluations of machine learning-based recognition algorithms in computer vision have taken the form of "closed set"…”
Get full text

The Overlooked Elephant of Object Detection: Open Set by Dhamija, Akshay Raj, Gunther, Manuel, Ventura, Jonathan, Boult, Terrance E.

“…Even though object detection is a popular area of research that has found considerable applications in the real world, it has some fundamental aspects that…”
Get full text

Facial attributes: Accuracy and adversarial robustness by Rozsa, Andras, Günther, Manuel, Rudd, Ethan M., Boult, Terrance E.

“…•End-to-end deep neural networks (DNNs) excel at facial attribute classification.•Facial attribute classification via DNNs is vulnerable to adversarial…”
Get full text

Comparative study on chromatin loop callers using Hi-C data reveals their effectiveness by Chowdhury, H M A Mohit, Boult, Terrance, Oluwadare, Oluwatosin

“…Chromosome is one of the most fundamental part of cell biology where DNA holds the hierarchical information. DNA compacts its size by forming loops, and these…”
Get full text

DaliID: Distortion-Adaptive Learned Invariance for Identification-A Robust Technique for Face Recognition and Person Re-Identification by Robbins, Wes, Bertocco, Gabriel, Boult, Terrance E.

“…In real-world applications, face recognition, and person re-identification are subject to image degradations such as motion blur, atmospheric turbulence, or…”
Get full text

Meta-Recognition: The Theory and Practice of Recognition Score Analysis by Scheirer, W J, Rocha, A, Micheals, R J, Boult, T E

“…In this paper, we define meta-recognition, a performance prediction method for recognition algorithms, and examine the theoretical basis for its…”
Get full text

Weibull-Open-World (WOW) Multi-Type Novelty Detection in CartPole3D by Boult, Terrance E., Windesheim, Nicolas M., Zhou, Steven, Pereyda, Christopher, Holder, Lawrence B.

“…Algorithms for automated novelty detection and management are of growing interest but must address the inherent uncertainty from variations in non-novel…”
Get full text

Open-Set Support Vector Machines by Ribeiro Mendes Junior, Pedro, Boult, Terrance E., Wainer, Jacques, Rocha, Anderson

“…Often, when dealing with real-world recognition problems, we do not need, and often cannot have, knowledge of the entire set of possible classes that might…”
Get full text

Good recognition is non-metric by Scheirer, Walter J., Wilber, Michael J., Eckmann, Michael, Boult, Terrance E.

“…Recognition is the fundamental task of visual cognition, yet how to formalize the general recognition problem for computer vision remains an open issue. The…”
Get full text

Agglomerative Clustering with Threshold Optimization via Extreme Value Theory by Li, Chunchun, Günther, Manuel, Dhamija, Akshay Raj, Cruz, Steve, Jafarzadeh, Mohsen, Ahmad, Touqeer, Boult, Terrance E.

“…Clustering is a critical part of many tasks and, in most applications, the number of clusters in the data are unknown and must be estimated. This paper…”
Get full text

Infoprint: Information Theoretic Digital Image Forensics by Ghosh, Aurobrata, Zhong, Zheng, Cruz, Steve, Veeravasarapu, Subbu, Singh, Maneesh, Boult, Terrance E

“…Tampered images pose a serious predicament since digitized media is a ubiquitous part of our lives. These are facilitated by the availability of image editing…”
Get full text

CAST: Conditional Attribute Subsampling Toolkit for Fine-grained Evaluation by Robbins, Wes, Zhou, Steven, Bhatta, Aman, Mello, Chad, Albiero, Vitor, Bowyer, Kevin W., Boult, Terrance E.

“…Thorough evaluation is critical for developing models that are fair and robust. In this work, we describe the Conditional Attribute Subsampling Toolkit (CAST)…”
Get full text

I-MOVE: Independent Moving Objects for Velocity Estimation by Schwan, Jonathan, Dhamija, Akshay Raj, Boult, Terrance E.

“…We introduce I-MOVE, the first publicly available RGBD/stereo dataset for estimating velocities of independently moving objects. Velocity estimation given…”
Get full text

GRAB: generalized region assigned to binary by Sapkota, Archana, Boult, Terrance E

“…Scale is one of the major challenges in recognition problems. For example, a face captured across large distances is considerably harder to recognize than the…”
Get full text

Predicting Change in Posttraumatic Distress Through Change in Coping Self-Efficacy After Using the My Trauma Recovery eHealth Intervention: Laboratory Investigation by Benight, Charles C, Shoji, Kotaro, Yeager, Carolyn M, Weisman, Pamela, Boult, Terrance E

“…Technology offers a unique platform for delivering trauma interventions (ie, eHealth) to support trauma-exposed populations. It is important to evaluate…”
Get full text

Towards Open World Recognition by Bendale, Abhijit, Boult, Terrance

“…With the of advent rich classification models and high computational power visual recognition systems have found many operational applications. Recognition in…”
Get full text

Towards Open Set Deep Networks by Bendale, Abhijit, Boult, Terrance E.

“…Deep networks have produced significant gains for various visual recognition problems, leading to high impact academic and commercial applications. Recent work…”
Get full text