Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 1697 for “"In-the-wild"”.
-
Reasoning in the Wild
Teaching machines to reason has been a longstanding goal in artificial intelligence. Recently, the rapid advancement of language modeling has advanced this vision, opening up new possibilities for automated reasoning. Although existing benchmarks have demonstrated strong reasoning performance of …
-
Human Detection in the Wild
Human detection remains a challenging task due to the problems caused by occlusion variance. Visible-body bounding boxes are typically used as an extra supervision signal to improve the performance of human detection. However, visible-body assisted approaches produce a large number of false …
-
Face recognition in the wild.
Research in face recognition deals with problems related to Age, Pose, Illumination and Expression (A-PIE), and seeks approaches that are invariant to these factors. Video images add a temporal aspect to the image acquisition process. Another degree of complexity, above and beyond A-PIE …
-
Discovering heap anomalies in the wild
Programmers increasingly rely on managed languages (e.g. Java and C#) to develop applications faster and with fewer bugs. Managed languages encourage allocating objects in the heap and rely on automatic memory management (garbage collection) to reclaim objects the program can no longer access. With …
-
Towards Visual Recognition in the Wild
The predefined artificially-balanced training classes in object recognition have limited capability in modeling real-world scenarios where objects are imbalanced-distributed with unknown classes. In this thesis, we present three research works on Long-Tailed Recognition task for both closed-set and …
-
Monitoring Gait Complexity in the Wild
… patterns, termed gait complexity, which provide information about the quality of gait control and adaptive capacity of the walker. Our knowledge of gait complexity is premised on studies estimating nonlinear measures such as fractal indices and entropy within controlled walking environments, …
-
Complex Affect Recognition in the Wild
Artificial social intelligence is a step towards human-like human-computer interaction. One important milestone towards building socially intelligent systems is enabling computers with the ability to process and interpret the social signals of humans in the real world. Social signals include a wide …
-
Adversarial Machine Learning in the Wild
Deep neural networks are making their way into our everyday lives at an increasing rate. While the adoption of these models has greatly improved our everyday lives, it has also opened the door to new vulnerabilities in real-world systems. More specifically, in the scope of this work we are …
-
Towards in-the-wild visual understanding
… vision research has seen tremendous success in recent times . This success can be attributed to recent breakthroughs in deep learning technology and such systems have been shown to achieve super human performance on several academic datasets. Driven by this success, these systems are actively …
-
Monitoring eating behaviour in the wild
A system to estimate the daily intake of food and drinks of a person was investigated. The system should distinguish intake moments from other gestures and sounds during the day, that occur such as when making a phone call, working at the office, etc. The system can be used for dietary training …
-
Tracking certificate misissuance in the wild
… Authorities (CAs) are responsible for delegating trust in the TLS Public Key Infrastructure (PKI). Unfortunately, there is a long history of CAs abusing this responsibility, either due to negligence or in some cases, falling victim to attacks. As a result, the PKI community has established …
-
Towards unified object recognition in the wild
Large-scale well-curated datasets are the fuel of computer vision. However, most datasets only focus on one single domain with a specific task and a fixed label set. Computer vision models trained on a single dataset only apply to a subset of applications in the real world. The goal of my research …
-
Text Detection and Recognition in the Wild
Text detection and recognition (TDR) in highly structured environments with a clean background and consistent fonts (e.g., office documents, postal addresses and bank cheque) is a well understood problem (i.e., OCR), however this is not the case for unstructured environments. The main objective for …
-
Designing for Shareable Interfaces in the Wild
Despite excitement about the potential of interactive tabletops to support collaborative work, there have been few empirical demonstrations of their effectiveness (Marshall et al., 2011). In particular, while lab-based studies have explored the effects of individual design features, there has been …
-
Taming Cloud Integrated Systems in the Wild
This thesis unfolds a journey into the realm of cloud integrated systems. More specifically, it explores the transformational role of diverse cloud infrastructure, be it public or private, centralized or edge-based, when integrated into traditional systems. In this transformation, the cloud assumes …
-
Invariant learning for learning in the wild
… a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-12-01
-
TOWARDS MULTI-MODAL FACE RECOGNITION IN THE WILD
Face recognition aims at utilizing the facial appearance for the identification or verification of human individuals, and has been one of the fundamental research areas in computer vision. Over the past a few decades, face recognition has drawn significant attention due to its potential use in …
Page 1 of 85