The College of Engineering and Computer Science: Recent submissions
Now showing items 1-20 of 184
-
Diffeomorphism matching for fast unsupervised pretraining on radiographs
(2020)Unsupervised pretraining is an approach that leverages a large unlabeled data pool to learn data features. However, it requires billion-scale datasets and a month-long training time to surpass its supervised counterpart ... -
Towards a comprehensive solution for a vision-based digitized neurological examination
(2022-08)The ability to use digitally recorded and quantified neurological exam information is important to help healthcare systems deliver better care, in-person and via telehealth, as they compensate for a growing shortage of ... -
Engineering a light–matter strong coupling regime in perovskite-based plasmonic metasurface: quasi-bound state in the continuum and exceptional points
(2020-12-14)We present theoretically the formation of exciton-photon polaritons and exciton-surface plasmon polaritons in perovskite-based subwavelength lattice on metallic plane. It is showed that the later polaritons will be achieved ... -
Improving transformers with probabilistic attention keys
(2022-06-13)Multi-head attention is a driving force behind state-of-the-art transformers, which achieve remarkable performance across a variety of natural language processing (NLP) and computer vision tasks. It has been observed that ... -
Task-oriented communication design in cyber-physical systems: A survey on theory and applications
(2023-05-25)Communication system design has been traditionally guided by task-agnostic principles, which aim at efficiently transmitting as many correct bits as possible through a given channel. However, in the era of cyber-physical ... -
Phase recognition in contrast-enhanced CT scans based on deep learning and random sampling
(2022-03-20)Purpose: A fully automated system for interpreting abdominal computed tomography (CT) scans with multiple phases of contrast enhancement requires an accurate classification of the phases. Current approaches to classify the ... -
Interpreting chest X-rays via CNNs that exploit hierarchical disease dependencies and uncertainty labels
(2020-06-12)Chest radiography is one of the most common types of diagnostic radiology exams, which is critical for screening and diagnosis of many different thoracic diseases. Specialized algorithms have been developed to detect several ... -
Impacts of retina-related zones on quality perception of omnidirectional image
(2019-11-18)Virtual Reality (VR), which brings immersive experiences to viewers, has been gaining popularity in recent years. A key feature in VR systems is the use of omnidirectional content, which provides 360-degree views of scenes. ... -
Network-aware prefetching method for short-form video streaming
(2022-09-07)Recent years have witnessed the rising of short-form video platforms such as TikTok. Apart from conventional videos, short-form videos are much shorter and users frequently change the content to watch. Thus, it is crucial ... -
Reinforced coloring for end-to-end instance segmentation
(2020-05-19)Instance segmentation is one of the actively studied research topics in computer vision in which many objects of interest should be separated individually. While many feed-forward networks produce high-quality segmentation ... -
Dual consistency assisted multi-confident learning for the hepatic vessel segmentation using noisy labels
(2022)Noisy hepatic vessel labels from Computer Tomography (CT) are popular due to vessels’ low-contrast and complex morphology. This is challenging for automatic hepatic vessel segmentation, which is essential to many hepatic ... -
Improving local features with relevant spatial information by vision transformer for crowd counting
(2022)Vision Transformer (ViT) variants have demonstrated state-of-the-art performances in plenty of computer vision benchmarks, including crowd counting. Although Transformer-based models have shown breakthroughs in crowd ... -
VinDr-CXR: An open dataset of chest X-rays with radiologist’s annotations
(2022-03-20)Most of the existing chest X-ray datasets include labels from a list of findings without specifying their locations on the radiographs. This limits the development of machine learning algorithms for the detection and ... -
A comparative study on mechanical properties of fully dense 420 stainless steel parts produced by modified binder jet printing
(2022-11-03)The mechanical properties of the parts produced by binder jet printing (BJP) are often considerably inferior to those of the parts produced by traditional manufacturing processes because BJP parts retain at best about 95% ... -
Joint Resource Allocation and Link Adaptation for Ultra-Reliable and Low-Latency Services
(2023)With the emergence of ultra-reliable and low latency communication (URLLC) services, link adaptation (LA) plays a pivotal role in improving the robustness and reliability of communication networks via appropriate modulation ... -
Robust educational dialogue act classifiers with low-resource and imbalanced datasets
(2023-04-15)Dialogue acts (DAs) can represent conversational actions of tutors or students that take place during tutoring dialogues. Automating the identification of DAs in tutoring dialogues is significant to the design of dialogue-based ... -
FEDGRAD: Mitigating backdoor attacks in federated learning through local ultimate gradients inspection
(2023-04-29)Federated learning (FL) enables multiple clients to train a model without compromising sensitive data. However, the decentralized nature of FL makes it susceptible to adversarial attacks, particularly backdoor insertion ... -
A survey on out-of-distribution evaluation of neural NLP models
(2023-06-27)Adversarial robustness, domain generalization, and dataset biases are three active lines of research contributing to out-of-distribution (OOD) evaluation on neural NLP models. However, a comprehensive, integrated discussion ... -
Efficient human vision inspired action recognition using adaptive spatiotemporal sampling
(2022-07-14)Adaptive sampling that exploits the spatiotemporal redundancy in videos is critical for always-on action recognition on wearable devices with limited computing and battery resources. The commonly used fixed sampling strategy ... -
Revisiting reverse distillation for anomaly detection
(2023)Anomaly detection is an important application in large-scale industrial manufacturing. Recent methods for this task have demonstrated excellent accuracy but come with a latency trade-off. Memory based approaches with ...
