Related papers: Semantically Encoding Activity Labels for Context-…
In text classification tasks, useful information is encoded in the label names. Label semantic aware systems have leveraged this information for improved text classification performance during fine-tuning and prediction. However, use of…
Human Activity Recognition (HAR) is a well-studied field with research dating back to the 1980s. Over time, HAR technologies have evolved significantly from manual feature extraction, rule-based algorithms, and simple machine learning…
Sequence classification is the supervised learning task of building models that predict class labels of unseen sequences of symbols. Although accuracy is paramount, in certain scenarios interpretability is a must. Unfortunately, such…
The number of categories for action recognition is growing rapidly. It is thus becoming increasingly hard to collect sufficient training data to learn conventional models for each category. This issue may be ameliorated by the increasingly…
Speech representation learning approaches for non-semantic tasks such as language recognition have either explored supervised embedding extraction methods using a classifier model or self-supervised representation learning approaches using…
Recent achievements in language models have showcased their extraordinary capabilities in bridging visual information with semantic language understanding. This leads us to a novel question: can language models connect textual semantics…
The objective of active learning (AL) is to train classification models with less number of labeled instances by selecting only the most informative instances for labeling. The AL algorithms designed for other data types such as images and…
Deep learning approaches achieve state-of-the-art performance for classifying radiology images, but rely on large labelled datasets that require resource-intensive annotation by specialists. Both semi-supervised learning and active learning…
Knowledge-based conversational question answering (KBCQA) confronts persistent challenges in resolving coreference, modeling contextual dependencies, and executing complex logical reasoning. Existing approaches often suffer from…
Few-shot action recognition (FSAR) aims to classify human actions in videos with only a small number of labeled samples per category. The scarcity of training data has driven recent efforts to incorporate additional modalities, particularly…
Different from traditional video retrieval, sign language retrieval is more biased towards understanding the semantic information of human actions contained in video clips. Previous works typically only encode RGB videos to obtain…
Human activity recognition (HAR) by wearable sensor devices embedded in the Internet of things (IOT) can play a significant role in remote health monitoring and emergency notification, to provide healthcare of higher standards. The purpose…
Human activity recognition (HAR) in wearable computing is typically based on direct processing of sensor data. Sensor readings are translated into representations, either derived through dedicated preprocessing, or integrated into…
As of today, state-of-the-art activity recognition from wearable sensors relies on algorithms being trained to classify fixed windows of data. In contrast, video-based Human Activity Recognition, known as Temporal Action Localization (TAL),…
Mobile and wearable devices have enabled numerous applications, including activity tracking, wellness monitoring, and human--computer interaction, that measure and improve our daily lives. Many of these applications are made possible by…
Sensor-based human activity recognition (HAR) has been an active research area, owing to its applications in smart environments, assisted living, fitness, healthcare, etc. Recently, deep learning based end-to-end training has resulted in…
Deep learning methods are successfully used in applications pertaining to ubiquitous computing, health, and well-being. Specifically, the area of human activity recognition (HAR) is primarily transformed by the convolutional and recurrent…
Human Activity Recognition (HAR) is a challenging, multi-label classification problem as activities may co-occur and sensor signals corresponding to the same activity may vary in different contexts (e.g., different device placements). This…
Radar systems are increasingly favored for medical applications because they provide non-intrusive monitoring with high privacy and robustness to lighting conditions. However, existing research typically relies on single-domain radar…
Zero-Shot Learning (ZSL) presents the challenge of identifying categories not seen during training. This task is crucial in domains where it is costly, prohibited, or simply not feasible to collect training data. ZSL depends on a mapping…