Related papers: Contrastive Learning for Multimodal Human Activity…
Human activity recognition using smart home sensors is one of the bases of ubiquitous computing in smart environments and a topic undergoing intense research in the field of ambient assisted living. The increasingly large amount of data…
The availability of large, unlabeled datasets across various domains has contributed to the development of a plethora of methods that learn representations for multiple target (downstream) tasks through self-supervised pre-training. In this…
Using supervised machine learning approaches to recognize human activities from on-body wearable accelerometers generally requires a large amount of labelled data. When ground truth information is not available, too expensive, time…
Recently, transfer subspace learning based approaches have shown to be a valid alternative to unsupervised subspace clustering and temporal data clustering for human motion segmentation (HMS). These approaches leverage prior knowledge from…
Language-supervised vision models have recently attracted great attention in computer vision. A common approach to build such models is to use contrastive learning on paired data across the two modalities, as exemplified by Contrastive…
3D skeleton-based motion prediction and activity recognition are two interwoven tasks in human behaviour analysis. In this work, we propose a motion context modeling methodology that provides a new way to combine the advantages of both…
Inspired by recent advances in neural machine translation, that jointly align and translate using encoder-decoder networks equipped with attention, we propose an attentionbased LSTM model for human activity recognition. Our model jointly…
Deep learning has been successfully applied to human activity recognition. However, training deep neural networks requires explicitly labeled data which is difficult to acquire. In this paper, we present a model with multiple siamese…
With the rapid development of digital multimedia, video understanding has become an important field. For action recognition, temporal dimension plays an important role, and this is quite different from image recognition. In order to learn…
Labeled data used for training activity recognition classifiers are usually limited in terms of size and diversity. Thus, the learned model may not generalize well when used in real-world use cases. Semi-supervised learning augments labeled…
Human Activity Recognition (HAR) using Inertial Measurement Unit (IMU) sensors is critical for applications in healthcare, safety, and industrial production. However, variations in activity patterns, device types, and sensor placements…
Animal pose estimation is challenging for existing image-based methods because of limited training data and large intra- and inter-species variances. Motivated by the progress of visual-language research, we propose that pre-trained…
Multimodal contrastive learning (MCL) has shown remarkable advances in zero-shot classification by learning from millions of image-caption pairs crawled from the Internet. However, this reliance poses privacy risks, as hackers may…
How can we teach a computer to recognize 10,000 different actions? Deep learning has evolved from supervised and unsupervised to self-supervised approaches. In this paper, we present a new contrastive learning-based framework for decision…
Correlation exploitation is essential for efficient multi-user channel estimation (MUCE) in massive MIMO systems. However, the existing works either rely on presumed strong correlation or learn the correlation through large amount of…
Human action recognition refers to automatic recognizing human actions from a video clip. In reality, there often exist multiple human actions in a video stream. Such a video stream is often weakly-annotated with a set of relevant human…
Human mobility clustering is an important problem for understanding human mobility behaviors (e.g., work and school commutes). Existing methods typically contain two steps: choosing or learning a mobility representation and applying a…
Multimodal fusion frameworks for Human Action Recognition (HAR) using depth and inertial sensor data have been proposed over the years. In most of the existing works, fusion is performed at a single level (feature level or decision level),…
Fine-tuning pre-trained language models (PLMs) has demonstrated its effectiveness on various downstream NLP tasks recently. However, in many low-resource scenarios, the conventional fine-tuning strategies cannot sufficiently capture the…
Videos are inherently multimodal. This paper studies the problem of how to fully exploit the abundant multimodal clues for improved video categorization. We introduce a hybrid deep learning framework that integrates useful clues from…