Related papers: Part Aware Contrastive Learning for Self-Supervise…
Skeleton sequence representation learning has shown great advantages for action recognition due to its promising ability to model human joints and topology. However, the current methods usually require sufficient labeled data for training…
Supervised learning for semantic segmentation requires a large number of labeled samples, which is difficult to obtain in the field of remote sensing. Self-supervised learning (SSL), can be used to solve such problems by pre-training a…
High-quality representation of transactional sequences is vital for modern banking applications, including risk management, churn prediction, and personalized customer offers. Different tasks require distinct representation properties:…
Contrastive learning has nearly closed the gap between supervised and self-supervised learning of image representations, and has also been explored for videos. However, prior work on contrastive learning for video data has not explored the…
Neural networks exhibit severe brittleness to semantically irrelevant transformations. A mere 75ms electrocardiogram (ECG) phase shift degrades latent cosine similarity from 1.0 to 0.2, while sensor rotations collapse activity recognition…
Self-supervised learning approach like contrastive learning is attached great attention in natural language processing. It uses pairs of training data augmentations to build a classification task for an encoder with well representation…
Human action recognition in 3D skeleton sequences has attracted a lot of research attention. Recently, Long Short-Term Memory (LSTM) networks have shown promising performance in this task due to their strengths in modeling the dependencies…
Graph convolutional networks (GCNs) achieved promising performance in skeleton-based human action recognition by modeling a sequence of skeletons as a spatio-temporal graph. Most of the recently proposed GCN-based methods improve the…
Facial action unit (AU) detection and face alignment are two highly correlated tasks since facial landmarks can provide precise AU locations to facilitate the extraction of meaningful local features for AU detection. Most existing AU…
Supervised learning-based adversarial attack detection methods rely on a large number of labeled data and suffer significant performance degradation when applying the trained model to new domains. In this paper, we propose a self-supervised…
We present MaCLR, a novel method to explicitly perform cross-modal self-supervised video representations learning from visual and motion modalities. Compared to previous video representation learning methods that mostly focus on learning…
Action recognition with skeleton data has recently attracted much attention in computer vision. Previous studies are mostly based on fixed skeleton graphs, only capturing local physical dependencies among joints, which may miss implicit…
The data-driven approach that learns an optimal representation of vision features like skeleton frames or RGB videos is currently a dominant paradigm for activity recognition. While great improvements have been achieved from existing single…
Self-supervised learning has gained popularity because of its ability to avoid the cost of annotating large-scale datasets. It is capable of adopting self-defined pseudo labels as supervision and use the learned representations for several…
Disease diagnosis from medical images via supervised learning is usually dependent on tedious, error-prone, and costly image labeling by medical experts. Alternatively, semi-supervised learning and self-supervised learning offer…
Facial action unit (AU) detection, aiming to classify AU present in the facial image, has long suffered from insufficient AU annotations. In this paper, we aim to mitigate this data scarcity issue by learning AU representations from a large…
Graph clustering is essential in graph analysis for revealing structural patterns and node communities. Despite recent advances in self-supervised contrastive learning that have improved clustering via structural and attribute signals,…
Facial action unit (AU) detection and face alignment are two highly correlated tasks, since facial landmarks can provide precise AU locations to facilitate the extraction of meaningful local features for AU detection. However, most existing…
Recently, there have been efforts to improve the performance in sign language recognition by designing self-supervised learning methods. However, these methods capture limited information from sign pose data in a frame-wise learning manner,…
Whilst contrastive learning has recently brought notable benefits to deep clustering of unlabelled images by learning sample-specific discriminative visual features, its potential for explicitly inferring class decision boundaries is less…