Abstract Human Pose Estimation (HPE) is widely used in various fields, including motion
analysis, healthcare, and virtual reality. However, the great expenses of labeled real-world …

Unconstrained facial emotion recognition has been an active and challenging research over
the past decades. Understanding human emotions and enhancing the functionality of …

State-of-the-art pre-trained image models predominantly adopt a two-stage approach: initial
unsupervised pre-training on large-scale datasets followed by task-specific fine-tuning using …

Recently supervised contrastive learning (SCL) has achieved remarkable progress in
semantic segmentation. Nevertheless, prior works have often necessitated a substantial …

Multi-view clustering (MVC) can explore common semantics from multiple views and has
been extensively used to support management with unsupervised training data. However …

The combination of semi-supervised learning (SemiSL) and contrastive learning (CL) has
been successful in medical image segmentation with limited annotations. However, these …

A thorough comprehension of textual data is a fundamental element in multi-modal video
analysis tasks. However, recent works have shown that the current models do not achieve a …

Detecting implicit hate speech that is not directly hateful remains a challenge. Recent
research has attempted to detect implicit hate speech by applying contrastive learning to pre …

The brain-inspired Spiking Neural Networks (SNNs) offer a promising event-driven and low-
power approach to deep learning. Self-attention (SA) mechanism, the cornerstone of the …

For a widely-studied data model and general loss and sample-hardening functions we prove
that the Supervised Contrastive Learning (SCL), Hard-SCL (HSCL), and Unsupervised …