Related papers: Hierarchical Insights: Exploiting Structural Simil…

Scene labeling is the problem of assigning an object label to each pixel. It unifies the image segmentation and object recognition problems. The importance of using contextual information in scene labeling frameworks has been widely…

We present a novel hierarchical model for human activity recognition. In contrast to approaches that successively recognize actions and activities, our approach jointly models actions and activities in a unified framework, and their labels…

Most existing metric learning methods focus on learning a similarity or distance measure relying on similar and dissimilar relations between sample pairs. However, pairs of samples cannot be simply identified as similar or dissimilar in…

It is well known that semantic segmentation can be used as an effective intermediate representation for learning driving policies. However, the task of street scene semantic segmentation requires expensive annotations. Furthermore,…

LiDAR semantic segmentation plays a pivotal role in 3D scene understanding for edge applications such as autonomous driving. However, significant challenges remain for real-world deployments, particularly for on-device post-deployment…

Deep-learning based computer vision models have proved themselves to be ground-breaking approaches to human activity recognition (HAR). However, most existing works are dedicated to improve the prediction accuracy through either creating…

Continual learning (CL) enables models to adapt to new tasks and environments without forgetting previously learned knowledge. While current CL setups have ignored the relationship between labels in the past task and the new task with or…

Numerous embedding models have been recently explored to incorporate semantic knowledge into visual recognition. Existing methods typically focus on minimizing the distance between the corresponding images and texts in the embedding space…

In autonomous driving, 3D LiDAR plays a crucial role in understanding the vehicle's surroundings. However, the newly emerged, unannotated objects presents few-shot learning problem for semantic segmentation. This paper addresses the…

Hierarchical classification aims to sort the object into a hierarchical structure of categories. For example, a bird can be categorized according to a three-level hierarchy of order, family, and species. Existing methods commonly address…

Language recognition system is typically trained directly to optimize classification error on the target language labels, without using the external, or meta-information in the estimation of the model parameters. However labels are not…

Many sectors nowadays require accurate and coherent predictions across their organization to effectively operate. Otherwise, decision-makers would be planning using disparate views of the future, resulting in inconsistent decisions across…

Much effort has been devoted to evaluate whether multi-task learning can be leveraged to learn rich representations that can be used in various Natural Language Processing (NLP) down-stream applications. However, there is still a lack of…

Recent advances in Hierarchical Multi-label Classification (HMC), particularly neurosymbolic-based approaches, have demonstrated improved consistency and accuracy by enforcing constraints on a neural model during training. However, such…

Semantic segmentation consists of predicting a semantic label for each image pixel. While existing deep learning approaches achieve high accuracy, they often overlook the ordinal relationships between classes, which can provide critical…

Current contrastive learning frameworks focus on leveraging a single supervisory signal to learn representations, which limits the efficacy on unseen data and downstream tasks. In this paper, we present a hierarchical multi-label…

Robots are expected to operate autonomously in dynamic environments. Understanding the underlying dynamic characteristics of objects is a key enabler for achieving this goal. In this paper, we propose a method for pointwise semantic…

Semantic segmentation models only perform well on the domain they are trained on and datasets for training are scarce and often have a small label-spaces, because the pixel level annotations required are expensive to make. Thus training…

Remote sensing image segmentation faces persistent challenges in distinguishing morphologically similar categories and adapting to diverse scene variations. While existing methods rely on implicit representation learning paradigms, they…

Multi-label learning has attracted significant interests in computer vision recently, finding applications in many vision tasks such as multiple object recognition and automatic image annotation. Associating multiple labels to a complex…