Related papers: Semantic-Aware Representation Learning via Conditi…

Spatial reasoning from monocular images is essential for autonomous driving, yet current Vision-Language Models (VLMs) still struggle with fine-grained geometric perception, particularly under large scale variation and ambiguous object…

Multi-label learning handles instances associated with multiple class labels. The original label space is a logical matrix with entries from the Boolean domain $\in \left \{ 0,1 \right \}$. Logical labels are not able to show the relative…

Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics. Learning-based methods, such as deep reinforcement learning, have the potential to outperform the classical solutions developed for this…

Real-world recognition system often encounters the challenge of unseen labels. To identify such unseen labels, multi-label zero-shot learning (ML-ZSL) focuses on transferring knowledge by a pre-trained textual label embedding (e.g., GloVe).…

Sign language translation (SLT) aims to convert continuous sign language videos into textual sentences. As a typical multi-modal task, there exists an inherent modality gap between sign language videos and spoken language text, which makes…

Previous works on multi-label image recognition (MLIR) usually use CNNs as a starting point for research. In this paper, we take pure Vision Transformer (ViT) as the research base and make full use of the advantages of Transformer with…

Current multimodal LLMs encode images as static visual prefixes and rely on text-based reasoning, lacking goal-driven and adaptive visual access. Inspired by human visual perception-where attention is selectively and sequentially shifted…

This paper describes a novel method of training a semantic segmentation model for scene recognition of agricultural mobile robots exploiting publicly available datasets of outdoor scenes that are different from the target greenhouse…

Generating schema labels automatically for column values of data tables has many data science applications such as schema matching, and data discovery and linking. For example, automatically extracted tables with missing headers can be…

We develop methods for detector learning which exploit joint training over both weak and strong labels and which transfer learned perceptual representations from strongly-labeled auxiliary tasks. Previous methods for weak-label learning…

Recent approaches for instance-aware semantic labeling have augmented convolutional neural networks (CNNs) with complex multi-task architectures or computationally expensive graphical models. We present a method that leverages a fully…

This paper proposes a new transformer-based framework to learn class-specific object localization maps as pseudo labels for weakly supervised semantic segmentation (WSSS). Inspired by the fact that the attended regions of the one-class…

Semantic segmentation has made significant strides in pixel-level image understanding, yet it remains limited in capturing contextual and semantic relationships between objects. Current models, such as CNN and Transformer-based…

Semantic segmentation methods have achieved outstanding performance thanks to deep learning. Nevertheless, when such algorithms are deployed to new contexts not seen during training, it is necessary to collect and label scene-specific data…

This paper studies a text classification algorithm based on an improved Transformer to improve the performance and efficiency of the model in text classification tasks. Aiming at the shortcomings of the traditional Transformer model in…

Continually learning to segment more and more types of image regions is a desired capability for many intelligent systems. However, such continual semantic segmentation suffers from the same catastrophic forgetting issue as in continual…

In this paper, we propose a novel approach for learning multi-label classifiers with the help of privileged information. Specifically, we use similarity constraints to capture the relationship between available information and privileged…

Deep learning models obtain impressive accuracy in road scenes understanding, however they need a large quantity of labeled samples for their training. Additionally, such models do not generalise well to environments where the statistical…

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,…

Research on continual learning has led to a variety of approaches to mitigating catastrophic forgetting in feed-forward classification networks. Until now surprisingly little attention has been focused on continual learning of recurrent…