Related papers: SteelDefectX: A Multi-Form Vision-Language Dataset…
Benchmark datasets play an important role in evaluating Natural Language Understanding (NLU) models. However, shortcuts -- unwanted biases in the benchmark datasets -- can damage the effectiveness of benchmark datasets in revealing models'…
Multilingual document and scene text understanding plays an important role in applications such as search, finance, and public services. However, most existing benchmarks focus on high-resource languages and fail to evaluate models in…
Vision-Language Models (VLMs) achieve strong cross-modal performance, yet recent evidence suggests they over-rely on textual descriptions while under-utilizing visual evidence -- a phenomenon termed ``text shortcut learning.'' We propose an…
Structured-output learning is a challenging problem; particularly so because of the difficulty in obtaining large datasets of fully labelled instances for training. In this paper we try to overcome this difficulty by presenting a…
Quality inspection in smart manufacturing requires identifying intrinsic material and surface properties beyond visible geometry, yet vision-only methods remain vulnerable to occlusion and reflection. We propose VitaTouch, a property-aware…
Referring image segmentation is a challenging task that involves generating pixel-wise segmentation masks based on natural language descriptions. The complexity of this task increases with the intricacy of the sentences provided. Existing…
Language-conditioned robotic manipulation in open-world settings requires not only accurate task execution but also the ability to detect failures for robust deployment in real-world environments. Although recent advances in vision-language…
Recent progress in large-scale pre-training has led to the development of advanced vision-language models (VLMs) with remarkable proficiency in comprehending and generating multimodal content. Despite the impressive ability to perform…
Despite recent progress on the short-video Text-Visual Question Answering (ViteVQA) task - largely driven by benchmarks such as M4-ViteVQA - existing datasets still suffer from limited video duration and narrow evaluation scopes, making it…
Construction safety inspections typically involve a human inspector identifying safety concerns on-site. With the rise of powerful Vision Language Models (VLMs), researchers are exploring their use for tasks such as detecting safety rule…
Surface defect detection is a critical task across numerous industries, aimed at efficiently identifying and localising imperfections or irregularities on manufactured components. While numerous methods have been proposed, many fail to meet…
Describing images with text is a fundamental problem in vision-language research. Current studies in this domain mostly focus on single image captioning. However, in various real applications (e.g., image editing, difference interpretation,…
Despite the significant impact of visual events on human cognition, understanding events in videos remains a challenging task for AI due to their complex structures, semantic hierarchies, and dynamic evolution. To address this, we propose…
Scaling up the vocabulary of semantic segmentation models is extremely challenging because annotating large-scale mask labels is labour-intensive and time-consuming. Recently, language-guided segmentation models have been proposed to…
Industrial diagrams such as piping and instrumentation diagrams (P&IDs) are essential for the design, operation, and maintenance of industrial plants. Converting these diagrams into digital form is an important step toward building digital…
Language plays a critical role in Vision-Language-Action (VLA) models, yet the linguistic characteristics of the datasets used to train and evaluate these systems remain poorly documented. In this work, we present a systematic dataset audit…
Visual captioning benchmarks have become outdated with the emergence of modern multimodal large language models (MLLMs), as the brief ground-truth sentences and traditional metrics fail to assess detailed captions effectively. While recent…
Visualizations help communicate data insights, but deceptive data representations can distort their interpretation and propagate misinformation. While recent Vision Language Models (VLMs) perform well on many chart understanding tasks,…
Few-Shot Industrial Anomaly Detection (FS-IAD) has important applications in automating industrial quality inspection. Recently, some FS-IAD methods based on Large Vision-Language Models (LVLMs) have been proposed with some achievements…
A key algorithm for understanding the world is material segmentation, which assigns a label (metal, glass, etc.) to each pixel. We find that a model trained on existing data underperforms in some settings and propose to address this with a…