Related papers: SITUATE -- Synthetic Object Counting Dataset for V…

Vision-language models (VLMs) work well in tasks ranging from image captioning to visual question answering (VQA), yet they struggle with spatial reasoning, a key skill for understanding our physical world that humans excel at. We find that…

Vision-Language Models (VLMs) excel at multimodal reasoning, yet it remains unclear whether their answers are grounded in visual evidence or driven by learned language and world priors. Counting provides a precise testbed: when visual…

While table understanding increasingly relies on pixel-only settings, current benchmarks predominantly use synthetic renderings that lack the complexity and visual diversity of real-world tables. Additionally, existing visual table…

Object counting is a foundational vision task with over a decade of dedicated research, yet state-of-the-art models still fail systematically in the mixed-object setting that dominates real-world applications such as industrial inspection…

Visually-grounded spoken language datasets can enable models to learn cross-modal correspondences with very weak supervision. However, modern audio-visual datasets contain biases that undermine the real-world performance of models trained…

Vision-language temporal alignment is a crucial capability for human dynamic recognition and cognition in real-world scenarios. While existing research focuses on capturing vision-language relevance, it faces limitations due to biased…

Effectively understanding urban scenes requires fine-grained spatial reasoning about objects, layouts, and depth cues. However, how well current vision-language models (VLMs), pretrained on general scenes, transfer these abilities to urban…

Fine-tuning Vision-Language Models (VLMs) is a common strategy to improve performance following an ad-hoc data collection and annotation of real-world scenes. However, this process is often prone to biases, errors, and distribution…

Counting the number of items in a visual scene remains a fundamental yet challenging task in computer vision. Traditional approaches to solving this problem rely on domain-specific counting architectures, which are trained using datasets…

Despite the rapid development of Chinese vision-language models (VLMs), most existing Chinese vision-language (VL) datasets are constructed on Western-centric images from existing English VL datasets. The cultural bias in the images makes…

Object state recognition aims to identify the specific condition of objects, such as their positional states (e.g., open or closed) and functional states (e.g., on or off). While recent Vision-Language Models (VLMs) are capable of…

While Vision-Language Models (VLMs) have achieved competitive performance in various tasks, their comprehension of the underlying structure and semantics of a scene remains understudied. To investigate the understanding of VLMs, we study…

Vision-Language Models (VLMs) have recently gained attention due to their competitive performance on multiple downstream tasks, achieved by following user-input instructions. However, VLMs still exhibit several limitations in visual…

Diffusion models excel at photorealistic synthesis but struggle with precise object counts, especially in high-density settings. We introduce COUNTLOOP, a training-free framework that achieves precise instance control through iterative,…

Integration of Large Language Models (LLMs) into visual domain tasks, resulting in visual-LLMs (V-LLMs), has enabled exceptional performance in vision-language tasks, particularly for visual question answering (VQA). However, existing…

Prompt tuning, which involves training a small set of parameters, effectively enhances the pre-trained Vision-Language Models (VLMs) to downstream tasks. However, they often come at the cost of flexibility and adaptability when the tuned…

Text Image Machine Translation (TIMT) aims to translate texts embedded within an image into another language. Current TIMT studies primarily focus on providing translations for all the text within an image, while neglecting to provide…

We introduce and formalize the Synthetic Dataset Quality Estimation (SynQuE) problem: ranking synthetic datasets by their expected real-world task performance using only limited unannotated real data. This addresses a critical and open…

Density map estimation enables accurate object counting in heavily occluded, and densely packed scenes where detection-based counting fails. In multi-class density estimation, class awareness can be introduced by modelling classes…

Capturing spatial relationships from visual inputs is a cornerstone of human-like general intelligence. Several previous studies have tried to enhance the spatial awareness of Vision-Language Models (VLMs) by adding extra expert encoders,…