相关论文: Reverse Region-to-Entity Annotation for Pixel-Leve…

Active learning enhances annotation efficiency by selecting the most revealing samples for labeling, thereby reducing reliance on extensive human input. Previous methods in semantic segmentation have centered on individual pixels or small…

Visual grounding localizes regions (boxes or segments) in the image corresponding to given referring expressions. In this work we address image segmentation from referring expressions, a problem that has so far only been addressed in a…

Dominant pre-training work for video-text retrieval mainly adopt the "dual-encoder" architectures to enable efficient retrieval, where two separate encoders are used to contrast global video and text representations, but ignore detailed…

Understanding the semantic meaning of tabular data requires Entity Linking (EL), in order to associate each cell value to a real-world entity in a Knowledge Base (KB). In this work, we focus on end-to-end solutions for EL on tabular data…

Entity Linking aims to link entity mentions in texts to knowledge bases, and neural models have achieved recent success in this task. However, most existing methods rely on local contexts to resolve entities independently, which may usually…

Instance segmentation methods often require costly per-pixel labels. We propose a method that only requires point-level annotations. During training, the model only has access to a single pixel label per object, yet the task is to output…

Semantic segmentation aims to classify every pixel of an input image. Considering the difficulty of acquiring dense labels, researchers have recently been resorting to weak labels to alleviate the annotation burden of segmentation. However,…

Open-domain visual entity recognition aims to identify and link entities depicted in images to a vast and evolving set of real-world concepts, such as those found in Wikidata. Unlike conventional classification tasks with fixed label sets,…

Recent generalist vision-language models (VLMs) have demonstrated impressive reasoning capabilities across diverse multimodal tasks. However, these models still struggle with fine-grained object-level understanding and grounding. In terms…

Deep learning stands at the forefront in many computer vision tasks. However, deep neural networks are usually data-hungry and require a huge amount of well-annotated training samples. Collecting sufficient annotated data is very expensive…

Visual localization is of great importance in robotics and computer vision. Recently, scene coordinate regression based methods have shown good performance in visual localization in small static scenes. However, it still estimates camera…

Entity Linking (EL) is the process of associating ambiguous textual mentions to specific entities in a knowledge base. Traditional EL methods heavily rely on large datasets to enhance their performance, a dependency that becomes problematic…

Referring Expression Comprehension (REC) aims to localize specified entities or regions in an image based on natural language descriptions. While existing methods handle single-entity localization, they often ignore complex inter-entity…

The performance of deep learning based semantic segmentation models heavily depends on sufficient data with careful annotations. However, even the largest public datasets only provide samples with pixel-level annotations for rather limited…

There have been remarkable improvements in the semantic labelling task in the recent years. However, the state of the art methods rely on large-scale pixel-level annotations. This paper studies the problem of training a pixel-wise semantic…

Entity linking (EL) aligns textual mentions with their corresponding entities in a knowledge base, facilitating various applications such as semantic search and question answering. Recent advances in multimodal entity linking (MEL) have…

Multimodal Entity Linking (MEL) aims to associate textual and visual mentions with entities in a multimodal knowledge graph. Despite its importance, current methods face challenges such as incomplete contextual information, coarse…

Cross-modal alignment is one key challenge for Vision-and-Language Navigation (VLN). Most existing studies concentrate on mapping the global instruction or single sub-instruction to the corresponding trajectory. However, another critical…

Current autoregressive Vision Language Models (VLMs) usually rely on a large number of visual tokens to represent images, resulting in a need for more compute especially at inference time. To address this problem, we propose Mask-LLaVA, a…

Despite recent progress, vision-language encoders struggle with two core limitations: (1) weak alignment between language and dense vision features, which hurts tasks like open-vocabulary semantic segmentation; and (2) high token counts for…