Related papers: PARL: Position-Aware Relation Learning Network for…

Multimodal document retrieval aims to identify and retrieve various forms of multimodal content, such as figures, tables, charts, and layout information from extensive documents. Despite its increasing popularity, there is a notable lack of…

Recently, large-scale visual language pre-trained (VLP) models have demonstrated impressive performance across various downstream tasks. Motivated by these advancements, pioneering efforts have emerged in multi-label image recognition with…

Vision-language models like CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions because of their training focus on short and concise captions. We present…

Optical character recognition (OCR) and multilingual text understanding remain major failure modes of multimodal large language models (MLLMs), particularly in real-world images containing cluttered layouts, small fonts, blur, occlusion,…

Document extraction is an important step before retrieval-augmented generation (RAG), knowledge bases, and downstream generative AI can work. It turns unstructured documents like PDFs and scans into structured text and layout-aware…

Although Large Vision-Language Models (LVLMs) have achieved impressive results, their high computational costs pose a significant barrier to wide application. To enhance inference efficiency, most existing approaches can be categorized as…

Large language models (LLMs) enhanced with retrieval-augmented generation (RAG) have introduced a new paradigm for web search. However, the limited context awareness of LLMs degrades their performance on RAG tasks. Existing methods to…

Computer-aided medical image analysis is crucial for disease diagnosis and treatment planning, yet limited annotated datasets restrict medical-specific model development. While vision-language models (VLMs) like CLIP offer strong…

Content-aware layout aims to arrange design elements appropriately on a given canvas to convey information effectively. Recently, the trend for this task has been to leverage large language models (LLMs) to generate layouts automatically,…

Node classification on graphs is of great importance in many applications. Due to the limited labeling capability and evolution in real-world open scenarios, novel classes can emerge on unlabeled testing nodes. However, little attention has…

Pedestrian attribute recognition (PAR) has received increasing attention because of its wide application in video surveillance and pedestrian analysis. Extracting robust feature representation is one of the key challenges in this task. The…

Multi-objective decision-making problems have emerged in numerous real-world scenarios, such as video games, navigation and robotics. Considering the clear advantages of Reinforcement Learning (RL) in optimizing decision-making processes,…

While Large Language Models (LLMs) and Vision-Language Models (VLMs) demonstrate remarkable capabilities in high-level reasoning and semantic understanding, applying them directly to contact-rich manipulation remains a challenge due to…

Relational tables on the Web store a vast amount of knowledge. Owing to the wealth of such tables, there has been tremendous progress on a variety of tasks in the area of table understanding. However, existing work generally relies on…

Vision-Language Pretraining (VLP) has achieved remarkable success across various downstream tasks, but such gains are largely driven by scaling up on training data. Yet, literature methods treat image-text pairs as isolated training…

Causal deep learning (CDL) is a new and important research area in the larger field of machine learning. With CDL, researchers aim to structure and encode causal knowledge in the extremely flexible representation space of deep learning…

Harnessing the full potential of visually-rich documents requires retrieval systems that understand not just text, but intricate layouts, a core challenge in Visual Document Retrieval (VDR). The prevailing multi-vector architectures, while…

In order to efficiently learn with small amount of data on new tasks, meta-learning transfers knowledge learned from previous tasks to the new ones. However, a critical challenge in meta-learning is the task heterogeneity which cannot be…

Tables are pervasive in diverse documents, making table recognition (TR) a fundamental task in document analysis. Existing modular TR pipelines separately model table structure and content, leading to suboptimal integration and complex…

This paper presents a deep architecture for dense semantic correspondence, called pyramidal affine regression networks (PARN), that estimates locally-varying affine transformation fields across images. To deal with intra-class appearance…