Related papers: CrossFormer: Cross-Segment Semantic Fusion for Doc…

The combination of audio and vision has long been a topic of interest in the multi-modal community. Recently, a new audio-visual segmentation (AVS) task has been introduced, aiming to locate and segment the sounding objects in a given…

Document understanding is critical for applications from financial analysis to scientific discovery. Current approaches, whether OCR-based pipelines feeding Large Language Models (LLMs) or native Multimodal LLMs (MLLMs), face key…

Real-world image super-resolution (Real-ISR) has achieved a remarkable leap by leveraging large-scale text-to-image models, enabling realistic image restoration from given recognition textual prompts. However, these methods sometimes fail…

Existing semantic segmentation approaches either aim to improve the object's inner consistency by modeling the global context, or refine objects detail along their boundaries by multi-scale feature fusion. In this paper, a new paradigm for…

Low computational complexity and high segmentation accuracy are both essential to the real-world semantic segmentation tasks. However, to speed up the model inference, most existing approaches tend to design light-weight networks with a…

Referring image segmentation aims at segmenting the foreground masks of the entities that can well match the description given in the natural language expression. Previous approaches tackle this problem using implicit feature interaction…

Large Language Models (LLMs) are limited by their parametric knowledge, leading to hallucinations in knowledge-extensive tasks. To address this, Retrieval-Augmented Generation (RAG) incorporates external document chunks to expand LLM…

Importance of document clustering is now widely acknowledged by researchers for better management, smart navigation, efficient filtering, and concise summarization of large collection of documents like World Wide Web (WWW). The next…

Interactive image segmentation enables annotators to efficiently perform pixel-level annotation for segmentation tasks. However, the existing interactive segmentation pipeline suffers from inefficient computations of interactive models…

With the increasing adoption of Large Language Models (LLMs) and Vision-Language Models (VLMs), rich document analysis technologies for applications like Retrieval-Augmented Generation (RAG) and visual RAG are gaining significant attention.…

Traditional topic modeling assigns a single topic to each document. In practice, however, many real-world documents, such as product reviews or open-ended survey responses, contain multiple distinct topics. This mismatch often leads to…

Long-context question answering over narrative tasks is challenging because correct answers often hinge on reconstructing a coherent timeline of events while preserving contextual f low in a limited context window. Retrievalaugmented…

Multi-scale architecture, including hierarchical vision transformer, has been commonly applied to high-resolution semantic segmentation to deal with computational complexity with minimum performance loss. In this paper, we propose a novel…

Text-based image segmentation aims to delineate object boundaries within an image from text prompts, offering higher flexibility and broader application scope compared to traditional fixed-category segmentation tasks. Recent studies have…

Representing structured text from complex documents typically calls for different machine learning techniques, such as language models for paragraphs and convolutional neural networks (CNNs) for table extraction, which prohibits drawing…

Algorithms for the action segmentation task typically use temporal models to predict what action is occurring at each frame for a minute-long daily activity. Recent studies have shown the potential of Transformer in modeling the relations…

Transformers achieve promising performance in document understanding because of their high effectiveness and still suffer from quadratic computational complexity dependency on the sequence length. General efficient transformers are…

2D images and 3D point clouds are foundational data types for multimedia applications, including real-time video analysis, augmented reality (AR), and 3D scene understanding. Class-incremental semantic segmentation (CSS) requires…

Canonical morphological segmentation is the process of analyzing words into the standard (aka underlying) forms of their constituent morphemes. This is a core task in language documentation, and NLP systems have the potential to…

Diffusion models are primarily trained for image synthesis, yet their denoising trajectories encode rich, spatially aligned visual priors. In this paper, we demonstrate that these priors can be utilized for text-conditioned semantic and…