Related papers: TreeSeg: Hierarchical Topic Segmentation of Large …

We present REM, a framework for segmenting a wide range of concepts in video that can be described through natural language. Our method leverages the universal visual-language mapping learned by video diffusion models on Internet-scale data…

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by incorporating external knowledge, particularly for long-tail domains such as literary works. However, the critical step of document segmentation in RAG remains…

Segmenting an object in a video presents significant challenges. Each pixel must be accurately labelled, and these labels must remain consistent across frames. The difficulty increases when the segmentation is with arbitrary granularity,…

Accurate segmentation of tubular structures in medical images, such as vessels and airway trees, is crucial for computer-aided diagnosis, radiotherapy, and surgical planning. However, significant challenges exist in algorithm design when…

Zero-resource speech technology is a growing research area that aims to develop methods for speech processing in the absence of transcriptions, lexicons, or language modelling text. Early term discovery systems focused on identifying…

Livestream videos have become a significant part of online learning, where design, digital marketing, creative painting, and other skills are taught by experienced experts in the sessions, making them valuable materials. However, Livestream…

We study the problem of learning a hierarchical tree representation of data from labeled samples, taken from an arbitrary (and possibly adversarial) distribution. Consider a collection of data tuples labeled according to their hierarchical…

Sub-word segmentation is an essential pre-processing step for Neural Machine Translation (NMT). Existing work has shown that neural sub-word segmenters are better than Byte-Pair Encoding (BPE), however, they are inefficient as they require…

Despite recent advances in retrieval-augmented generation (RAG) for video understanding, effectively understanding long-form video content remains underexplored due to the vast scale and high complexity of video data. Current RAG approaches…

Sparse coding consists in representing signals as sparse linear combinations of atoms selected from a dictionary. We consider an extension of this framework where the atoms are further assumed to be embedded in a tree. This is achieved…

In recent years, automatic speech recognition (ASR) systems have significantly improved, especially in languages with a vast amount of transcribed speech data. However, ASR systems tend to perform poorly for low-resource languages with…

There has been a surge in the use of large language models (LLM) conversational agents to generate responses based on long-term history from multiple sessions. However, existing long-term open-domain dialogue datasets lack complex,…

ASR systems often struggle with maintaining syntactic and semantic accuracy in long audio transcripts, impacting tasks like Named Entity Recognition (NER), capitalization, and punctuation. We propose a novel approach that enhances ASR by…

Every day we are surrounded by spoken dialog. This medium delivers rich diverse streams of information auditorily; however, systematically understanding dialog can often be non-trivial. Despite the pervasiveness of spoken dialog, automated…

Given recent advances in generative AI technology, a key question is how large language models (LLMs) can enhance acoustic modeling tasks using text decoding results from a frozen, pretrained automatic speech recognition (ASR) model. To…

Individual tree crown segmentation is an important task in remote sensing for forest biomass estimation and ecological monitoring. However, accurate delineation in dense, overlapping canopies remains a bottleneck. While supervised deep…

Recently, automated medical image segmentation methods based on deep learning have achieved great success. However, they heavily rely on large annotated datasets, which are costly and time-consuming to acquire. Few-shot learning aims to…

Retrieval-augmented generation (RAG) enhances large language models with external knowledge, and tree-based RAG organizes documents into hierarchical indexes to support queries at multiple granularities. However, existing Tree-RAG methods…

We introduce a cluster evaluation technique called Tree Index. Our Tree Index algorithm aims at describing the structural information of the clustering rather than the quantitative format of cluster-quality indexes (where the representation…

Typography and layout lead to the hierarchical organisation of text in words, text lines, paragraphs. This inherent structure is a key property of text in any script and language, which has nonetheless been minimally leveraged by existing…