Related papers: DASH: Dynamic Audio-Driven Semantic Chunking for E…

Multimodal large language models (MLLMs) have shown strong capability in semantic understanding and visual reasoning, yet their use on continuous video streams in bandwidth-constrained edge-cloud systems incurs prohibitive computation and…

The development of cross-modal retrieval systems that can search and retrieve semantically relevant data across different modalities based on a query in any modality has attracted great attention in remote sensing (RS). In this paper, we…

Large Language Models (LLMs) apply uniform computation to all tokens, despite language exhibiting highly non-uniform information density. This token-uniform regime wastes capacity on locally predictable spans while under-allocating…

Audio-Visual Speech Recognition (AVSR) achieves robust speech recognition in noisy environments by combining auditory and visual information. However, recent Large Language Model (LLM) based AVSR systems incur high computational costs due…

Hashing has attracted increasing research attentions in recent years due to its high efficiency of computation and storage in image retrieval. Recent works have demonstrated the superiority of simultaneous feature representations and hash…

Recent advancements in multimodal vision models have highlighted limitations in late-stage feature fusion and suboptimal query selection for hybrid prompts open-world segmentation, alongside constraints from caption-derived vocabularies. To…

The development of accurate and scalable cross-modal image-text retrieval methods, where queries from one modality (e.g., text) can be matched to archive entries from another (e.g., remote sensing image) has attracted great attention in…

Recent progress in speech separation has been largely driven by advances in deep neural networks, yet their high computational and memory requirements hinder deployment on resource-constrained devices. A significant inefficiency in…

Effective speech representations for spoken language models must balance semantic relevance with acoustic fidelity for high-quality reconstruction. However, existing approaches struggle to achieve both simultaneously. To address this, we…

This paper presents a simple yet effective supervised deep hash approach that constructs binary hash codes from labeled data for large-scale image search. We assume that the semantic labels are governed by several latent attributes with…

Existing cross-modal retrieval methods typically rely on large-scale vision-language pair data. This makes it challenging to efficiently develop a cross-modal retrieval model for under-resourced languages of interest. Therefore,…

Unsupervised hashing can desirably support scalable content-based image retrieval (SCBIR) for its appealing advantages of semantic label independence, memory and search efficiency. However, the learned hash codes are embedded with limited…

Audio-text retrieval enables semantic alignment between audio content and natural language queries, supporting applications in multimedia search, accessibility, and surveillance. However, current state-of-the-art approaches struggle with…

Multimodal Large Language Models (MLLMs) encounter significant computational and memory bottlenecks from the massive number of visual tokens generated by high-resolution images or multi-image inputs. Previous token compression techniques…

Audio-Visual Segmentation (AVS) aims to localize sound-producing objects at the pixel level by jointly leveraging auditory and visual information. However, existing methods often suffer from multi-source entanglement and audio-visual…

Open-Vocabulary Semantic Segmentation (OVSS) assigns pixel-level labels from an open set of text-defined categories, demanding reliable generalization to unseen classes at inference. Although modern vision-language models (VLMs) support…

We present DASH (Deep Automated Supernova and Host classifier), a novel software package that automates the classification of the type, age, redshift, and host galaxy of supernova spectra. DASH makes use of a new approach that does not rely…

Despite progress in audio classification, a generalization gap remains between speech and other sound domains, such as environmental sounds and music. Models trained for speech tasks often fail to perform well on environmental or musical…

Tongue segmentation serves as the primary step in automated TCM tongue diagnosis, which plays a significant role in the diagnostic results. Currently, numerous deep learning based methods have achieved promising results. However, when…

Vision-language models (VLMs) have transformed multimodal reasoning, but feeding hundreds of visual patch tokens into LLMs incurs quadratic computational costs, straining memory and context windows. Traditional approaches face a trade-off:…