相关论文: Multi-Granularity Guided Fusion-in-Decoder

Information retrieval is indispensable for today's Internet applications, yet traditional semantic matching techniques often fall short in capturing the fine-grained cross-modal interactions required for complex queries. Although…

Answering questions that require reading texts in an image is challenging for current models. One key difficulty of this task is that rare, polysemous, and ambiguous words frequently appear in images, e.g., names of places, products, and…

Answering questions using pre-trained language models (LMs) and knowledge graphs (KGs) presents challenges in identifying relevant knowledge and performing joint reasoning.We compared LMs (fine-tuned for the task) with the previously…

Discrete diffusion models have emerged as a promising direction for vision-language tasks, offering bidirectional context modeling and theoretical parallelization. However, their practical application is severely hindered by a…

Real-world problems are often dependent on multiple data modalities, making multimodal fusion essential for leveraging diverse information sources. In high-stakes domains, such as in healthcare, understanding how each modality contributes…

Multi-modality image fusion aims at fusing modality-specific (complementarity) and modality-shared (correlation) information from multiple source images. To tackle the problem of the neglect of inter-feature relationships, high-frequency…

Multimodal sarcasm detection (MSD) aims to identify sarcastic intent from semantic incongruity between text and image. Although recent methods have improved MSD through cross-modal interaction and incongruity reasoning, most still treat…

Understanding 3D scenes is pivotal for autonomous driving, robotics, and augmented reality. Recent semantic Gaussian Splatting approaches leverage large-scale 2D vision models to project 2D semantic features onto 3D scenes. However, they…

We present Multiple-Question Multiple-Answer (MQMA), a novel approach to do text-VQA in encoder-decoder transformer models. The text-VQA task requires a model to answer a question by understanding multi-modal content: text (typically from…

Large Vision-Language Models (LVLMs) have achieved remarkable success in a wide range of multimodal tasks by integrating pre-trained vision encoders and large language models. However, current LVLMs primarily rely on visual features…

Domain Generalized Semantic Segmentation (DGSS) aims to improve the generalization ability of models across unseen domains without access to target data during training. Recent advances in DGSS have increasingly exploited vision foundation…

Accurate identification of protein-nucleotide binding sites is fundamental to deciphering molecular mechanisms and accelerating drug discovery. However, current computational methods often struggle with suboptimal performance due to…

Multimodal large language models (MLLMs) typically rely on a single late-layer feature from a frozen vision encoder, leaving the encoder's rich hierarchy of visual cues under-utilized. MLLMs still suffer from visually ungrounded…

Conventional works generally employ a two-phase model in which a generator selects the most important pieces, followed by a predictor that makes predictions based on the selected pieces. However, such a two-phase model may incur the…

Multimodal Federated Learning (MFL) enables clients with heterogeneous data modalities to collaboratively train models without sharing raw data, offering a privacy-preserving framework that leverages complementary cross-modal information.…

State-of-the-art face recognition (FR) models often experience a significant performance drop when dealing with facial images in surveillance scenarios where images are in low quality and often corrupted with noise. Leveraging facial…

Many language generation models are now available for a wide range of generation tasks, including machine translation and summarization. Combining such diverse models may lead to further progress, but ensembling generation models is…

Recent advancements in Large Language Models (LLMs) underscore the necessity of Retrieval Augmented Generation (RAG) to leverage external information. However, LLMs are sensitive to the position of relevant information within contexts and…

Large-scale digitization initiatives have unlocked massive collections of historical newspapers, yet effective computational access remains hindered by OCR corruption, multilingual orthographic variation, and temporal language drift. We…

Real-world multimodal applications often require any-to-any capabilities, enabling both understanding and generation across modalities including text, image, audio, and video. However, integrating the strengths of autoregressive language…