Related papers: FlexMUSE: Multimodal Unification and Semantics Enh…
We introduce the first generative model capable of simultaneous multi-object compositing, guided by both text and layout. Our model allows for the addition of multiple objects within a scene, capturing a range of interactions from simple…
Contemporary cardiovascular management involves complex consideration and integration of multimodal cardiac datasets, where each modality provides distinct but complementary physiological characteristics. While the effective integration of…
Multimodal interfaces, combining the use of speech, graphics, gestures, and facial expressions in input and output, promise to provide new possibilities to deal with information in more effective and efficient ways, supporting for instance:…
Task-oriented dialogue systems have garnered significant attention due to their conversational ability to accomplish goals, such as booking airline tickets for users. Traditionally, task-oriented dialogue systems are conceptualized as…
Generative image compression has recently shown impressive perceptual quality, but often suffers from semantic deviations caused by generative hallucinations at ultra-low bitrate (bpp < 0.05), limiting its reliable deployment in…
This work explores a closure task in comics, a medium where visual and textual elements are intricately intertwined. Specifically, Text-cloze refers to the task of selecting the correct text to use in a comic panel, given its neighboring…
Visual Word Sense Disambiguation (VWSD) is a multi-modal task that aims to select, among a batch of candidate images, the one that best entails the target word's meaning within a limited context. In this paper, we propose a multi-modal…
Nowadays, cross-modal retrieval plays an indispensable role to flexibly find information across different modalities of data. Effectively measuring the similarity between different modalities of data is the key of cross-modal retrieval.…
The emoticons are symbolic representations that generally accompany the textual content to visually enhance or summarize the true intention of a written message. Although widely utilized in the realm of social media, the core semantics of…
Knowledge editing techniques have emerged as essential tools for updating the factual knowledge of large language models (LLMs) and multimodal models (LMMs), allowing them to correct outdated or inaccurate information without retraining…
Multi-modal cues, including spatial information, facial expression and voiceprint, are introduced to the speech separation and speaker extraction tasks to serve as complementary information to achieve better performance. However, the…
Image fusion aims to synthesize a single high-quality image from a pair of inputs captured under challenging conditions, such as differing exposure levels or focal depths. A core challenge lies in effectively handling disparities in dynamic…
Natural human interactions for Mixed Reality Applications are overwhelmingly multimodal: humans communicate intent and instructions via a combination of visual, aural and gestural cues. However, supporting low-latency and accurate…
Multimodal federated learning (FL) aims to enrich model training in FL settings where devices are collecting measurements across multiple modalities (e.g., sensors measuring pressure, motion, and other types of data). However, key…
Multimodal models have been proven to outperform text-based models on learning semantic word representations. Almost all previous multimodal models typically treat the representations from different modalities equally. However, it is…
Multimodal semantic segmentation integrates complementary information from diverse sensors for remote sensing Earth observation. However, practical systems often encounter missing modalities due to sensor failures or incomplete coverage,…
Despite significant progress in diffusion-based image generation, subject-driven generation and instruction-based editing remain challenging. Existing methods typically treat them separately, struggling with limited high-quality data and…
Molecular representation learning plays a crucial role in advancing applications such as drug discovery and material design. Existing work leverages 2D and 3D modalities of molecular information for pre-training, aiming to capture…
This paper presents a novel model for multimodal learning based on gated neural networks. The Gated Multimodal Unit (GMU) model is intended to be used as an internal unit in a neural network architecture whose purpose is to find an…
Controllable speech generation methods typically rely on single or fixed prompts, hindering creativity and flexibility. These limitations make it difficult to meet specific user needs in certain scenarios, such as adjusting the style while…