Related papers: Holistic Multi-modal Memory Network for Movie Ques…
Understanding dynamic scenes and dialogue contexts in order to converse with users has been challenging for multimodal dialogue systems. The 8-th Dialog System Technology Challenge (DSTC8) proposed an Audio Visual Scene-Aware Dialog (AVSD)…
Recent vision and multimodal foundation backbones, such as Transformer families and state-space models like Mamba, have achieved remarkable progress, enabling unified modeling across images, text, and beyond. Despite their empirical…
With the prevalence of Multimodal Large Language Models(MLLMs), autonomous driving has encountered new opportunities and challenges. In particular, multi-modal video understanding is critical to interactively analyze what will happen in the…
Memes have evolved as a prevalent medium for diverse communication, ranging from humour to propaganda. With the rising popularity of image-focused content, there is a growing need to explore its potential harm from different aspects.…
Multi-source multi-hop question answering (QA) represents a challenging task in natural language processing due to the need for dynamic integration of heterogeneous knowledge sources and multi-step reasoning. Existing methods often suffer…
Transformer-based large language models (LLM) have been widely used in language processing applications. However, due to the memory constraints of the devices, most of them restrict the context window. Even though recurrent models in…
We present VQA-MHUG - a novel 49-participant dataset of multimodal human gaze on both images and questions during visual question answering (VQA) collected using a high-speed eye tracker. We use our dataset to analyze the similarity between…
Query-based moment retrieval aims to localize the most relevant moment in an untrimmed video according to the given natural language query. Existing works often only focus on one aspect of this emerging task, such as the query…
Multi-relation Question Answering is a challenging task, due to the requirement of elaborated analysis on questions and reasoning over multiple fact triples in knowledge base. In this paper, we present a novel model called Interpretable…
Traditional joint source-channel coding employs static learned semantic representations that cannot dynamically adapt to evolving source distributions. Shared semantic memories between transmitter and receiver can potentially enable…
Multimodal fusion frameworks, which integrate diverse medical imaging modalities (e.g., MRI, CT), have shown great potential in applications such as skin cancer detection, dementia diagnosis, and brain tumor prediction. However, existing…
The task of event detection involves identifying and categorizing event triggers. Contextual information has been shown effective on the task. However, existing methods which utilize contextual information only process the context once. We…
Machine Reading Comprehension (MRC) for question answering (QA), which aims to answer a question given the relevant context passages, is an important way to test the ability of intelligence systems to understand human language.…
In order to achieve a general visual question answering (VQA) system, it is essential to learn to answer deeper questions that require compositional reasoning on the image and external knowledge. Meanwhile, the reasoning process should be…
Understanding Theory of Mind is essential for building socially intelligent multimodal agents capable of perceiving and interpreting human behavior. We introduce MoMentS (Multimodal Mental States), a comprehensive benchmark designed to…
With the rapid development of multimodal models, the demand for assessing video understanding capabilities has been steadily increasing. However, existing benchmarks for evaluating video understanding exhibit significant limitations in…
Hashing has been widely applied to multimodal retrieval on large-scale multimedia data due to its efficiency in computation and storage. In this article, we propose a novel deep semantic multimodal hashing network (DSMHN) for scalable…
Multimodal information extraction (MIE) aims to extract structured information from unstructured multimedia content. Due to the diversity of tasks and settings, most current MIE models are task-specific and data-intensive, which limits…
Human-like attention as a supervisory signal to guide neural attention has shown significant promise but is currently limited to uni-modal integration - even for inherently multimodal tasks such as visual question answering (VQA). We…
Multimodal semantic learning plays a critical role in embodied intelligence, especially when robots perceive their surroundings, understand human instructions, and make intelligent decisions. However, the field faces technical challenges…