Related papers: How2: A Large-scale Dataset for Multimodal Languag…
In recent years, multimodal natural language processing, aimed at learning from diverse data types, has garnered significant attention. However, there needs to be more clarity when it comes to analysing multimodal tasks in multi-lingual…
Large Language Models (LLMs) have demonstrated exceptional proficiency in text understanding and embedding tasks. However, their potential in multimodal representation, particularly for item-to-item (I2I) recommendations, remains…
Text-rich visual understanding-the ability to process environments where dense textual content is integrated with visuals-is crucial for multimodal large language models (MLLMs) to interact effectively with structured environments. To…
Training multimodal large language models (MLLMs) for video understanding requires large-scale annotated data spanning diverse tasks such as object counting, question answering, and segmentation. However, collecting and annotating…
Video captioning aims to describe video contents using natural language format that involves understanding and interpreting scenes, actions and events that occurs simultaneously on the view. Current approaches have mainly concentrated on…
The objective of this work is to manipulate visual timelines (e.g. a video) through natural language instructions, making complex timeline editing tasks accessible to non-expert or potentially even disabled users. We call this task…
We introduce WikiLingua, a large-scale, multilingual dataset for the evaluation of crosslingual abstractive summarization systems. We extract article and summary pairs in 18 languages from WikiHow, a high quality, collaborative resource of…
In this paper, we explore self-supervised audio-visual models that learn from instructional videos. Prior work has shown that these models can relate spoken words and sounds to visual content after training on a large-scale dataset of…
With the rapid development of mobile Internet and big data, a huge amount of data is generated in the network, but the data that users are really interested in a very small portion. To extract the information that users are interested in…
Significant progress has been made recently on challenging tasks in automatic sign language understanding, such as sign language recognition, translation and production. However, these works have focused on datasets with relatively few…
An increasing number of datasets contain multiple views, such as video, sound and automatic captions. A basic challenge in representation learning is how to leverage multiple views to learn better representations. This is further…
Text-level discourse parsing aims to unmask how two sentences in the text are related to each other. We propose the task of Visual Discourse Parsing, which requires understanding discourse relations among scenes in a video. Here we use the…
Computational sign language research lacks the large-scale datasets that enables the creation of useful reallife applications. To date, most research has been limited to prototype systems on small domains of discourse, e.g. weather…
Recent integration of Natural Language Processing (NLP) and multimodal models has advanced the field of sports analytics. This survey presents a comprehensive review of the datasets and applications driving these innovations post-2020. We…
We introduce the Multi30K dataset to stimulate multilingual multimodal research. Recent advances in image description have been demonstrated on English-language datasets almost exclusively, but image description should not be limited to…
With the rapid advancement of mathematical reasoning capabilities in Large Language Models (LLMs), AI systems are increasingly being adopted in educational settings to support students' comprehension of problem-solving processes. However, a…
The goal of multimodal summarization is to extract the most important information from different modalities to form output summaries. Unlike the unimodal summarization, the multimodal summarization task explicitly leverages cross-modal…
The real-world is inherently multi-modal at its core. Our tools observe and take snapshots of it, in digital form, such as videos or sounds, however much of it is lost. Similarly for actions and information passing between humans, languages…
To support machine learning of cross-language prosodic mappings and other ways to improve speech-to-speech translation, we present a protocol for collecting closely matched pairs of utterances across languages, a description of the…
We propose a new and fully end-to-end approach for multimodal translation where the source text encoder modulates the entire visual input processing using conditional batch normalization, in order to compute the most informative image…