English
Related papers

Related papers: Zorro: the masked multimodal transformer

200 papers

In this paper, we propose a single UniFied transfOrmer (UFO), which is capable of processing either unimodal inputs (e.g., image or language) or multimodal inputs (e.g., the concatenation of the image and the question), for vision-language…

Computer Vision and Pattern Recognition · Computer Science 2021-11-22 Jianfeng Wang , Xiaowei Hu , Zhe Gan , Zhengyuan Yang , Xiyang Dai , Zicheng Liu , Yumao Lu , Lijuan Wang

Recent studies have shown the importance of modeling long-range interactions in the inpainting problem. To achieve this goal, existing approaches exploit either standalone attention techniques or transformers, but usually under a low…

Computer Vision and Pattern Recognition · Computer Science 2022-06-28 Wenbo Li , Zhe Lin , Kun Zhou , Lu Qi , Yi Wang , Jiaya Jia

Existing work in multilingual pretraining has demonstrated the potential of cross-lingual transferability by training a unified Transformer encoder for multiple languages. However, much of this work only relies on the shared vocabulary and…

Computation and Language · Computer Science 2021-06-03 Fuli Luo , Wei Wang , Jiahao Liu , Yijia Liu , Bin Bi , Songfang Huang , Fei Huang , Luo Si

Studies on emotion recognition (ER) show that combining lexical and acoustic information results in more robust and accurate models. The majority of the studies focus on settings where both modalities are available in training and…

Computation and Language · Computer Science 2019-06-26 Gustavo Aguilar , Viktor Rozgić , Weiran Wang , Chao Wang

Transformers have become the de facto standard for a wide range of tasks, from image classification to physics simulations. Despite their impressive performance, the quadratic complexity of standard Transformers in both memory and time with…

Computer Vision and Pattern Recognition · Computer Science 2025-07-04 Alex Colagrande , Paul Caillon , Eva Feillet , Alexandre Allauzen

Accurate beam prediction is essential for mitigating signalling overhead and latency in integrated sensing and communication-enabled massive multi-input multi-output systems. With the aid of multimodal learning, the prediction accuracy can…

Signal Processing · Electrical Eng. & Systems 2026-05-15 Zijian Zheng , Wenqiang Yi , Hyundong Shin , Arumugam Nallanathan

Masked modeling has emerged as a powerful self-supervised learning framework, but existing methods largely rely on random masking, disregarding the structural properties of different modalities. In this work, we introduce structured…

Machine Learning · Computer Science 2025-03-21 Aritra Bhowmik , Fida Mohammad Thoker , Carlos Hinojosa , Bernard Ghanem , Cees G. M. Snoek

Multimodal learning seeks to combine data from multiple input sources to enhance the performance of different downstream tasks. In real-world scenarios, performance can degrade substantially if some input modalities are missing. Existing…

Machine Learning · Computer Science 2024-10-10 Niki Nezakati , Md Kaykobad Reza , Ameya Patil , Mashhour Solh , M. Salman Asif

Humans are excellent at understanding language and vision to accomplish a wide range of tasks. In contrast, creating general instruction-following embodied agents remains a difficult challenge. Prior work that uses pure language-only models…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Hao Liu , Lisa Lee , Kimin Lee , Pieter Abbeel

Vision-language-action models have gained significant attention for their ability to model multimodal sequences in embodied instruction following tasks. However, most existing models rely on causal attention, which we find suboptimal for…

Robotics · Computer Science 2026-01-21 Yueen Ma , Dafeng Chi , Shiguang Wu , Yuecheng Liu , Yuzheng Zhuang , Irwin King

In recommender systems, models mostly use a combination of embedding layers and multilayer feedforward neural networks. The high-dimensional sparse original features are downscaled in the embedding layer and then fed into the fully…

Information Retrieval · Computer Science 2022-05-19 Mohan Hasama , Jing Li

We develop an approach to learning visual representations that embraces multimodal data, driven by a combination of intra- and inter-modal similarity preservation objectives. Unlike existing visual pre-training methods, which solve a proxy…

Computer Vision and Pattern Recognition · Computer Science 2021-04-28 Xin Yuan , Zhe Lin , Jason Kuen , Jianming Zhang , Yilin Wang , Michael Maire , Ajinkya Kale , Baldo Faieta

Multimodal learning, which integrates data from diverse sensory modes, plays a pivotal role in artificial intelligence. However, existing multimodal learning methods often struggle with challenges where some modalities appear more dominant…

Machine Learning · Computer Science 2024-04-02 Xiaohui Zhang , Jaehong Yoon , Mohit Bansal , Huaxiu Yao

Multimodal Deep Learning has garnered much interest, and transformers have triggered novel approaches, thanks to the cross-attention mechanism. Here we propose an approach to deal with two key existing challenges: the high computational…

Machine Learning · Computer Science 2021-10-20 Dhruv Agarwal , Tanay Agrawal , Laura M. Ferrari , François Bremond

The dominant probing approaches rely on the zero-shot performance of image-text matching tasks to gain a finer-grained understanding of the representations learned by recent multimodal image-language transformer models. The evaluation is…

Computation and Language · Computer Science 2024-01-31 Ivana Beňová , Jana Košecká , Michal Gregor , Martin Tamajka , Marcel Veselý , Marián Šimko

Transformers are increasingly dominating multi-modal reasoning tasks, such as visual question answering, achieving state-of-the-art results thanks to their ability to contextualize information using the self-attention and co-attention…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Hila Chefer , Shir Gur , Lior Wolf

Transformer models have achieved state-of-the-art results across a diverse range of domains. However, concern over the cost of training the attention mechanism to learn complex dependencies between distant inputs continues to grow. In…

Creating a meaningful representation by fusing single modalities (e.g., text, images, or audio) is the core concept of multimodal learning. Although several techniques for building multimodal representations have been proven successful,…

Machine Learning · Computer Science 2025-08-08 Maciej Pawłowski , Anna Wróblewska , Sylwia Sysko-Romańczuk

Why do large pre-trained transformer-based models perform so well across a wide variety of NLP tasks? Recent research suggests the key may lie in multi-headed attention mechanism's ability to learn and represent linguistic information.…

Computation and Language · Computer Science 2021-06-08 Zijie J. Wang , Robert Turko , Duen Horng Chau

Humans express their emotions via facial expressions, voice intonation and word choices. To infer the nature of the underlying emotion, recognition models may use a single modality, such as vision, audio, and text, or a combination of…

Machine Learning · Computer Science 2022-02-21 Vandana Rajan , Alessio Brutti , Andrea Cavallaro