Exploiting relationships between visual regions and question words have achieved great success in learning multi-modality features for Visual Question Answering (VQA). However, we argue that existing methods mostly model relations between individual visual regions and words, which are not enough to correctly answer the question. From humans' perspective, answering a visual question requires understanding the summarizations of visual and language information. In this paper, we proposed the Multi-modality Latent Interaction module (MLI) to tackle this problem. The proposed module learns the cross-modality relationships between latent visual and language summarizations, which summarize visual regions and question into a small number of latent representations to avoid modeling uninformative individual region-word relations. The cross-modality information between the latent summarizations are propagated to fuse valuable information from both modalities and are used to update the visual and word features. Such MLI modules can be stacked for several stages to model complex and latent relations between the two modalities and achieves highly competitive performance on public VQA benchmarks, VQA v2.0 and TDIUC . In addition, we show that the performance of our methods could be significantly improved by combining with pre-trained language model BERT.
The Chinese University of Hong Kong（香港中文大学）；Singapore Management University（新加坡管理大学）；NLPR, CASIA（中国科学院自动化研究所模式识别国家重点实验室）；Tsinghua University（清华大学）
Learning effective fusion of multi-modality features is at the heart of visual question answering. We propose a novel method of dynamically fusing multi-modal features with intra- and inter-modality information flow, which alternatively pass dynamic information between and across the visual and language modalities. It can robustly capture the high-level interactions between language and vision domains, thus significantly improves the performance of visual question answering. We also show that the proposed dynamic intra-modality attention flow conditioned on the other modality can dynamically m…
Beijing Institution of Technology（北京理工大学）；Baidu Inc.（百度公司）；Inception Institute of Artificial Intelligence（起源人工智能研究院）
Answering semantically-complicated questions according to an image is challenging in Visual Question Answering (VQA) task. Although the image can be well represented by deep learning, the question is always simply embedded and cannot well indicate its meaning. Besides, the visual and textual features have a gap for different modalities, it is difficult to align and utilize the cross-modality information. In this paper, we focus on these two problems and propose a Graph Matching Attention (GMA) network. Firstly, it not only builds graph for the image, but also constructs graph for the question …
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University at Buffalo（布法罗大学）；Amazon（亚马逊）
Contrastive loss has been increasingly used in learning representations from multiple modalities. In the limit, the nature of the contrastive loss encourages modalities to exactly match each other in the latent space. Yet it remains an open question how the modality alignment affects the downstream task performance. In this paper, based on an information-theoretic argument, we first prove that exact modality alignment is sub-optimal in general for downstream prediction tasks. Hence we advocate that the key of better performance lies in meaningful latent modality structures instead of perfect m…
Korea Advanced Institute of Science and Technology (KAIST)（韩国高等科学技术院（KAIST））；Samsung Research（三星研究院）
This paper proposes the progressive attention memory network (PAMN) for movie story question answering (QA). Movie story QA is challenging compared to VQA in two aspects: (1) pinpointing the temporal parts relevant to answer the question is difficult as the movies are typically longer than an hour, (2) it has both video and subtitle where different questions require different modality to infer the answer. To overcome these challenges, PAMN involves three main features: (1) progressive attention mechanism that utilizes cues from both question and answer to progressively prune out irrelevant tem…
Imperial College London（帝国理工学院）；University of Sheffield（谢菲尔德大学）；Department of Computing, Imperial College London（帝国理工学院计算机系）；Department of Computer Science, University of Sheffield（谢菲尔德大学计算机科学系）
Current work on Visual Question Answering (VQA) explore deterministic approaches conditioned on various types of image and question features. We posit that, in addition to image and question pairs, other modalities are useful for teaching machine to carry out question answering. Hence in this paper, we propose latent variable models for VQA where extra information (e.g. captions and answer categories) are incorporated as latent variables, which are observed during training but in turn benefit question-answering performance at test time. Experiments on the VQA v2.0 benchmarking dataset demonstr…
Visual Question Answering (VQA) attracts much attention from both industry and academia. As a multi-modality task, it is challenging since it requires not only visual and textual understanding, but also the ability to align cross-modality representations. Previous approaches extensively employ entity-level alignments, such as the correlations between the visual regions and their semantic labels, or the interactions across question words and object features. These attempts aim to improve the cross-modality representations, while ignoring their internal relations. Instead, we propose to apply st…
Different approaches have been proposed to Visual Question Answering (VQA). However, few works are aware of the behaviors of varying joint modality methods over question type prior knowledge extracted from data in constraining answer search space, of which information gives a reliable cue to reason about answers for questions asked in input images. In this paper, we propose a novel VQA model that utilizes the question-type prior information to improve VQA by leveraging the multiple interactions between different joint modality methods based on their behaviors in answering questions from differ…
AV-Master: Dual-Path Comprehensive Perception Makes Better Audio-Visual Question Answering
Great Bay University（大湾区大学）；Dongguan Key Laboratory for Intelligence and Information Technology（东莞智能与信息科技重点实验室）；Nankai University（南开大学）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；The Chinese University of Hong Kong（香港中文大学）
Northwestern University（西北大学）；Samsung Research America（三星美国研究院）
Learning to answer visual questions is a challenging task since the multi-modal inputs are within two feature spaces. Moreover, reasoning in visual question answering requires the model to understand both image and question, and align them in the same space, rather than simply memorize statistics about the question-answer pairs. Thus, it is essential to find component connections between different modalities and within each modality to achieve better attention. Previous works learned attention weights directly on the features. However, the improvement is limited since these two modality featur…
With the new generation of satellite technologies, the archives of remote sensing (RS) images are growing very fast. To make the intrinsic information of each RS image easily accessible, visual question answering (VQA) has been introduced in RS. VQA allows a user to formulate a free-form question concerning the content of RS images to extract generic information. It has been shown that the fusion of the input modalities (i.e., image and text) is crucial for the performance of VQA systems. Most of the current fusion approaches use modality-specific representations in their fusion modules instea…
MedLVR: Latent Visual Reasoning for Reliable Medical Visual Question Answering
Department of Radiation Oncology and Winship Cancer Institute, Emory University School of Medicine（埃默里大学医学院放射肿瘤学系与温希普癌症研究所）；Department of Biostatistics and Bioinformatics, Emory University（埃默里大学生物统计学与生物信息学系）
Vision-and-language reasoning requires an understanding of visual concepts, language semantics, and, most importantly, the alignment and relationships between these two modalities. We thus propose the LXMERT (Learning Cross-Modality Encoder Representations from Transformers) framework to learn these vision-and-language connections. In LXMERT, we build a large-scale Transformer model that consists of three encoders: an object relationship encoder, a language encoder, and a cross-modality encoder. Next, to endow our model with the capability of connecting vision and language semantics, we pre-tr…
MM-Prompt: Cross-Modal Prompt Tuning for Continual Visual Question Answering
Khoury College of Computer Sciences, Northeastern University（东北大学克劳尔计算机科学学院）；New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别新实验室）
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；Microsoft Research Asia（微软亚洲研究院）；University of Adelaide（阿德莱德大学）
Fact-based Visual Question Answering (FVQA) requires external knowledge beyond visible content to answer questions about an image, which is challenging but indispensable to achieve general VQA. One limitation of existing FVQA solutions is that they jointly embed all kinds of information without fine-grained selection, which introduces unexpected noises for reasoning the final answer. How to capture the question-oriented and information-complementary evidence remains a key challenge to solve the problem. In this paper, we depict an image by a multi-modal heterogeneous graph, which contains mult…
Imperial College London（帝国理工学院）；University of Sheffield（谢菲尔德大学）
Data augmentation has been shown to effectively improve the performance of multimodal machine learning models. This paper introduces a generative model for data augmentation by leveraging the correlations among multiple modalities. Different from conventional data augmentation approaches that apply low-level operations with deterministic heuristics, our method learns a generator that generates samples of the target modality conditioned on observed modalities in the variational auto-encoder framework. Additionally, the proposed model is able to quantify the confidence of augmented data by its g…
Most existing research on visual question answering (VQA) is limited to information explicitly present in an image or a video. In this paper, we take visual understanding to a higher level where systems are challenged to answer questions that involve mentally simulating the hypothetical consequences of performing specific actions in a given scenario. Towards that end, we formulate a vision-language question answering task based on the CLEVR (Johnson et. al., 2017) dataset. We then modify the best existing VQA methods and propose baseline solvers for this task. Finally, we motivate the developm…
Images are more than a collection of objects or attributes -- they represent a web of relationships among interconnected objects. Scene Graph has emerged as a new modality for a structured graphical representation of images. Scene Graph encodes objects as nodes connected via pairwise relations as edges. To support question answering on scene graphs, we propose GraphVQA, a language-guided graph neural network framework that translates and executes a natural language question as multiple iterations of message passing among graph nodes. We explore the design space of GraphVQA framework, and discu…
Applied Artificial Intelligence Institute, Deakin University（迪肯大学应用人工智能研究所）
The current success of modern visual reasoning systems is arguably attributed to cross-modality attention mechanisms. However, in deliberative reasoning such as in VQA, attention is unconstrained at each step, and thus may serve as a statistical pooling mechanism rather than a semantic operation intended to select information relevant to inference. This is because at training time, attention is only guided by a very sparse signal (i.e. the answer label) at the end of the inference chain. This causes the cross-modality attention weights to deviate from the desired visual-language bindings. To r…
Retrieving to Recover: Towards Incomplete Audio-Visual Question Answering via Semantic-consistent Purification
School of Computing and Information Technology, Great Bay University（大湾大学计算机与信息学院）；Dongguan Key Laboratory for Intelligence and Information Technology（东莞智能与信息科技重点实验室）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；College of Computer Science, Nankai University（南开大学计算机学院）；School of mathematics, Sun Yat-sen University（中山大学数学学院）
We present MMFT-BERT(MultiModal Fusion Transformer with BERT encodings), to solve Visual Question Answering (VQA) ensuring individual and combined processing of multiple input modalities. Our approach benefits from processing multimodal data (video and text) adopting the BERT encodings individually and using a novel transformer-based fusion method to fuse them together. Our method decomposes the different sources of modalities, into different BERT instances with similar architectures, but variable weights. This achieves SOTA results on the TVQA dataset. Additionally, we provide TVQA-Visual, an…
Guangdong University of Technology（广东工业大学）；City University of Hong Kong（香港城市大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；The Hong Kong Polytechnic University（香港理工大学）
In this work, we construct and release a multi-domain and multi-modality event dataset (MMED), containing 25,165 textual news articles collected from hundreds of news media sites (e.g., Yahoo News, Google News, CNN News.) and 76,516 image posts shared on Flickr social media, which are annotated according to 412 real-world events. The dataset is collected to explore the problem of organizing heterogeneous data contributed by professionals and amateurs in different data domains, and the problem of transferring event knowledge obtained from one data domain to heterogeneous data domain, thus summa…
National University of Singapore（新加坡国立大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Shandong University（山东大学）；Shandong Artificial Intelligence Institute（山东人工智能研究院）；University of Florence（佛罗伦萨大学）
Making each modality in multi-modal data contribute is of vital importance to learning a versatile multi-modal model. Existing methods, however, are often dominated by one or few of modalities during model training, resulting in sub-optimal performance. In this paper, we refer to this problem as modality bias and attempt to study it in the context of multi-modal classification systematically and comprehensively. After stepping into several empirical analysis, we recognize that one modality affects the model prediction more just because this modality has a spurious correlation with instance lab…
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；Samsung Research（三星研究院）
This paper considers a network referred to as Modality Shifting Attention Network (MSAN) for Multimodal Video Question Answering (MVQA) task. MSAN decomposes the task into two sub-tasks: (1) localization of temporal moment relevant to the question, and (2) accurate prediction of the answer based on the localized moment. The modality required for temporal localization may be different from that for answer prediction, and this ability to shift modality is essential for performing the task. To this end, MSAN is based on (1) the moment proposal network (MPN) that attempts to locate the most approp…
Make-A-Volume: Leveraging Latent Diffusion Models for Cross-Modality 3D Brain MRI Synthesis
The University of Hong Kong（香港大学）；The Chinese University of Hong Kong（香港中文大学）；Qilu Hospital of Shandong University（山东大学齐鲁医院）；Nanyang Technological University（南洋理工大学）
3D Wavelet Latent Diffusion Model for Whole-Body MR-to-CT Modality Translation
School of Biomedical Engineering, Shanghai Jiao Tong University（上海交通大学生物医学工程学院）；School of Information Science and Technology, ShanghaiTech University（上海交通大学信息科学与技术学院）；Shanghai United Imaging Healthcare Co., Ltd.（上海联影医疗科技有限公司）；Department of Radiology and Biomedical Imaging, Yale University（耶鲁大学放射科与生物医学成像系）；Department of Applied Mathematics & Statistics and Department of Computer Science, Stony Brook University（石溪大学应用数学与统计系和计算机科学系）
Robust Multispectral Semantic Segmentation under Missing or Full Modalities via Structured Latent Projection
Department of Computer Engineering, Ankara University（安卡拉大学计算机工程系）；Department of Modeling and Simulation, Graduate School of Informatics, METU（信息学院建模与模拟系，METU）
Wavelet-Fusion Diffusion Model for Multimodal Brain MRI Synthesis with Modality and Metadata Conditioning
Department of Psychology & Neuroscience, Auckland University of Technology（心理学与神经科学系，奥克兰技术大学）；Department of Psychiatry, University of Melbourne（精神病学系，墨尔本大学）
University of Dundee（邓迪大学）；University of Cambridge（剑桥大学）；University of Bath（巴斯大学）；East China Normal University（华东师范大学）
MRI synthesis promises to mitigate the challenge of missing MRI modality in clinical practice. Diffusion model has emerged as an effective technique for image synthesis by modelling complex and variable data distributions. However, most diffusion-based MRI synthesis models are using a single modality. As they operate in the original image domain, they are memory-intensive and less feasible for multi-modal synthesis. Moreover, they often fail to preserve the anatomical structure in MRI. Further, balancing the multiple conditions from multi-modal MRI inputs is crucial for multi-modal synthesis. …
Compositional Cross-Modality Translation via Whole-Volume Multitask Latent Flow Matching
Università Campus Bio-Medico di Roma（罗马 Campus Bio-Medico 大学）；Umeå University（于默奥大学）；UniCamillus – Saint Camillus International University of Health Sciences（UniCamillus – 圣卡米勒斯国际健康科学大学）
