Videos are multimodal in nature. Conventional video recognition pipelines typically fuse multimodal features for improved performance. However, this is not only computationally expensive but also neglects the fact that different videos rely on different modalities for predictions. This paper introduces Hierarchical and Conditional Modality Selection (HCMS), a simple yet efficient multimodal learning framework for efficient video recognition. HCMS operates on a low-cost modality, i.e., audio clues, by default, and dynamically decides on-the-fly whether to use computationally-expensive modalities, including appearance and motion clues, on a per-input basis. This is achieved by the collaboration of three LSTMs that are organized in a hierarchical manner. In particular, LSTMs that operate on high-cost modalities contain a gating module, which takes as inputs lower-level features and historical information to adaptively determine whether to activate its corresponding modality; otherwise it simply reuses historical information. We conduct extensive experiments on two large-scale video benchmarks, FCVID and ActivityNet, and the results demonstrate the proposed approach can effectively explore multimodal information for improved classification performance while requiring much less computation.
MMoT: Mixture-of-Modality-Tokens Transformer for Composed Multimodal Conditional Image Synthesis
South China University of Technology（华南理工大学）；JD Explore Academy（京东探索研究院）；Nanyang Technological University（南洋理工大学）；Shanghai Jiao Tong University（上海交通大学）
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Bosch Center for Artificial Intelligence（博世人工智能中心）；CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）
Prediction of future states of the environment and interacting agents is a key competence required for autonomous agents to operate successfully in the real world. Prior work for structured sequence prediction based on latent variable models imposes a uni-modal standard Gaussian prior on the latent variables. This induces a strong model bias which makes it challenging to fully capture the multi-modality of the distribution of the future states. In this work, we introduce Conditional Flow Variational Autoencoders (CF-VAE) using our novel conditional normalizing flow based prior to capture compl…
Chongqing University（重庆大学）；University of Delaware（特拉华大学）
Data augmentation is a powerful technique for improving the performance of the few-shot classification task. It generates more samples as supplements, and then this task can be transformed into a common supervised learning issue for solution. However, most mainstream data augmentation based approaches only consider the single modality information, which leads to the low diversity and quality of generated features. In this paper, we present a novel multi-modal data augmentation approach named Dizygotic Conditional Variational AutoEncoder (DCVAE) for addressing the aforementioned issue. DCVAE co…
Massachusetts General Hospital（马萨诸塞总医院）；Harvard Medical School（哈佛医学院）
Multimodal MRI provides complementary and clinically relevant information to probe tissue condition and to characterize various diseases. However, it is often difficult to acquire sufficiently many modalities from the same subject due to limitations in study plans, while quantitative analysis is still demanded. In this work, we propose a unified conditional disentanglement framework to synthesize any arbitrary modality from an input modality. Our framework hinges on a cycle-constrained conditional adversarial training approach, where it can extract a modality-invariant anatomical feature with …
AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling
Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, China（中国科学院智能信息处理重点实验室（中国科学院计算技术研究所，中国））；University of Chinese Academy of Sciences, China（中国科学院大学）
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Shandong University（山东大学）；Inception Institute of Artificial Intelligence（起源人工智能研究院）
Positron emission tomography (PET) imaging is an imaging modality for diagnosing a number of neurological diseases. In contrast to Magnetic Resonance Imaging (MRI), PET is costly and involves injecting a radioactive substance into the patient. Motivated by developments in modality transfer in vision, we study the generation of certain types of PET images from MRI data. We derive new flow-based generative models which we show perform well in this small sample size regime (much smaller than dataset sizes available in standard vision tasks). Our formulation, DUAL-GLOW, is based on two invertible …
Conditional Evidence Reconstruction and Decomposition for Interpretable Multimodal Diagnosis
Department of Biomedical Engineering, New Jersey Institute of Technology（新泽西理工学院生物医学工程系）；Department of Computer Science and Engineering, The University of Texas at Arlington（德克萨斯大学阿灵顿分校计算机科学与工程系）；Department of Computer Science, Indiana University Indianapolis（印第安纳大学印第安纳波利斯分校计算机科学系）；School of Computing, University of Georgia（佐治亚大学计算科学学院）
Cocktail: Mixing Multi-Modality Controls for Text-Conditional Image Generation
Nanyang Technological University（南洋理工大学）；South China University of Technology（华南理工大学）；University of Oxford（牛津大学）；The University of Sydney（悉尼大学）；JD Explore Academy（京东探索研究院）
Backbone-Conditional Behavior of Modality Gating in Multi-Modal Prostate MRI Segmentation: A 5-Fold Cross-Validation and Gate Mechanism Analysis
The Second Xiangya Hospital of Central South University（中南大学湘雅医学院第二医院）；The Third Xiangya Hospital of Central South University（中南大学湘雅医学院第三医院）；School of Life Sciences, Central South University（中南大学生命科学学院）；Hunan Provincial Key Laboratory of Medical Information Research (Central South University)（湖南省医学信息研究重点实验室（中南大学））；Hunan Provincial Clinical Medical Research Center for Cardiovascular Intelligent Medicine（湖南省心血管智能医学临床医学研究中心）
HangZhou Dianzi University（杭州电子科技大学）；The University of Sydney（悉尼大学）
Unsupervised cross-modal hashing (UCMH) has become a hot topic recently. Current UCMH focuses on exploring data similarities. However, current UCMH methods calculate the similarity between two data, mainly relying on the two data's cross-modal features. These methods suffer from inaccurate similarity problems that result in a suboptimal retrieval Hamming space, because the cross-modal features between the data are not sufficient to describe the complex data relationships, such as situations where two data have different feature representations but share the inherent concepts. In this paper, we…
Plasma-CycleGAN: Plasma Biomarker-Guided MRI to PET Cross-modality Translation Using Conditional CycleGAN
School of Computing and Augmented Intelligence, Arizona State University（亚利桑那州立大学计算与增强智能学院）；Banner Alzheimer’s Institute（班纳阿尔茨海默病研究所）；Basis Scottsdale（斯科茨代尔贝斯机构）；College of Health Solutions, Arizona State University（亚利桑那州立大学健康解决方案学院）；Mayo Clinic Arizona（梅奥诊所亚利桑那州分院）
New York University（纽约大学）；NYU Grossman School of Medicine（纽约大学格罗斯曼医学院）；Courant Institute of Mathematical Sciences（库朗数学科学研究所）；Genentech（基因泰克）；CIFAR LMB（加拿大高等研究院分子生物学实验室）
We hypothesize that due to the greedy nature of learning in multi-modal deep neural networks, these models tend to rely on just one modality while under-fitting the other modalities. Such behavior is counter-intuitive and hurts the models' generalization, as we observe empirically. To estimate the model's dependence on each modality, we compute the gain on the accuracy when the model has access to it in addition to another modality. We refer to this gain as the conditional utilization rate. In the experiments, we consistently observe an imbalance in conditional utilization rates between modali…
ShanghaiTech University（上海科技大学）；Shanghai United Imaging Intelligence Co., Ltd.（上海联影智能科技有限公司）；Northwestern Polytechnical University（西北工业大学）
Multi-modal medical image completion has been extensively applied to alleviate the missing modality issue in a wealth of multi-modal diagnostic tasks. However, for most existing synthesis methods, their inferences of missing modalities can collapse into a deterministic mapping from the available ones, ignoring the uncertainties inherent in the cross-modal relationships. Here, we propose the Unified Multi-Modal Conditional Score-based Generative Model (UMM-CSGM) to take advantage of Score-based Generative Model (SGM) in modeling and stochastically sampling a target probability distribution, and…
In this paper, we address the problem of conditional modality learning, whereby one is interested in generating one modality given the other. While it is straightforward to learn a joint distribution over multiple modalities using a deep multimodal architecture, we observe that such models aren't very effective at conditional generation. Hence, we address the problem by learning conditional distributions between the modalities. We use variational methods for maximizing the corresponding conditional log-likelihood. The resultant deep model, which we refer to as conditional multimodal autoencode…
Referring Video Object Segmentation with Cross-Modality Proxy Queries
DUT-RU International School of Information Science & Engineering, Dalian University of Technology, China（大连理工大学国际信息科学与工程学院，中国）；Chinese University of Hong Kong, China（香港中文大学，中国）；University of Sydney, Australia（悉尼大学，澳大利亚）
Existing conditional image synthesis frameworks generate images based on user inputs in a single modality, such as text, segmentation, sketch, or style reference. They are often unable to leverage multimodal user inputs when available, which reduces their practicality. To address this limitation, we propose the Product-of-Experts Generative Adversarial Networks (PoE-GAN) framework, which can synthesize images conditioned on multiple input modalities or any subset of them, even the empty set. PoE-GAN consists of a product-of-experts generator and a multimodal multiscale projection discriminator…
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. …
Research Institute of Beihang University in Shenzhen（北京航空航天大学深圳研究院）；Beihang University（北京航空航天大学）；Chongqing University（重庆大学）；Microsoft Research（微软研究院）
We present a cross-modality generation framework that learns to generate translated modalities from given modalities in MR images without real acquisition. Our proposed method performs NeuroImage-to-NeuroImage translation (abbreviated as N2N) by means of a deep learning model that leverages conditional generative adversarial networks (cGANs). Our framework jointly exploits the low-level features (pixel-wise information) and high-level representations (e.g. brain tumors, brain structure like gray matter, etc.) between cross modalities which are important for resolving the challenging complexity…
We present a conditional generative model that maps low-dimensional embeddings of multiple modalities of data to a common latent space hence extracting semantic relationships between them. The embedding specific to a modality is first extracted and subsequently a constrained optimization procedure is performed to project the two embedding spaces to a common manifold. The individual embeddings are generated back from this common latent space. However, in order to enable independent conditional inference for separately extracting the corresponding embeddings from the common latent space represen…
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）
PRA-PoE: Robust Multimodal Alzheimer's Diagnosis with Arbitrary Missing Modalities
Department of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China（生物医学工程系，香港理工大学，香港特别行政区，中国）；Department of Technology Management for Innovation, The University of Tokyo, Japan（创新技术管理系，东京大学，日本）；Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR, China（数据科学与人工智能系，香港理工大学，香港特别行政区，中国）
Nanyang Technological University（南洋理工大学）；University of Surrey（萨里大学）；Institute of Engineering & Management（工程与管理学院）；Jadavpur University（贾达普大学）；Indian Institute of Technology, Roorkee（印度理工学院鲁尔基分校）；Indian Statistical Institute（印度统计研究所）
In this paper, we propose a novel approach of word-level Indic script identification using only character-level data in training stage. The advantages of using character level data for training have been outlined in section I. Our method uses a multimodal deep network which takes both offline and online modality of the data as input in order to explore the information from both the modalities jointly for script identification task. We take handwritten data in either modality as input and the opposite modality is generated through intermodality conversion. Thereafter, we feed this offline-onlin…
Humans have perfected the art of learning from multiple modalities through sensory organs. Despite their impressive predictive performance on a single modality, neural networks cannot reach human level accuracy with respect to multiple modalities. This is a particularly challenging task due to variations in the structure of respective modalities. Conditional Batch Normalization (CBN) is a popular method that was proposed to learn contextual features to aid deep learning tasks. This technique uses auxiliary data to improve representational power by learning affine transformations for convolutio…
Parameter-Efficient Modality-Balanced Symmetric Fusion for Multimodal Remote Sensing Semantic Segmentation
College of Land Science and Technology, China Agricultural University（中国农业大学土地科学与技术学院）；Key Laboratory of Remote Sensing for Agri-Hazards, Ministry of Agriculture and Rural Affairs（农业农村部农业灾害遥感重点实验室）；Faculty of Geosciences and Engineering, Southwest Jiaotong University（西南交通大学地质科学与工程学院）；School of Artificial Intelligence, Sun Yat-Sen University（中山大学人工智能学院）；Henan Polytechnic University（河南理工大学）；Key Laboratory of Spatio-Temporal Information and Ecological Restoration of Mines, Ministry of Natural Resources of the People’s Republic of China（矿产资源时空信息与生态修复重点实验室）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；National Supercomputing Center in Shenzhen, Shenzhen, China（深圳国家超算中心）；Ministry of Education Key Laboratory for Earth System Modeling and the Department of Earth System Science, Tsinghua University（地球系统模拟教育部重点实验室和清华大学地球系统科学系）
Auxiliary information can be exploited in machine learning models using the paradigm of evidence based conditional inference. Multi-modal techniques in Deep Neural Networks (DNNs) can be seen as perturbing the latent feature representation for incorporating evidence from the auxiliary modality. However, they require training a specialized network which can map sparse evidence to a high dimensional latent space vector. Designing such a network, as well as collecting jointly labeled data for training is a non-trivial task. In this paper, we present a novel multi-task learning (MTL) based framewo…
University of Surrey（萨里大学）；iFlyTek-Surrey Joint Research Centre on Artificial Intelligence（讯飞-萨里人工智能联合研究中心）
In this paper, we extend scene understanding to include that of human sketch. The result is a complete trilogy of scene representation from three diverse and complementary modalities -- sketch, photo, and text. Instead of learning a rigid three-way embedding and be done with it, we focus on learning a flexible joint embedding that fully supports the ``optionality" that this complementarity brings. Our embedding supports optionality on two axes: (i) optionality across modalities -- use any combination of modalities as query for downstream tasks like retrieval, (ii) optionality across tasks -- s…
Continuous dimensional emotion prediction is a challenging task where the fusion of various modalities usually achieves state-of-the-art performance such as early fusion or late fusion. In this paper, we propose a novel multi-modal fusion strategy named conditional attention fusion, which can dynamically pay attention to different modalities at each time step. Long-short term memory recurrent neural networks (LSTM-RNN) is applied as the basic uni-modality model to capture long time dependencies. The weights assigned to different modalities are automatically decided by the current input feature…
MMFusion: Multi-modality Diffusion Model for Lymph Node Metastasis Diagnosis in Esophageal Cancer
Shandong University（山东大学）；Hangzhou Dianzi University（杭州电子科技大学）；Communication University of Zhejiang（浙江传媒学院）；University of Leicester（莱斯特大学）；Sichuan Cancer Hospital and Institution（四川省肿瘤医院）；Sichuan Cancer Center（四川省癌症中心）；University of Electronic Science and Technology of China（电子科技大学）；Suzhou Research Institute of Shandong University（山东大学苏州研究院）
State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences（机器人学国家重点实验室，中国科学院沈阳自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Visual-tactile fused sensing for object clustering has achieved significant progresses recently, since the involvement of tactile modality can effectively improve clustering performance. However, the missing data (i.e., partial data) issues always happen due to occlusion and noises during the data collecting process. This issue is not well solved by most existing partial multi-view clustering methods for the heterogeneous modality challenge. Naively employing these methods would inevitably induce a negative effect and further hurt the performance. To solve the mentioned challenges, we propose …
Learning modality invariant features is central to the problem of Visible-Thermal cross-modal Person Reidentification (VT-ReID), where query and gallery images come from different modalities. Existing works implicitly align the modalities in pixel and feature spaces by either using adversarial learning or carefully designing feature extraction modules that heavily rely on domain knowledge. We propose a simple but effective framework, MMD-ReID, that reduces the modality gap by an explicit discrepancy reduction constraint. MMD-ReID takes inspiration from Maximum Mean Discrepancy (MMD), a widely …
National University of Singapore（新加坡国立大学）；University of Moratuwa（莫拉图瓦大学）
The accurate prognosis of Glioblastoma Multiforme (GBM) plays an essential role in planning correlated surgeries and treatments. The conventional models of survival prediction rely on radiomic features using magnetic resonance imaging (MRI). In this paper, we propose a radiogenomic overall survival (OS) prediction approach by incorporating gene expression data with radiomic features such as shape, geometry, and clinical information. We exploit TCGA (The Cancer Genomic Atlas) dataset and synthesize the missing MRI modalities using a fully convolutional network (FCN) in a conditional Generative …
Tel Aviv University（特拉维夫大学）；Sheba Medical Center（谢巴医疗中心）；University College London Hospital（伦敦大学学院医院）
In this work we present a novel system for generation of virtual PET images using CT scans. We combine a fully convolutional network (FCN) with a conditional generative adversarial network (GAN) to generate simulated PET data from given input CT data. The synthesized PET can be used for false-positive reduction in lesion detection solutions. Clinically, such solutions may enable lesion detection and drug treatment evaluation in a CT-only environment, thus reducing the need for the more expensive and radioactive PET/CT scan. Our dataset includes 60 PET/CT scans from Sheba Medical center. We use…
OSDM-MReg: Multimodal Image Registration based One Step Diffusion Model
Shanghai Key Laboratory of Intelligent Sensing and Recognition（上海智能感知与识别重点实验室）；Shanghai Jiao Tong University（上海交通大学）；Center of Digital Innovation（数字创新中心）
Brain Tumour Removing and Missing Modality Generation using 3D WDM
Center Algoritmi / LASI, University of Minho（米尼奥大学Algoritmi中心 / LASI）；Computer Algorithms for Medicine Laboratory（计算机医学算法实验室）；Institute for AI in Medicine (IKIM), University Medicine Essen（埃森大学医学医院医学人工智能研究所）；Institute of Medical Informatics, University Hospital RWTH Aachen（亚琛工业大学医学院医学信息学研究所）；Department of Oral and Maxillofacial Surgery, University Hospital RWTH Aachen（亚琛工业大学医学院口腔颌面外科）；Institute of Computer Graphics and Vision, Graz University of Technology（格拉茨工业大学计算机图形学与视觉研究所）；Cancer Research Center Cologne Essen (CCCE), University Medicine Essen（埃森大学医学医院科隆埃森癌症研究中心）；German Cancer Consortium (DKTK), Partner Site Essen（德国癌症联盟埃森合作站点）；Department of Physics, TU Dortmund University（多特蒙德工业大学物理系）
A Mathematical Perspective On Contrastive Learning
Stores Foundational AI, Amazon, Palo Alto CA 94301 and Pasadena CA 91125（亚马逊公司、帕洛阿尔托加州94301和帕萨迪纳加州91125）；Computing and Mathematical Sciences, California Institute of Technology, Pasadena CA 91125（计算与数学科学系，加州理工学院，帕萨迪纳加州91125）
