Multiple modalities can provide more valuable information than single one by describing the same contents in various ways. Hence, it is highly expected to learn effective joint representation by fusing the features of different modalities. However, previous methods mainly focus on fusing the shallow features or high-level representations generated by unimodal deep networks, which only capture part of the hierarchical correlations across modalities. In this paper, we propose to densely integrate the representations by greedily stacking multiple shared layers between different modality-specific networks, which is named as Dense Multimodal Fusion (DMF). The joint representations in different shared layers can capture the correlations in different levels, and the connection between shared layers also provides an efficient way to learn the dependence among hierarchical correlations. These two properties jointly contribute to the multiple learning paths in DMF, which results in faster convergence, lower training loss, and better performance. We evaluate our model on three typical multimodal learning tasks, including audiovisual speech recognition, cross-modal retrieval, and multimodal classification. The noticeable performance in the experiments demonstrates that our model can learn more effective joint representation.
MagicAnime: A Hierarchically Annotated, Multimodal and Multitasking Dataset with Benchmarks for Cartoon Animation Generation
National Centre for Computer Animation, Bournemouth University（伯恩茅斯大学计算机动画国家中心）；Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Hong Kong University of Science and Technology（香港科技大学）；Department of Computer Science and Information Engineering, National Cheng Kung University（国立成功大学计算机科学与信息工程系）
Think Hierarchically, Act Dynamically: Hierarchical Multi-modal Fusion and Reasoning for Vision-and-Language Navigation
City University of Hong Kong, Dongguan Campus（香港城市大学东莞校区）；The University of Melbourne（墨尔本大学）；Tsinghua University（清华大学）；Baidu Inc.（百度公司）；University of Chinese Academy of Science（中国科学院大学）；National University of Singapore（新加坡国立大学）
Image outpainting technology generates visually plausible content regardless of authenticity, making it unreliable to be applied in practice. Thus, we propose a reliable image outpainting task, introducing the sparse depth from LiDARs to extrapolate authentic RGB scenes. The large field view of LiDARs allows it to serve for data enhancement and further multimodal tasks. Concretely, we propose a Depth-Guided Outpainting Network to model different feature representations of two modalities and learn the structure-aware cross-modal fusion. And two components are designed: 1) The Multimodal Learnin…
The success of multimodal data fusion in deep learning appears to be attributed to the use of complementary in-formation between multiple input data. Compared to their predictive performance, relatively less attention has been devoted to the robustness of multimodal fusion models. In this paper, we investigated whether the current multimodal fusion model utilizes the complementary intelligence to defend against adversarial attacks. We applied gradient based white-box attacks such as FGSM and PGD on MFNet, which is a major multispectral (RGB, Thermal) fusion deep learning model for semantic seg…
There has recently been growing interest in utilizing multimodal sensors to achieve robust lane line segmentation. In this paper, we introduce a novel multimodal fusion architecture from an information theory perspective, and demonstrate its practical utility using Light Detection and Ranging (LiDAR) camera fusion networks. In particular, we develop, for the first time, a multimodal fusion network as a joint coding model, where each single node, layer, and pipeline is represented as a channel. The forward propagation is thus equal to the information transmission in the channels. Then, we can q…
School of Electronics and Information Technology, Sun Yat-sen University（中山大学电子与信息工程学院）
Learning joint embedding space for various modalities is of vital importance for multimodal fusion. Mainstream modality fusion approaches fail to achieve this goal, leaving a modality gap which heavily affects cross-modal fusion. In this paper, we propose a novel adversarial encoder-decoder-classifier framework to learn a modality-invariant embedding space. Since the distributions of various modalities vary in nature, to reduce the modality gap, we translate the distributions of source modalities into that of target modality via their respective encoders using adversarial training. Furthermore…
We propose a compact and effective framework to fuse multimodal features at multiple layers in a single network. The framework consists of two innovative fusion schemes. Firstly, unlike existing multimodal methods that necessitate individual encoders for different modalities, we verify that multimodal features can be learnt within a shared single network by merely maintaining modality-specific batch normalization layers in the encoder, which also enables implicit fusion via joint feature representation learning. Secondly, we propose a bidirectional multi-layer fusion scheme, where multimodal f…
A review of deep learning-based information fusion techniques for multimodal medical image classification
Inserm（法国国家健康与医学研究院）；University of Western Brittany（西布列塔尼大学）；IMT Atlantique（大西洋电信学院）；Sorbonne University（索邦大学）；Lariboisière Hospital（拉里布瓦西耶尔医院）；AP-HP（巴黎公共医疗集团）；Paris Cité University（巴黎城市大学）；CHRU Brest（布雷斯特大学中心医院）；LaTIM UMR 1101（LaTIM联合研究单位1101）
This paper proposes a novel multimodal fusion approach, aiming to produce best possible decisions by integrating information coming from multiple media. While most of the past multimodal approaches either work by projecting the features of different modalities into the same space, or by coordinating the representations of each modality through the use of constraints, our approach borrows from both visions. More specifically, assuming each modality can be processed by a separated deep convolutional network, allowing to take decisions independently from each modality, we introduce a central netw…
Nanjing University of Posts and Telecommunications（南京邮电大学）
Due to the instability and limitations of unimodal biometric systems, multimodal systems have attracted more and more attention from researchers. However, how to exploit the independent and complementary information between different modalities remains a key and challenging problem. In this paper, we propose a multimodal biometric fusion recognition algorithm based on fingerprints and finger veins (Fingerprint Finger Veins-Channel Spatial Attention Fusion Module, FPV-CSAFM). Specifically, for each pair of fingerprint and finger vein images, we first propose a simple and effective Convolutional…
Depression is a leading cause of death worldwide, and the diagnosis of depression is nontrivial. Multimodal learning is a popular solution for automatic diagnosis of depression, and the existing works suffer two main drawbacks: 1) the high-order interactions between different modalities can not be well exploited; and 2) interpretability of the models are weak. To remedy these drawbacks, we propose a multimodal multi-order factor fusion (MMFF) method. Our method can well exploit the high-order interactions between different modalities by extracting and assembling modality factors under the guid…
University of Toronto（多伦多大学）；The Hospital for Sick Children（病童医院）
Medical images play an important role in clinical applications. Multimodal medical images could provide rich information about patients for physicians to diagnose. The image fusion technique is able to synthesize complementary information from multimodal images into a single image. This technique will prevent radiologists switch back and forth between different images and save lots of time in the diagnostic process. In this paper, we introduce a novel Dilated Residual Attention Network for the medical image fusion task. Our network is capable to extract multi-scale deep semantic features. Furt…
While deeply supervised networks are common in recent literature, they typically impose the same learning objective on all transitional layers despite their varying representation powers. In this paper, we propose Hierarchically Supervised Semantic Segmentation (HS3), a training scheme that supervises intermediate layers in a segmentation network to learn meaningful representations by varying task complexity. To enforce a consistent performance vs. complexity trade-off throughout the network, we derive various sets of class clusters to supervise each transitional layer of the network. Furtherm…
IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection
School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院）；University of Macau（澳门大学）；The University of Hong Kong（香港大学）；Inceptio（嬴彻科技）；École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）；Zhejiang University（浙江大学）
University of Campinas (UNICAMP)（坎皮纳斯州立大学）；Université de Lorraine（洛林大学）；Norwegian University of Science and Technology (NTNU)（挪威科技大学）
This paper proposes a learning model, based on rank-fusion graphs, for general applicability in multimodal prediction tasks, such as multimodal regression and image classification. Rank-fusion graphs encode information from multiple descriptors and retrieval models, thus being able to capture underlying relationships between modalities, samples, and the collection itself. The solution is based on the encoding of multiple ranks for a query (or test sample), defined according to different criteria, into a graph. Later, we project the generated graph into an induced vector space, creating fusion …
NMAM Institute of Technology（NMAM 理工学院）；MSR Institute of Technology（MSR 理工学院）
Multimodal medical image fusion helps to increase efficiency in medical diagnosis. This paper presents multimodal medical image fusion by selecting relevant features using Principle Component Analysis (PCA) and Particle Swarm Optimization techniques (PSO). DTCWT is used for decomposition of the images into low and high frequency coefficients. Fusion rules such as combination of minimum, maximum and simple averaging are applied to approximate and detailed coefficients. The fused image is reconstructed by inverse DTCWT. Performance metrics are evaluated and it shows that DTCWT-PCA performs bette…
U3M: Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation
Institute of Artificial Intelligence (TeleAI), China Telecom（中国电信人工智能研究院（TeleAI））；School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University（西北工业大学人工智能、光学与电子学院（iOPEN））
FGU3R: Fine-Grained Fusion via Unified 3D Representation for Multimodal 3D Object Detection
State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications（北京邮电大学网络与交换技术国家重点实验室）；School of Computer Science and Technology, Beijing Jiaotong University（北京交通大学计算机科学与技术学院）
In this paper, we present Fusion-GCN, an approach for multimodal action recognition using Graph Convolutional Networks (GCNs). Action recognition methods based around GCNs recently yielded state-of-the-art performance for skeleton-based action recognition. With Fusion-GCN, we propose to integrate various sensor data modalities into a graph that is trained using a GCN model for multi-modal action recognition. Additional sensor measurements are incorporated into the graph representation, either on a channel dimension (introducing additional node attributes) or spatial dimension (introducing new …
University of Waterloo（滑铁卢大学）；Shenzhen University（深圳大学）
Multimodal learning mimics the reasoning process of the human multi-sensory system, which is used to perceive the surrounding world. While making a prediction, the human brain tends to relate crucial cues from multiple sources of information. In this work, we propose a novel multimodal fusion module that learns to emphasize more contributive features across all modalities. Specifically, the proposed Multimodal Split Attention Fusion (MSAF) module splits each modality into channel-wise equal feature blocks and creates a joint representation that is used to generate soft attention for each chann…
Tasks that rely on multi-modal information typically include a fusion module that combines information from different modalities. In this work, we develop a Refiner Fusion Network (ReFNet) that enables fusion modules to combine strong unimodal representation with strong multimodal representations. ReFNet combines the fusion network with a decoding/defusing module, which imposes a modality-centric responsibility condition. This approach addresses a big gap in existing multimodal fusion frameworks by ensuring that both unimodal and fused representations are strongly encoded in the latent fusion …
DepMamba: Progressive Fusion Mamba for Multimodal Depression Detection
Institute of Science and Technology for Brain-inspired Intelligence, Fudan University（复旦大学脑智能科学与技术研究院）；School of Computer Science, Fudan University（复旦大学计算机科学技术学院）
MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning
CVIU Lab, University of Arkansas, USA（大学实验室，亚利桑那大学，美国）；University of Florida, USA（佛罗里达大学，美国）；COSMOS Research Center, University of Arkansas, Little Rock, USA（研究机构，亚利桑那大学，小石城，美国）；ICSI, University of California, Berkeley, USA（研究机构，加州大学伯克利分校，美国）
MambaTrans: Multimodal Fusion Image Translation via Large Language Model Priors for Downstream Visual Tasks
School of Physics and Optoelectronic Engineering（物理与光电工程学院）；Guangdong-HongKong-Macao Joint Laboratory for Intelligent Micro-Nano Optoelectronic Technology（粤港澳联合智能微纳光电技术实验室）；School of Information Engineering and Automation（信息工程与自动化学院）
本文提出MambaTrans，一种多模态融合图像模态翻译器，利用多模态大语言模型描述和语义分割掩码作为输入，通过Multi-Model State Space Block捕获跨模态依赖，在不调整预训练模型参数的情况下提升下游视觉任务性能。
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…
The fusion of multimodal sensor streams, such as camera, lidar, and radar measurements, plays a critical role in object detection for autonomous vehicles, which base their decision making on these inputs. While existing methods exploit redundant information in good environmental conditions, they fail in adverse weather where the sensory streams can be asymmetrically distorted. These rare "edge-case" scenarios are not represented in available datasets, and existing fusion architectures are not designed to handle them. To address this challenge we present a novel multimodal dataset acquired in o…
Instituto Politécnico Nacional（国立理工学院）；National University of Singapore（新加坡国立大学）；Nanyang Technological University（南洋理工大学）
Multimodal sentiment analysis is a very actively growing field of research. A promising area of opportunity in this field is to improve the multimodal fusion mechanism. We present a novel feature fusion strategy that proceeds in a hierarchical fashion, first fusing the modalities two in two and only then fusing all three modalities. On multimodal sentiment analysis of individual utterances, our strategy outperforms conventional concatenation of features by 1%, which amounts to 5% reduction in error rate. On utterance-level multimodal sentiment analysis of multi-utterance video clips, for which…
University of California, Santa Barbara（加州大学圣巴巴拉分校）；Saratoga High School（萨拉托加高中）；Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）
Multimodal classification is a core task in human-centric machine learning. We observe that information is highly complementary across modalities, thus unimodal information can be drastically sparsified prior to multimodal fusion without loss of accuracy. To this end, we present Sparse Fusion Transformers (SFT), a novel multimodal fusion method for transformers that performs comparably to existing state-of-the-art methods while having greatly reduced memory footprint and computation cost. Key to our idea is a sparse-pooling block that reduces unimodal token sets prior to cross-modality modelin…
Multimodal Fusion Learning with Dual Attention for Medical Imaging
Indian Institute of Technology Ropar（印度理工学院罗帕尔分校）；Deakin University（迪肯大学）；Queensland University of Technology（昆士兰科技大学）；NIMS University（NIMS大学）；Jio Institute（吉奥学院）；RMIT University（皇家墨尔本理工大学）
本文提出含多分支融合与多模态信息融合双注意力模块的DRIFA机制，构建可嵌入任意深度网络的DRIFA-Net，并用集成Monte Carlo dropout估计不确定性，在五个多模态医学数据集上取得优于现有方法的表现。
Beihang University（北京航空航天大学）；Baidu Research（百度研究院）；Beijing Institute of Technology（北京理工大学）
Accurate detection of obstacles in 3D is an essential task for autonomous driving and intelligent transportation. In this work, we propose a general multimodal fusion framework FusionPainting to fuse the 2D RGB image and 3D point clouds at a semantic level for boosting the 3D object detection task. Especially, the FusionPainting framework consists of three main modules: a multi-modal semantic segmentation module, an adaptive attention-based semantic fusion module, and a 3D object detector. First, semantic information is obtained for 2D images and 3D Lidar point clouds based on 2D and 3D segmen…
Shanghai Jiao Tong University（上海交通大学）；University of Electronic Science and Technology of China（电子科技大学）；University of Calgary（卡尔加里大学）
The fusion of images taken by heterogeneous sensors helps to enrich the information and improve the quality of imaging. In this article, we present a hybrid model consisting of a convolutional encoder and a Transformer-based decoder to fuse multimodal images. In the encoder, a non-local cross-modal attention block is proposed to capture both local and global dependencies of multiple source images. A branch fusion module is designed to adaptively fuse the features of the two branches. We embed a Transformer module with linear complexity in the decoder to enhance the reconstruction capability of…
Registration-Free Hybrid Learning Empowers Simple Multimodal Imaging System for High-quality Fusion Detection
School of Electronics and Information Engineering, Wuxi University（无锡大学电子与信息工程学院）；Academy for Engineering and Technology, Fudan University（复旦大学工程与技术学院）
Humans perceive the world by concurrently processing and fusing high-dimensional inputs from multiple modalities such as vision and audio. Machine perception models, in stark contrast, are typically modality-specific and optimised for unimodal benchmarks, and hence late-stage fusion of final representations or predictions from each modality (`late-fusion') is still a dominant paradigm for multimodal video classification. Instead, we introduce a novel transformer based architecture that uses `fusion bottlenecks' for modality fusion at multiple layers. Compared to traditional pairwise self-atten…
