Transformer architectures have brought about fundamental changes to computational linguistic field, which had been dominated by recurrent neural networks for many years. Its success also implies drastic changes in cross-modal tasks with language and vision, and many researchers have already tackled the issue. In this paper, we review some of the most critical milestones in the field, as well as overall trends on how transformer architecture has been incorporated into visuolinguistic cross-modal tasks. Furthermore, we discuss its current limitations and speculate upon some of the prospects that we find imminent.
University of Trento（特伦托大学）；University of Copenhagen（哥本哈根大学）
Pretrained vision-and-language BERTs aim to learn representations that combine information from both modalities. We propose a diagnostic method based on cross-modal input ablation to assess the extent to which these models actually integrate cross-modal information. This method involves ablating inputs from one modality, either entirely or selectively based on cross-modal grounding alignments, and evaluating the model prediction performance on the other modality. Model performance is measured by modality-specific tasks that mirror the model pretraining objectives (e.g. masked language modellin…
South China University of Technology（华南理工大学）；International Digital Economy Academy (IDEA)（国际数字经济研究院（IDEA））
Multi-modal named entity recognition (MNER) aims at identifying entity spans and recognizing their categories in social media posts with the aid of images. However, in dominant MNER approaches, the interaction of different modalities is usually carried out through the alternation of self-attention and cross-attention or over-reliance on the gating machine, which results in imprecise and biased correspondence between fine-grained semantic units of text and image. To address this issue, we propose a Flat Multi-modal Interaction Transformer (FMIT) for MNER. Specifically, we first utilize noun phr…
In this paper, inspired by the successes of visionlanguage pre-trained models and the benefits from training with adversarial attacks, we present a novel transformerbased cross-modal fusion modeling by incorporating the both notions for VQA challenge 2021. Specifically, the proposed model is on top of the architecture of VinVL model [19], and the adversarial training strategy [4] is applied to make the model robust and generalized. Moreover, two implementation tricks are also used in our system to obtain better results. The experiments demonstrate that the novel framework can achieve 76.72% on…
School of Computer Science, Southeast University（东南大学计算机科学与工程学院）
Most of existing RGB-D salient object detection (SOD) methods follow the CNN-based paradigm, which is unable to model long-range dependencies across space and modalities due to the natural locality of CNNs. Here we propose the Hierarchical Cross-modal Transformer (HCT), a new multi-modal transformer, to tackle this problem. Unlike previous multi-modal transformers that directly connecting all patches from two modalities, we explore the cross-modal complementarity hierarchically to respect the modality gap and spatial discrepancy in unaligned regions. Specifically, we propose to use intra-modal…
Rutgers University（罗格斯大学）；The Chinese University of Hong Kong（香港中文大学）；University of Illinois at Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）；Mitsubishi Electric Research Laboratories (MERL)（三菱电机研究实验室）
Given an input video, its associated audio, and a brief caption, the audio-visual scene aware dialog (AVSD) task requires an agent to indulge in a question-answer dialog with a human about the audio-visual content. This task thus poses a challenging multi-modal representation learning and reasoning scenario, advancements into which could influence several human-machine interaction applications. To solve this task, we introduce a semantics-controlled multi-modal shuffled Transformer reasoning framework, consisting of a sequence of Transformer modules, each taking a modality as input and produci…
University of Delaware（特拉华大学）；Snap Inc.（Snap公司）；Google Research（谷歌研究院）
Multimodal data collected from the real world are often imperfect due to missing modalities. Therefore multimodal models that are robust against modal-incomplete data are highly preferred. Recently, Transformer models have shown great success in processing multimodal data. However, existing work has been limited to either architecture designs or pre-training strategies; whether Transformer models are naturally robust against missing-modal data has rarely been investigated. In this paper, we present the first-of-its-kind work to comprehensively investigate the behavior of Transformers in the pr…
This paper presents a pure transformer-based approach, dubbed the Multi-Modal Video Transformer (MM-ViT), for video action recognition. Different from other schemes which solely utilize the decoded RGB frames, MM-ViT operates exclusively in the compressed video domain and exploits all readily available modalities, i.e., I-frames, motion vectors, residuals and audio waveform. In order to handle the large number of spatiotemporal tokens extracted from multiple modalities, we develop several scalable model variants which factorize self-attention across the space, time and modality dimensions. In …
Crowd counting aims to estimate the number of persons in a scene. Most state-of-the-art crowd counting methods based on color images can't work well in poor illumination conditions due to invisible objects. With the widespread use of infrared cameras, crowd counting based on color and thermal images is studied. Existing methods only achieve multi-modal fusion without count objective constraint. To better excavate multi-modal information, we use count-guided multi-modal fusion and modal-guided count enhancement to achieve the impressive performance. The proposed count-guided multi-modal fusion …
Multi-modal skin lesion diagnosis (MSLD) has achieved remarkable success by modern computer-aided diagnosis (CAD) technology based on deep convolutions. However, the information aggregation across modalities in MSLD remains challenging due to severity unaligned spatial resolution (e.g., dermoscopic image and clinical image) and heterogeneous data (e.g., dermoscopic image and patients' meta-data). Limited by the intrinsic local attention, most recent MSLD pipelines using pure convolutions struggle to capture representative features in shallow layers, thus the fusion across different modalities …
Harbin Institute of Technology（哈尔滨工业大学）；Huawei Technologies Co., Ltd（华为技术有限公司）
Cross-model retrieval has emerged as one of the most important upgrades for text-only search engines (SE). Recently, with powerful representation for pairwise text-image inputs via early interaction, the accuracy of vision-language (VL) transformers has outperformed existing methods for text-image retrieval. However, when the same paradigm is used for inference, the efficiency of the VL transformers is still too low to be applied in a real cross-modal SE. Inspired by the mechanism of human learning and using cross-modal knowledge, this paper presents a novel Vision-Language Decomposed Transfor…
State University of New York at Binghamton（纽约州立大学宾汉姆顿分校）
Multi-modal learning has been intensified in recent years, especially for applications in facial analysis and action unit detection whilst there still exist two main challenges in terms of 1) relevant feature learning for representation and 2) efficient fusion for multi-modalities. Recently, there are a number of works have shown the effectiveness in utilizing the attention mechanism for AU detection, however, most of them are binding the region of interest (ROI) with features but rarely apply attention between features of each AU. On the other hand, the transformer, which utilizes a more effi…
In autonomous driving, LiDAR point-clouds and RGB images are two major data modalities with complementary cues for 3D object detection. However, it is quite difficult to sufficiently use them, due to large inter-modal discrepancies. To address this issue, we propose a novel framework, namely Contrastively Augmented Transformer for multi-modal 3D object Detection (CAT-Det). Specifically, CAT-Det adopts a two-stream structure consisting of a Pointformer (PT) branch, an Imageformer (IT) branch along with a Cross-Modal Transformer (CMT) module. PT, IT and CMT jointly encode intra-modal and inter-m…
In this paper, we present a cross-modal recipe retrieval framework, Transformer-based Network for Large Batch Training (TNLBT), which is inspired by ACME~(Adversarial Cross-Modal Embedding) and H-T~(Hierarchical Transformer). TNLBT aims to accomplish retrieval tasks while generating images from recipe embeddings. We apply the Hierarchical Transformer-based recipe text encoder, the Vision Transformer~(ViT)-based recipe image encoder, and an adversarial network architecture to enable better cross-modal embedding learning for recipe texts and images. In addition, we use self-supervised learning t…
Tianjin University（天津大学）；The University of Hong Kong（香港大学）；Huanhu Hospital（环湖医院）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；The Hong Kong University of Science and Technology（香港科技大学）
Multi-modal MR imaging is routinely used in clinical practice to diagnose and investigate brain tumors by providing rich complementary information. Previous multi-modal MRI segmentation methods usually perform modal fusion by concatenating multi-modal MRIs at an early/middle stage of the network, which hardly explores non-linear dependencies between modalities. In this work, we propose a novel Nested Modality-Aware Transformer (NestedFormer) to explicitly explore the intra-modality and inter-modality relationships of multi-modal MRIs for brain tumor segmentation. Built on the transformer-based…
Over the past decade, convolutional neural networks (CNN) have shown very competitive performance in medical image analysis tasks, such as disease classification, tumor segmentation, and lesion detection. CNN has great advantages in extracting local features of images. However, due to the locality of convolution operation, it can not deal with long-range relationships well. Recently, transformers have been applied to computer vision and achieved remarkable success in large-scale datasets. Compared with natural images, multi-modal medical images have explicit and important long-range dependenci…
The task of retrieving video content relevant to natural language queries plays a critical role in effectively handling internet-scale datasets. Most of the existing methods for this caption-to-video retrieval problem do not fully exploit cross-modal cues present in video. Furthermore, they aggregate per-frame visual features with limited or no temporal information. In this paper, we present a multi-modal transformer to jointly encode the different modalities in video, which allows each of them to attend to the others. The transformer architecture is also leveraged to encode and model the temp…
Dense video captioning aims to localize and describe important events in untrimmed videos. Existing methods mainly tackle this task by exploiting only visual features, while completely neglecting the audio track. Only a few prior works have utilized both modalities, yet they show poor results or demonstrate the importance on a dataset with a specific domain. In this paper, we introduce Bi-modal Transformer which generalizes the Transformer architecture for a bi-modal input. We show the effectiveness of the proposed model with audio and visual modalities on the dense video captioning task, yet …
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…
Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学智能产业研究院（AIR））
Many adaptations of transformers have emerged to address the single-modal vision tasks, where self-attention modules are stacked to handle input sources like images. Intuitively, feeding multiple modalities of data to vision transformers could improve the performance, yet the inner-modal attentive weights may also be diluted, which could thus undermine the final performance. In this paper, we propose a multimodal token fusion method (TokenFusion), tailored for transformer-based vision tasks. To effectively fuse multiple modalities, TokenFusion dynamically detects uninformative tokens and subst…
Facial expression recognition is an essential task for various applications, including emotion detection, mental health analysis, and human-machine interactions. In this paper, we propose a multi-modal facial expression recognition method that exploits audio information along with facial images to provide a crucial clue to differentiate some ambiguous facial expressions. Specifically, we introduce a Modal Fusion Module (MFM) to fuse audio-visual information, where image and audio features are extracted from Swin Transformer. Additionally, we tackle the imbalance problem in the dataset by emplo…
Goethe University Frankfurt（法兰克福歌德大学）；Columbia University（哥伦比亚大学）；MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；IBM Research AI（IBM研究院人工智能部门）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；UT Austin（德克萨斯大学奥斯汀分校）
Multi-modal learning from video data has seen increased attention recently as it allows to train semantically meaningful embeddings without human annotation enabling tasks like zero-shot retrieval and classification. In this work, we present a multi-modal, modality agnostic fusion transformer approach that learns to exchange information between multiple modalities, such as video, audio, and text, and integrate them into a joined multi-modal representation to obtain an embedding that aggregates multi-modal temporal information. We propose to train the system with a combinatorial loss on everyth…
Multispectral image pairs can provide the combined information, making object detection applications more reliable and robust in the open world. To fully exploit the different modalities, we present a simple yet effective cross-modality feature fusion approach, named Cross-Modality Fusion Transformer (CFT) in this paper. Unlike prior CNNs-based works, guided by the transformer scheme, our network learns long-range dependencies and integrates global contextual information in the feature extraction stage. More importantly, by leveraging the self attention of the transformer, the network can natu…
Tel Aviv University（特拉维夫大学）；Facebook AI Research (FAIR)（Facebook AI研究院）
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 mechanisms. These attention modules also play a role in other computer vision tasks including object detection and image segmentation. Unlike Transformers that only use self-attention, Transformers with co-attention require to consider multiple attention maps in parallel in order to highlight the information that is relevant to the prediction in the model's input…
FM-ViT: Flexible Modal Vision Transformers for Face Anti-Spoofing
Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）；Baidu Research（百度研究院）；Great Bay University（大湾区大学）；Mininglamp Academy of Sciences, Mininglamp Technology（明略科技明略科学院）；Macau University of Science and Technology（澳门科技大学）；Westlake University（西湖大学）
Fraunhofer IOSB（弗劳恩霍夫光学、电子与精密工程研究所）；Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院）
Although human action anticipation is a task which is inherently multi-modal, state-of-the-art methods on well known action anticipation datasets leverage this data by applying ensemble methods and averaging scores of unimodal anticipation networks. In this work we introduce transformer based modality fusion techniques, which unify multi-modal data at an early stage. Our Anticipative Feature Fusion Transformer (AFFT) proves to be superior to popular score fusion approaches and presents state-of-the-art results outperforming previous methods on EpicKitchens-100 and EGTEA Gaze+. Our model is eas…
Convolutional neural networks (CNNs) are good at extracting contexture features within certain receptive fields, while transformers can model the global long-range dependency features. By absorbing the advantage of transformer and the merit of CNN, Swin Transformer shows strong feature representation ability. Based on it, we propose a cross-modality fusion model SwinNet for RGB-D and RGB-T salient object detection. It is driven by Swin Transformer to extract the hierarchical features, boosted by attention mechanism to bridge the gap between two modalities, and guided by edge information to sha…
MS-DETR: Multispectral Pedestrian Detection Transformer with Loosely Coupled Fusion and Modality-Balanced Optimization
School of Computer Science, Northwestern Polytechnical University（西北工业大学计算机学院）；Research Development Institute of Northwestern Polytechnical University in Shenzhen（西北工业大学深圳研究院）
The widespread dissemination of Deepfakes demands effective approaches that can detect perceptually convincing forged images. In this paper, we aim to capture the subtle manipulation artifacts at different scales using transformer models. In particular, we introduce a Multi-modal Multi-scale TRansformer (M2TR), which operates on patches of different sizes to detect local inconsistencies in images at different spatial levels. M2TR further learns to detect forgery artifacts in the frequency domain to complement RGB information through a carefully designed cross modality fusion block. In addition…
Improving the resolution of magnetic resonance (MR) image data is critical to computer-aided diagnosis and brain function analysis. Higher resolution helps to capture more detailed content, but typically induces to lower signal-to-noise ratio and longer scanning time. To this end, MR image super-resolution has become a widely-interested topic in recent times. Existing works establish extensive deep models with the conventional architectures based on convolutional neural networks (CNN). In this work, to further advance this research field, we make an early effort to build a Transformer-based MR…
The success of deep learning heavily relies on large-scale data with comprehensive labels, which is more expensive and time-consuming to fetch in 3D compared to 2D images or natural languages. This promotes the potential of utilizing models pretrained with data more than 3D as teachers for cross-modal knowledge transferring. In this paper, we revisit masked modeling in a unified fashion of knowledge distillation, and we show that foundational Transformers pretrained with 2D images or natural languages can help self-supervised 3D representation learning through training Autoencoders as Cross-Mo…
University of Science and Technology of China（中国科学技术大学）；Sun Yat-sen University（中山大学）；Microsoft Research（微软研究院）；University of Rochester（罗切斯特大学）
Vision-Language Pre-training (VLP) aims to learn multi-modal representations from image-text pairs and serves for downstream vision-language tasks in a fine-tuning fashion. The dominant VLP models adopt a CNN-Transformer architecture, which embeds images with a CNN, and then aligns images and text with a Transformer. Visual relationship between visual contents plays an important role in image understanding and is the basic for inter-modal alignment learning. However, CNNs have limitations in visual relation learning due to local receptive field's weakness in modeling long-range dependencies. T…
Most of the existing bi-modal (RGB-D and RGB-T) salient object detection methods utilize the convolution operation and construct complex interweave fusion structures to achieve cross-modal information integration. The inherent local connectivity of the convolution operation constrains the performance of the convolution-based methods to a ceiling. In this work, we rethink these tasks from the perspective of global information alignment and transformation. Specifically, the proposed \underline{c}ross-mod\underline{a}l \underline{v}iew-mixed transform\underline{er} (CAVER) cascades several cross-…
The George Washington University（乔治华盛顿大学）；Children’s National Hospital（国家儿童医院）
Accurate nerve identification is critical during surgical procedures for preventing any damages to nerve tissues. Nerve injuries can lead to long-term detrimental effects for patients as well as financial overburdens. In this study, we develop a deep-learning network framework using the U-Net architecture with a Transformer block based fusion module at the bottleneck to identify nerve tissues from a multi-modal optical imaging system. By leveraging and extracting the feature maps of each modality independently and using each modalities information for cross-modal interactions, we aim to provid…
University of Electronic Science and Technology of China（中国电子科技大学）
Facial Action Coding System is an important approach of facial expression analysis.This paper describes our submission to the third Affective Behavior Analysis (ABAW) 2022 competition. We proposed a transfomer based model to detect facial action unit (FAU) in video. To be specific, we firstly trained a multi-modal model to extract both audio and visual feature. After that, we proposed a action units correlation module to learn relationships between each action unit labels and refine action unit detection result. Experimental results on validation dataset shows that our method achieves better p…
Cross-modal recipe retrieval has recently gained substantial attention due to the importance of food in people's lives, as well as the availability of vast amounts of digital cooking recipes and food images to train machine learning models. In this work, we revisit existing approaches for cross-modal recipe retrieval and propose a simplified end-to-end model based on well established and high performing encoders for text and images. We introduce a hierarchical recipe Transformer which attentively encodes individual recipe components (titles, ingredients and instructions). Further, we propose a…
Transformer-based Multi-Modal Learning for Multi Label Remote Sensing Image Classification
Faculty of Electrical Engineering and Computer Science, Technische Universität Berlin（柏林工业大学电机工程与计算机科学学院）；BIFOLD – Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所）
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…
Aggregating multi-modality data to obtain reliable data representation attracts more and more attention. Recent studies demonstrate that Transformer models usually work well for multi-modality tasks. Existing Transformers generally either adopt the Cross-Attention (CA) mechanism or simple concatenation to achieve the information interaction among different modalities which generally ignore the issue of modality gap. In this work, we re-think Transformer and extend it to MutualFormer for multi-modality data representation. Rather than CA in Transformer, MutualFormer employs our new design of Cr…
Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Northwestern Polytechnical University（西北工业大学）；Terminus Group（特斯联集团）；Institute of High Performance Computing, A*STAR（新加坡科技研究局高性能计算研究所）
Accelerated multi-modal magnetic resonance (MR) imaging is a new and effective solution for fast MR imaging, providing superior performance in restoring the target modality from its undersampled counterpart with guidance from an auxiliary modality. However, existing works simply combine the auxiliary modality as prior information, lacking in-depth investigations on the potential mechanisms for fusing different modalities. Further, they usually rely on the convolutional neural networks (CNNs), which is limited by the intrinsic locality in capturing the long-distance dependency. To this end, we …
Cross-modal image-recipe retrieval has gained significant attention in recent years. Most work focuses on improving cross-modal embeddings using unimodal encoders, that allow for efficient retrieval in large-scale databases, leaving aside cross-attention between modalities which is more computationally expensive. We propose a new retrieval framework, T-Food (Transformer Decoders with MultiModal Regularization for Cross-Modal Food Retrieval) that exploits the interaction between modalities in a novel regularization scheme, while using only unimodal encoders at test time for efficient retrieval.…
Seoul National University（首尔国立大学）；NVIDIA Research（英伟达研究院）；Microsoft Research（微软研究院）
The recent success of Transformers in the language domain has motivated adapting it to a multimodal setting, where a new visual model is trained in tandem with an already pretrained language model. However, due to the excessive memory requirements from Transformers, existing work typically fixes the language model and train only the vision module, which limits its ability to learn cross-modal information in an end-to-end manner. In this work, we focus on reducing the parameters of multimodal Transformers in the context of audio-visual video representation learning. We alleviate the high memory…
