Oftentimes, patterns can be represented through different modalities. For example, leaf data can be in the form of images or contours. Handwritten characters can also be either online or offline. To exploit this fact, we propose the use of self-augmentation and combine it with multi-modal feature embedding. In order to take advantage of the complementary information from the different modalities, the self-augmented multi-modal feature embedding employs a shared feature space. Through experimental results on classification with online handwriting and leaf images, we demonstrate that the proposed method can create effective embeddings.
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 video understanding, most cross-modal knowledge distillation (KD) methods are tailored for classification tasks, focusing on the discriminative representation of the trimmed videos. However, action detection requires not only categorizing actions, but also localizing them in untrimmed videos. Therefore, transferring knowledge pertaining to temporal relations is critical for this task which is missing in the previous cross-modal KD frameworks. To this end, we aim at learning an augmented RGB representation for action detection, taking advantage of additional modalities at training time throu…
CLIP (Contrastive Language-Image Pre-Training) has shown remarkable zero-shot transfer capabilities in cross-modal correlation tasks such as visual classification and image retrieval. However, its performance in cross-modal generation tasks like zero-shot image captioning remains unsatisfied. In this work, we discuss that directly employing CLIP for zero-shot image captioning relies more on the textual modality in context and largely ignores the visual information, which we call \emph{contextual language prior}. To address this, we propose Cross-modal Language Models (CLMs) to facilitate unsup…
Nanyang Technological University（南洋理工大学）；Singapore Management University（新加坡管理大学）；Salesforce Research Asia（赛富时亚洲研究院）
This paper investigates an open research problem of generating text-image pairs to improve the training of fine-grained image-to-text cross-modal retrieval task, and proposes a novel framework for paired data augmentation by uncovering the hidden semantic information of StyleGAN2 model. Specifically, we first train a StyleGAN2 model on the given dataset. We then project the real images back to the latent space of StyleGAN2 to obtain the latent codes. To make the generated images manipulatable, we further introduce a latent space alignment module to learn the alignment between StyleGAN2 latent …
TPCap: Unlocking Zero-Shot Image Captioning with Trigger-Augmented and Multi-Modal Purification Modules
Faculty of Information Engineering and Automation, Kunming University of Science and Technology（昆明理工大学信息工程与自动化学院）；Yunnan Key Laboratory of Computer Technologies Application（云南省计算机技术应用重点实验室）；Hongyun Honghe Group Honghe Cigarette Factory（红云红河集团红河卷烟厂）
Renmin University of China（中国人民大学）；University of Surrey（萨里大学）；Alibaba Group（阿里巴巴集团）
Most recent few-shot learning (FSL) methods are based on meta-learning with episodic training. In each meta-training episode, a discriminative feature embedding and/or classifier are first constructed from a support set in an inner loop, and then evaluated in an outer loop using a query set for model updating. This query set sample centered learning objective is however intrinsically limited in addressing the lack of training data problem in the support set. In this paper, a novel contrastive prototype learning with augmented embeddings (CPLAE) model is proposed to overcome this limitation. Fi…
CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric Reasoning
School of Software Engineering, Huazhong University of Science and Technology（华中科技大学软件学院）；Nanyang Technological University, Singapore（新加坡南洋理工大学）；University College London（伦敦大学学院）
We propose and investigate an identity sensitive joint embedding of face and voice. Such an embedding enables cross-modal retrieval from voice to face and from face to voice. We make the following four contributions: first, we show that the embedding can be learnt from videos of talking faces, without requiring any identity labels, using a form of cross-modal self-supervision; second, we develop a curriculum learning schedule for hard negative mining targeted to this task, that is essential for learning to proceed successfully; third, we demonstrate and evaluate cross-modal retrieval for ident…
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…
Automatically describing video, or video captioning, has been widely studied in the multimedia field. This paper proposes a new task of sensor-augmented egocentric-video captioning, a newly constructed dataset for it called MMAC Captions, and a method for the newly proposed task that effectively utilizes multi-modal data of video and motion sensors, or inertial measurement units (IMUs). While conventional video captioning tasks have difficulty in dealing with detailed descriptions of human activities due to the limited view of a fixed camera, egocentric vision has greater potential to be used …
Autonomous University of Barcelona（巴塞罗那自治大学）；Indian Statistical Institute（印度统计研究所）
In this work we introduce a cross modal image retrieval system that allows both text and sketch as input modalities for the query. A cross-modal deep network architecture is formulated to jointly model the sketch and text input modalities as well as the the image output modality, learning a common embedding between text and images and between sketches and images. In addition, an attention model is used to selectively focus the attention on the different objects of the image, allowing for retrieval with multiple objects in the query. Experiments show that the proposed method performs the best i…
NAVER AI Lab（NAVER人工智能实验室）；NAVER LABS Europe（NAVER欧洲实验室）
Cross-modal retrieval methods build a common representation space for samples from multiple modalities, typically from the vision and the language domains. For images and their captions, the multiplicity of the correspondences makes the task particularly challenging. Given an image (respectively a caption), there are multiple captions (respectively images) that equally make sense. In this paper, we argue that deterministic functions are not sufficiently powerful to capture such one-to-many correspondences. Instead, we propose to use Probabilistic Cross-Modal Embedding (PCME), where samples fro…
University of Science and Technology of China（中国科学技术大学）；WeChat, Tencent Inc.（腾讯微信事业部）；National University of Singapore（新加坡国立大学）；Fudan University（复旦大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
Multi-label image and video classification are fundamental yet challenging tasks in computer vision. The main challenges lie in capturing spatial or temporal dependencies between labels and discovering the locations of discriminative features for each class. In order to overcome these challenges, we propose to use cross-modality attention with semantic graph embedding for multi label classification. Based on the constructed label graph, we propose an adjacency-based similarity graph embedding method to learn semantic label embeddings, which explicitly exploit label relationships. Then our nove…
National Library of Medicine（国家医学图书馆）；National Institutes of Health（美国国立卫生研究院）；Saint Louis University（圣路易斯大学）
Deep learning (DL) has drawn tremendous attention in object localization and recognition for both natural and medical images. U-Net segmentation models have demonstrated superior performance compared to conventional handcrafted feature-based methods. Medical image modality-specific DL models are better at transferring domain knowledge to a relevant target task than those that are pretrained on stock photography images. This helps improve model adaptation, generalization, and class-specific region of interest (ROI) localization. In this study, we train chest X-ray (CXR) modality-specific U-Nets…
University of Bristol（布里斯托大学）；Naver Labs Europe（Naver欧洲实验室）
We address the problem of cross-modal fine-grained action retrieval between text and video. Cross-modal retrieval is commonly achieved through learning a shared embedding space, that can indifferently embed modalities. In this paper, we propose to enrich the embedding by disentangling parts-of-speech (PoS) in the accompanying captions. We build a separate multi-modal embedding space for each PoS tag. The outputs of multiple PoS embeddings are then used as input to an integrated multi-modal space, where we perform action retrieval. All embeddings are trained jointly through a combination of PoS…
Memorial Sloan-Kettering Cancer Center（纪念斯隆-凯特琳癌症中心）
Lack of large expert annotated MR datasets makes training deep learning models difficult. Therefore, a cross-modality (MR-CT) deep learning segmentation approach that augments training data using pseudo MR images produced by transforming expert-segmented CT images was developed. Eighty-One T2-weighted MRI scans from 28 patients with non-small cell lung cancers were analyzed. Cross-modality prior encoding the transformation of CT to pseudo MR images resembling T2w MRI was learned as a generative adversarial deep learning model. This model augmented training data arising from 6 expert-segmented …
National University of Singapore（新加坡国立大学）；Zhejiang Gongshang University（浙江工商大学）；Hefei University of Technology（合肥工业大学）
The rapid growth of user-generated videos on the Internet has intensified the need for text-based video retrieval systems. Traditional methods mainly favor the concept-based paradigm on retrieval with simple queries, which are usually ineffective for complex queries that carry far more complex semantics. Recently, embedding-based paradigm has emerged as a popular approach. It aims to map the queries and videos into a shared embedding space where semantically-similar texts and videos are much closer to each other. Despite its simplicity, it forgoes the exploitation of the syntactic structure of…
CR-JEPA: Cross-Modal Joint-Embedding Predictive Learning for Remote Sensing Image Retrieval
Space Applications Centre, Indian Space Research Organisation（印度空间研究组织空间应用中心）；Centre of Studies in Resources Engineering, Indian Institute of Technology Bombay（印度理工学院孟买资源工程研究中心）
RAGTrack: Language-aware RGBT Tracking with Retrieval-Augmented Generation
College of Command and Control Engineering, Army Engineering University of PLA（中国人民解放军陆军工程大学指挥控制工程学院）；School of Future Technology, Dalian University of Technology（大连理工大学未来技术学院）；School of Information and Communication Engineering, Dalian University of Technology（大连理工大学信息与通信工程学院）
Georgia Institute of Technology（佐治亚理工学院）；Wuhan University of Technology（武汉理工大学）
This paper presents a three-tier modality alignment approach to learning text-image joint embedding, coined as JEMA, for cross-modal retrieval of cooking recipes and food images. The first tier improves recipe text embedding by optimizing the LSTM networks with term extraction and ranking enhanced sequence patterns, and optimizes the image embedding by combining the ResNeXt-101 image encoder with the category embedding using wideResNet-50 with word2vec. The second tier modality alignment optimizes the textual-visual joint embedding loss function using a double batch-hard triplet loss with soft…
Johns Hopkins University（约翰斯·霍普金斯大学）；Ludwig-Maximilians-Universität München（慕尼黑大学）；Johns Hopkins Hospital（约翰斯·霍普金斯医院）；Technische Universität München（慕尼黑工业大学）
Fluoroscopic X-ray guidance is a cornerstone for percutaneous orthopaedic surgical procedures. However, two-dimensional observations of the three-dimensional anatomy suffer from the effects of projective simplification. Consequently, many X-ray images from various orientations need to be acquired for the surgeon to accurately assess the spatial relations between the patient's anatomy and the surgical tools. In this paper, we present an on-the-fly surgical support system that provides guidance using augmented reality and can be used in quasi-unprepared operating rooms. The proposed system build…
Memory-Augmented Incomplete Multimodal Survival Prediction via Cross-Slide and Gene-Attentive Hypergraph Learning
Faculty of Computing, Harbin Institute of Technology（哈尔滨工业大学计算机学院）；School of Software, Tsinghua University（清华大学软件学院）；School of Computer Science and Engineering, UNSW Sydney（新南威尔士大学计算机科学与工程学院）
Vision-and-language multi-modal pretraining and fine-tuning have shown great success in visual question answering (VQA). Compared to general domain VQA, the performance of biomedical VQA suffers from limited data. In this paper, we propose a retrieval-augmented pretrain-and-finetune paradigm named RAMM for biomedical VQA to overcome the data limitation issue. Specifically, we collect a new biomedical dataset named PMCPM which offers patient-based image-text pairs containing diverse patient situations from PubMed. Then, we pretrain the biomedical multi-modal model to learn visual and textual re…
Massachusetts Institute of Technology（麻省理工学院）；Computer Science and Artificial Intelligence Laboratory（计算机科学与人工智能实验室）
Recent advances in representation learning have demonstrated an ability to represent information from different modalities such as video, text, and audio in a single high-level embedding vector. In this work we present a self-supervised learning framework that is able to learn a representation that captures finer levels of granularity across different modalities such as concepts or events represented by visual objects or spoken words. Our framework relies on a discretized embedding space created via vector quantization that is shared across different modalities. Beyond the shared embedding spa…
Microsoft Cognition（微软认知）；USC Institute for Creative Technologies（南加州大学创意技术研究所）
Visual-semantic embedding aims to find a shared latent space where related visual and textual instances are close to each other. Most current methods learn injective embedding functions that map an instance to a single point in the shared space. Unfortunately, injective embedding cannot effectively handle polysemous instances with multiple possible meanings; at best, it would find an average representation of different meanings. This hinders its use in real-world scenarios where individual instances and their cross-modal associations are often ambiguous. In this work, we introduce Polysemous I…
Multi-modal word semantics aims to enhance embeddings with perceptual input, assuming that human meaning representation is grounded in sensory experience. Most research focuses on evaluation involving direct visual input, however, visual grounding can contribute to linguistic applications as well. Another motivation for this paper is the growing need for more interpretable models and for evaluating model efficiency regarding size and performance. This work explores the impact of visual information for semantics when the evaluation involves no direct visual input, specifically semantic similari…
While many approaches exist in the literature to learn low-dimensional representations for data collections in multiple modalities, the generalizability of multi-modal nonlinear embeddings to previously unseen data is a rather overlooked subject. In this work, we first present a theoretical analysis of learning multi-modal nonlinear embeddings in a supervised setting. Our performance bounds indicate that for successful generalization in multi-modal classification and retrieval problems, the regularity of the interpolation functions extending the embedding to the whole data space is as importan…
Singapore Management University（新加坡管理大学）；Salesforce Research Asia（Salesforce亚洲研究院）
Food computing is playing an increasingly important role in human daily life, and has found tremendous applications in guiding human behavior towards smart food consumption and healthy lifestyle. An important task under the food-computing umbrella is retrieval, which is particularly helpful for health related applications, where we are interested in retrieving important information about food (e.g., ingredients, nutrition, etc.). In this paper, we investigate an open research task of cross-modal retrieval between cooking recipes and food images, and propose a novel framework Adversarial Cross-…
In this paper, we propose a novel approach for generalized zero-shot learning in a multi-modal setting, where we have novel classes of audio/video during testing that are not seen during training. We use the semantic relatedness of text embeddings as a means for zero-shot learning by aligning audio and video embeddings with the corresponding class label text feature space. Our approach uses a cross-modal decoder and a composite triplet loss. The cross-modal decoder enforces a constraint that the class label text features can be reconstructed from the audio and video embeddings of data points. …
As an effective way to integrate the information contained in multiple medical images under different modalities, medical image synthesis and fusion have emerged in various clinical applications such as disease diagnosis and treatment planning. In this paper, an invertible and variable augmented network (iVAN) is proposed for medical image synthesis and fusion. In iVAN, the channel number of the network input and output is the same through variable augmentation technology, and data relevance is enhanced, which is conducive to the generation of characterization information. Meanwhile, the inver…
In this paper, the problem of multi-view embedding from different visual cues and modalities is considered. We propose a unified solution for subspace learning methods using the Rayleigh quotient, which is extensible for multiple views, supervised learning, and non-linear embeddings. Numerous methods including Canonical Correlation Analysis, Partial Least Sqaure regression and Linear Discriminant Analysis are studied using specific intrinsic and penalty graphs within the same framework. Non-linear extensions based on kernels and (deep) neural networks are derived, achieving better performance …
Remote Sensing Retrieval-Augmented Generation: Bridging Remote Sensing Imagery and Comprehensive Knowledge with a Multi-Modal Dataset and Retrieval-Augmented Generation Model
School of Cyber Science and Technology, University of Science and Technology of China（信息科学技术学院，中国科学技术大学）；China Academy of Electronics and Information Technology（电子信息技术研究院）
The goal of this work is to train discriminative cross-modal embeddings without access to manually annotated data. Recent advances in self-supervised learning have shown that effective representations can be learnt from natural cross-modal synchrony. We build on earlier work to train embeddings that are more discriminative for uni-modal downstream tasks. To this end, we propose a novel training strategy that not only optimises metrics across modalities, but also enforces intra-class feature separation within each of the modalities. The effectiveness of the method is demonstrated on two downstr…
Singapore Management University（新加坡管理大学）；Nanyang Technological University（南洋理工大学）；Salesforce Research Asia（Salesforce亚洲研究院）
Food retrieval is an important task to perform analysis of food-related information, where we are interested in retrieving relevant information about the queried food item such as ingredients, cooking instructions, etc. In this paper, we investigate cross-modal retrieval between food images and cooking recipes. The goal is to learn an embedding of images and recipes in a common feature space, such that the corresponding image-recipe embeddings lie close to one another. Two major challenges in addressing this problem are 1) large intra-variance and small inter-variance across cross-modal food d…
Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn cross-modal embeddings for video and text, yet without exploiting its full potential. In particular, previous losses do not take the intra-modality similarities into account, which leads to inefficient embeddings, as the same content is mapped to multiple points in the embedding space. With CrossCLR, we present a contrastive loss that fixes this issue. Moreover, we define sets of highly related samples in terms of the…
State of the art architectures for untrimmed video Temporal Action Localization (TAL) have only considered RGB and Flow modalities, leaving the information-rich audio modality totally unexploited. Audio fusion has been explored for the related but arguably easier problem of trimmed (clip-level) action recognition. However, TAL poses a unique set of challenges. In this paper, we propose simple but effective fusion-based approaches for TAL. To the best of our knowledge, our work is the first to jointly consider audio and video modalities for supervised TAL. We experimentally show that our scheme…
Apple（苹果公司）；Facebook AI Research（Facebook 人工智能研究院）；Herophilus, Inc.（Herophilus 公司）
Without positional information, attention-based Transformer neural networks are permutation-invariant. Absolute or relative positional embeddings are the most popular ways to feed Transformer models with positional information. Absolute positional embeddings are simple to implement, but suffer from generalization issues when evaluating on sequences longer than seen at training time. Relative positions are more robust to input length change, but are more complex to implement and yield inferior model throughput due to extra computational and memory costs. In this paper, we propose an augmentatio…
