Textual-visual cross-modal retrieval has been a hot research topic in both computer vision and natural language processing communities. Learning appropriate representations for multi-modal data is crucial for the cross-modal retrieval performance. Unlike existing image-text retrieval approaches that embed image-text pairs as single feature vectors in a common representational space, we propose to incorporate generative processes into the cross-modal feature embedding, through which we are able to learn not only the global abstract features but also the local grounded features. Extensive experiments show that our framework can well match images and sentences with complex content, and achieve the state-of-the-art cross-modal retrieval results on MSCOCO dataset.
Human beings understand natural language description and could able to imagine a corresponding visual for the same. For example, given a description of the interior of a house, we could imagine its structure and arrangements of furniture. Automatic synthesis of real-world images from text descriptions has been explored in the computer vision community. However, there is no such attempt in the area of document images, like floor plans. Floor plan synthesis from sketches, as well as data-driven models, were proposed earlier. Ours is the first attempt to render building floor plan images from tex…
Artificial agents today can answer factual questions. But they fall short on questions that require common sense reasoning. Perhaps this is because most existing common sense databases rely on text to learn and represent knowledge. But much of common sense knowledge is unwritten - partly because it tends not to be interesting enough to talk about, and partly because some common sense is unnatural to articulate in text. While unwritten, it is not unseen. In this paper we leverage semantic common sense knowledge learned from images - i.e. visual common sense - in two textual tasks: fill-in-the-b…
We introduce an inversion based method, denoted as IMAge-Guided model INvErsion (IMAGINE), to generate high-quality and diverse images from only a single training sample. We leverage the knowledge of image semantics from a pre-trained classifier to achieve plausible generations via matching multi-level feature representations in the classifier, associated with adversarial training with an external discriminator. IMAGINE enables the synthesis procedure to simultaneously 1) enforce semantic specificity constraints during the synthesis, 2) produce realistic images without generator training, and …
What if Agents Could Imagine? Reinforcing Open-Vocabulary HOI Comprehension through Generation
Dream-X Team（Dream-X团队）；Stanford University（斯坦福大学）；National University of Singapore（新加坡国立大学）；Independent Researcher（独立研究者）；Case Western Reserve University（凯斯西储大学）；UC Santa Cruz（加州大学圣克鲁兹分校）
Imagine Before Concentration: Diffusion-Guided Registers Enhance Partially Relevant Video Retrieval
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Peng Cheng Laboratory（鹏城实验室）
Imagine a City: CityGenAgent for Procedural 3D City Generation
Lingnan University, Hong Kong SAR, China（岭南大学）；Zhejiang University, Hangzhou, China（浙江大学）；The Chinese University of Hong Kong, Hong Kong SAR, China（香港中文大学）；Autodesk AI Lab, Canada（Autodesk AI实验室）；The University of Hong Kong, Hong Kong SAR, China（香港大学）
Textual-visual matching aims at measuring similarities between sentence descriptions and images. Most existing methods tackle this problem without effectively utilizing identity-level annotations. In this paper, we propose an identity-aware two-stage framework for the textual-visual matching problem. Our stage-1 CNN-LSTM network learns to embed cross-modal features with a novel Cross-Modal Cross-Entropy (CMCE) loss. The stage-1 network is able to efficiently screen easy incorrect matchings and also provide initial training point for the stage-2 training. The stage-2 CNN-LSTM network refines th…
This short technical report demonstrates a simple technique that yields state of the art results in medical image-text matching tasks. We analyze the use of OpenAI's CLIP, a general image-text matching model, and observe that CLIP's limited textual input size has negative impact on downstream performance in the medical domain where encoding longer textual contexts is often required. We thus train and release ClipMD, which is trained with a simple sliding window technique to encode textual captions. ClipMD was tested on two medical image-text datasets and compared with other image-text matching…
Tianjin University（天津大学）；University of Warwick（华威大学）
This paper studies the task of matching image and sentence, where learning appropriate representations across the multi-modal data appears to be the main challenge. Unlike previous approaches that predominantly deploy symmetrical architecture to represent both modalities, we propose Saliency-guided Attention Network (SAN) that asymmetrically employs visual and textual attention modules to learn the fine-grained correlation intertwined between vision and language. The proposed SAN mainly includes three components: saliency detector, Saliency-weighted Visual Attention (SVA) module, and Saliency-…
Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning
Meta Superintelligence Labs（Meta超级智能实验室）；University of California, San Diego（加州大学圣迭戈分校）；Worcester Polytechnic Institute（伍斯特理工学院）；Northwestern University（西北大学）
Text-to-image person retrieval aims to identify the target person based on a given textual description query. The primary challenge is to learn the mapping of visual and textual modalities into a common latent space. Prior works have attempted to address this challenge by leveraging separately pre-trained unimodal models to extract visual and textual features. However, these approaches lack the necessary underlying alignment capabilities required to match multimodal data effectively. Besides, these works use prior information to explore explicit part alignments, which may lead to the distortio…
Text-to-image synthesis aims to generate a photo-realistic and semantic consistent image from a specific text description. The images synthesized by off-the-shelf models usually contain limited components compared with the corresponding image and text description, which decreases the image quality and the textual-visual consistency. To address this issue, we propose a novel Vision-Language Matching strategy for text-to-image synthesis, named VLMGAN*, which introduces a dual vision-language matching mechanism to strengthen the image quality and semantic consistency. The dual vision-language mat…
Beihang University（北京航空航天大学）；Arizona State University（亚利桑那州立大学）
Person search by natural language aims at retrieving a specific person in a large-scale image pool that matches the given textual descriptions. While most of the current methods treat the task as a holistic visual and textual feature matching one, we approach it from an attribute-aligning perspective that allows grounding specific attribute phrases to the corresponding visual regions. We achieve success as well as the performance boosting by a robust feature learning that the referred identity can be accurately bundled by multiple attribute visual cues. To be concrete, our Visual-Textual Attri…
How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning
Mila - Québec AI Institute（蒙特利尔AI研究所）；Université de Montréal（蒙特利尔大学）；McGill University（麦吉尔大学）；ServiceNow AI Research（ServiceNow人工智能研究）；Canada CIFAR AI Chair（加拿大CIFAR人工智能主席）
Imagine Before You Draw: Visual Prompt Engineering for Image Generation
Nanyang Technological University（南洋理工大学）；National University of Singapore（国立新加坡大学）；Zhejiang University（浙江大学）；The Chinese University of Hong Kong（香港中文大学）
Text-to-image models offer unprecedented freedom to guide creation through natural language. Yet, it is unclear how such freedom can be exercised to generate images of specific unique concepts, modify their appearance, or compose them in new roles and novel scenes. In other words, we ask: how can we use language-guided models to turn our cat into a painting, or imagine a new product based on our favorite toy? Here we present a simple approach that allows such creative freedom. Using only 3-5 images of a user-provided concept, like an object or a style, we learn to represent it through new "wor…
Nanjing University of information science and Technology（南京信息工程大学）；Xinjiang University（新疆大学）；Nanjing Institute of Technology（南京工程学院）；KingSaud University（沙特国王大学）
Text-based person re-identification(Re-id) is an important task in video surveillance, which consists of retrieving the corresponding person's image given a textual description from a large gallery of images. It is difficult to directly match visual contents with the textual descriptions due to the modality heterogeneity. On the one hand, the textual embeddings are not discriminative enough, which originates from the high abstraction of the textual descriptions. One the other hand,Global average pooling (GAP) is commonly utilized to extract more general or smoothed features implicitly but igno…
We propose Dual Attention Networks (DANs) which jointly leverage visual and textual attention mechanisms to capture fine-grained interplay between vision and language. DANs attend to specific regions in images and words in text through multiple steps and gather essential information from both modalities. Based on this framework, we introduce two types of DANs for multimodal reasoning and matching, respectively. The reasoning model allows visual and textual attentions to steer each other during collaborative inference, which is useful for tasks such as Visual Question Answering (VQA). In additi…
Tianjin University（天津大学）；University of South Carolina（南卡罗来纳大学）
Referring expression comprehension (REC) aims to localize a text-related region in a given image by a referring expression in natural language. Existing methods focus on how to build convincing visual and language representations independently, which may significantly isolate visual and language information. In this paper, we argue that for REC the referring expression and the target region are semantically correlated and subject, location and relationship consistency exist between vision and language.On top of this, we propose a novel approach called MutAtt to construct mutual guidance betwee…
ISTI - CNR（意大利国家研究委员会信息科学与技术研究所）；University of Geneva（日内瓦大学）
Despite the evolution of deep-learning-based visual-textual processing systems, precise multi-modal matching remains a challenging task. In this work, we tackle the task of cross-modal retrieval through image-sentence matching based on word-region alignments, using supervision only at the global image-sentence level. Specifically, we present a novel approach called Transformer Encoder Reasoning and Alignment Network (TERAN). TERAN enforces a fine-grained match between the underlying components of images and sentences, i.e., image regions and words, respectively, in order to preserve the inform…
ShapeSpeak: Body Shape-Aware Textual Alignment for Visible-Infrared Person Re-Identification
Nanjing University of Science and Technology（南京理工大学）；Chongqing University of Posts and Telecommunications（重庆邮电大学）；The Hong Kong Polytechnic University（香港理工大学）
We study the impact of using rich and diverse textual descriptions of classes for zero-shot learning (ZSL) on ImageNet. We create a new dataset ImageNet-Wiki that matches each ImageNet class to its corresponding Wikipedia article. We show that merely employing these Wikipedia articles as class descriptions yields much higher ZSL performance than prior works. Even a simple model using this type of auxiliary data outperforms state-of-the-art models that rely on standard features of word embedding encodings of class names. These results highlight the usefulness and importance of textual descripti…
Institute of Information Science and Technologies, National Research Council（国家研究委员会信息科学与技术研究所）；University of Geneva（日内瓦大学）
Cross-modal retrieval is an important functionality in modern search engines, as it increases the user experience by allowing queries and retrieved objects to pertain to different modalities. In this paper, we focus on the image-sentence retrieval task, where the objective is to efficiently find relevant images for a given sentence (image-retrieval) or the relevant sentences for a given image (sentence-retrieval). Computer vision literature reports the best results on the image-sentence matching task using deep neural networks equipped with attention and self-attention mechanisms. They evaluat…
Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIP
Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）；Division of Social Science and Department of Computer Science & Engineering, Hong Kong University of Science & Technology（香港科学与技术大学社会科学学院及计算机科学与工程系）；SenseTime Group Ltd（时光集团有限公司）
Tencent YouTu Lab（腾讯优图实验室）；AI Institute, Shanghai Jiao Tong University（上海交通大学人工智能研究院）
Text-based Person Search (TPS), is targeted on retrieving pedestrians to match text descriptions instead of query images. Recent Vision-Language Pre-training (VLP) models can bring transferable knowledge to downstream TPS tasks, resulting in more efficient performance gains. However, existing TPS methods improved by VLP only utilize pre-trained visual encoders, neglecting the corresponding textual representation and breaking the significant modality alignment learned from large-scale pre-training. In this paper, we explore the full utilization of textual potential from VLP in TPS tasks. We bui…
National Research Council（国家研究委员会）；Institute of Information Science and Technologies（信息科学与技术研究所）
Image-text matching is an interesting and fascinating task in modern AI research. Despite the evolution of deep-learning-based image and text processing systems, multi-modal matching remains a challenging problem. In this work, we consider the problem of accurate image-text matching for the task of multi-modal large-scale information retrieval. State-of-the-art results in image-text matching are achieved by inter-playing image and text features from the two different processing pipelines, usually using mutual attention mechanisms. However, this invalidates any chance to extract separate visual…
Arizona State University（亚利桑那州立大学）；University of California, Irvine（加州大学欧文分校）
Grounding textual phrases in visual content is a meaningful yet challenging problem with various potential applications such as image-text inference or text-driven multimedia interaction. Most of the current existing methods adopt the supervised learning mechanism which requires ground-truth at pixel level during training. However, fine-grained level ground-truth annotation is quite time-consuming and severely narrows the scope for more general applications. In this extended abstract, we explore methods to localize flexibly image regions from the top-down signal (in a form of one-hot label or …
Classifying a visual concept merely from its associated online textual source, such as a Wikipedia article, is an attractive research topic in zero-shot learning because it alleviates the burden of manually collecting semantic attributes. Several recent works have pursued this approach by exploring various ways of connecting the visual and text domains. This paper revisits this idea by stepping further to consider one important factor: the textual representation is usually too noisy for the zero-shot learning application. This consideration motivates us to design a simple-but-effective zero-sh…
Zhejiang University（浙江大学）；Renmin University of China（中国人民大学）；University of Amsterdam（阿姆斯特丹大学）
This paper strives to find the sentence best describing the content of an image or video. Different from existing works, which rely on a joint subspace for image / video to sentence matching, we propose to do so in a visual space only. We contribute Word2VisualVec, a deep neural network architecture that learns to predict a deep visual encoding of textual input based on sentence vectorization and a multi-layer perceptron. We thoroughly analyze its architectural design, by varying the sentence vectorization strategy, network depth and the deep feature to predict for image to sentence matching. …
Text-based person retrieval aims to find the query person based on a textual description. The key is to learn a common latent space mapping between visual-textual modalities. To achieve this goal, existing works employ segmentation to obtain explicitly cross-modal alignments or utilize attention to explore salient alignments. These methods have two shortcomings: 1) Labeling cross-modal alignments are time-consuming. 2) Attention methods can explore salient cross-modal alignments but may ignore some subtle and valuable pairs. To relieve these issues, we introduce an Implicit Visual-Textual (IVT…
The University of Sydney（悉尼大学）；Baidu Inc.（百度公司）；University of Chinese Academy of Sciences（中国科学院大学）；Shanghai AI Laboratory（上海人工智能实验室）
Most existing text-video retrieval methods focus on cross-modal matching between the visual content of videos and textual query sentences. However, in real-world scenarios, online videos are often accompanied by relevant text information such as titles, tags, and even subtitles, which can be utilized to match textual queries. This insight has motivated us to propose a novel approach to text-video retrieval, where we directly generate associated captions from videos using zero-shot video captioning with knowledge from web-scale pre-trained models (e.g., CLIP and GPT-2). Given the generated capt…
We extend Textual Inversion to learn pseudo-words that represent a concept at different resolutions. This allows us to generate images that use the concept with different levels of detail and also to manipulate different resolutions using language. Once learned, the user can generate images at different levels of agreement to the original concept; "A photo of $S^*(0)$" produces the exact object while the prompt "A photo of $S^*(0.8)$" only matches the rough outlines and colors. Our framework allows us to generate images that use different resolutions of an image (e.g. details, textures, styles…
The de-facto approach to many vision tasks is to start from pretrained visual representations, typically learned via supervised training on ImageNet. Recent methods have explored unsupervised pretraining to scale to vast quantities of unlabeled images. In contrast, we aim to learn high-quality visual representations from fewer images. To this end, we revisit supervised pretraining, and seek data-efficient alternatives to classification-based pretraining. We propose VirTex -- a pretraining approach using semantically dense captions to learn visual representations. We train convolutional network…
We introduce a multimodal visual-textual search refinement method for fashion garments. Existing search engines do not enable intuitive, interactive, refinement of retrieved results based on the properties of a particular product. We propose a method to retrieve similar items, based on a query item image and textual refinement properties. We believe this method can be leveraged to solve many real-life customer scenarios, in which a similar item in a different color, pattern, length or style is desired. We employ a joint embedding training scheme in which product images and their catalog textua…
We introduce CLEVR-Math, a multi-modal math word problems dataset consisting of simple math word problems involving addition/subtraction, represented partly by a textual description and partly by an image illustrating the scenario. The text describes actions performed on the scene that is depicted in the image. Since the question posed may not be about the scene in the image, but about the state of the scene before or after the actions are applied, the solver envision or imagine the state changes due to these actions. Solving these word problems requires a combination of language, visual and m…
