At Pinterest, we utilize image embeddings throughout our search and recommendation systems to help our users navigate through visual content by powering experiences like browsing of related content and searching for exact products for shopping. In this work we describe a multi-task deep metric learning system to learn a single unified image embedding which can be used to power our multiple visual search products. The solution we present not only allows us to train for multiple application objectives in a single deep neural network architecture, but takes advantage of correlated information in the combination of all training data from each application to generate a unified embedding that outperforms all specialized embeddings previously deployed for each product. We discuss the challenges of handling images from different domains such as camera photos, high quality web images, and clean product catalog images. We also detail how to jointly train for multiple product objectives and how to leverage both engagement data and human labeled data. In addition, our trained embeddings can also be binarized for efficient storage and retrieval without compromising precision and recall. Through comprehensive evaluations on offline metrics, user studies, and online A/B experiments, we demonstrate that our proposed unified embedding improves both relevance and engagement of our visual search products for both browsing and searching purposes when compared to existing specialized embeddings. Finally, the deployment of the unified embedding at Pinterest has drastically reduced the operation and engineering cost of maintaining multiple embeddings while improving quality.
Pinterest；University of California, Berkeley（加州大学伯克利分校）
Over the past three years Pinterest has experimented with several visual search and recommendation services, including Related Pins (2014), Similar Looks (2015), Flashlight (2016) and Lens (2017). This paper presents an overview of our visual discovery engine powering these services, and shares the rationales behind our technical and product decisions such as the use of object detection and interactive user interfaces. We conclude that this visual discovery engine significantly improves engagement in both search and recommendation tasks.
Pinterest；University of California, Berkeley（加州大学伯克利分校）
We demonstrate that, with the availability of distributed computation platforms such as Amazon Web Services and open-source tools, it is possible for a small engineering team to build, launch and maintain a cost-effective, large-scale visual search system with widely available tools. We also demonstrate, through a comprehensive set of live experiments at Pinterest, that content recommendation powered by visual search improve user engagement. By sharing our implementation details and the experiences learned from launching a commercial visual search engines from scratch, we hope visual search ar…
As online content becomes ever more visual, the demand for searching by visual queries grows correspondingly stronger. Shop The Look is an online shopping discovery service at Pinterest, leveraging visual search to enable users to find and buy products within an image. In this work, we provide a holistic view of how we built Shop The Look, a shopping oriented visual search system, along with lessons learned from addressing shopping needs. We discuss topics including core technology across object detection and visual embeddings, serving infrastructure for realtime inference, and data labeling m…
Cornell Tech（康奈尔科技校区）；University of California, Los Angeles（加州大学洛杉矶分校）
User preference profiling is an important task in modern online social networks (OSN). With the proliferation of image-centric social platforms, such as Pinterest, visual contents have become one of the most informative data streams for understanding user preferences. Traditional approaches usually treat visual content analysis as a general classification problem where one or more labels are assigned to each image. Although such an approach simplifies the process of image analysis, it misses the rich context and visual cues that play an important role in people's perception of images. In this …
Nanyang Technological University（南洋理工大学）；Institute for Infocomm Research, Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局资讯通信研究院）
In this paper, we propose a method for ranking fashion images to find the ones which might be liked by more people. We collect two new datasets from image sharing websites (Pinterest and Polyvore). We represent fashion images based on attributes: semantic attributes and data-driven attributes. To learn semantic attributes from limited training data, we use an algorithm on multi-task convolutional neural networks to share visual knowledge among different semantic attribute categories. To discover data-driven attributes unsupervisedly, we propose an algorithm to simultaneously discover visual cl…
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Pinterest Inc.（Pinterest公司）；Johns Hopkins University（约翰斯·霍普金斯大学）
In this paper, we focus on training and evaluating effective word embeddings with both text and visual information. More specifically, we introduce a large-scale dataset with 300 million sentences describing over 40 million images crawled and downloaded from publicly available Pins (i.e. an image with sentence descriptions uploaded by users) on Pinterest. This dataset is more than 200 times larger than MS COCO, the standard large-scale image dataset with sentence descriptions. In addition, we construct an evaluation dataset to directly assess the effectiveness of word embeddings in terms of fi…
Zero-shot learning (ZSL) highly depends on a good semantic embedding to connect the seen and unseen classes. Recently, distributed word embeddings (DWE) pre-trained from large text corpus have become a popular choice to draw such a connection. Compared with human defined attributes, DWEs are more scalable and easier to obtain. However, they are designed to reflect semantic similarity rather than visual similarity and thus using them in ZSL often leads to inferior performance. To overcome this visual-semantic discrepancy, this work proposes an objective function to re-align the distributed word…
VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning
Beijing University of Posts and Telecommunications（北京邮电大学）；University of Chinese Academy of Sciences（中国科学院大学）；Aerospace Information Research Institute, CAS（中国科学院空天信息创新研究院）；ETH Zurich（苏黎世联邦理工学院）；City University of Hong Kong（香港城市大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；University of Tübingen（图宾根大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
Tsinghua University（清华大学）；Virginia Tech（弗吉尼亚理工大学）；University of California, Merced（加利福尼亚大学默塞德分校）
Numerous embedding models have been recently explored to incorporate semantic knowledge into visual recognition. Existing methods typically focus on minimizing the distance between the corresponding images and texts in the embedding space but do not explicitly optimize the underlying structure. Our key observation is that modeling the pairwise image-image relationship improves the discrimination ability of the embedding model. In this paper, we propose the structured discriminative and difference constraints to learn visual-semantic embeddings. First, we exploit the discriminative constraints …
University of California, Los Angeles（加州大学洛杉矶分校）；Adobe Research（奥多比研究院）
Visual-semantic embedding models have been recently proposed and shown to be effective for image classification and zero-shot learning, by mapping images into a continuous semantic label space. Although several approaches have been proposed for single-label embedding tasks, handling images with multiple labels (which is a more general setting) still remains an open problem, mainly due to the complex underlying corresponding relationship between image and its labels. In this work, we present Multi-Instance visual-semantic Embedding model (MIE) for embedding images associated with either single …
We propose a novel Generalized Zero-Shot learning (GZSL) method that is agnostic to both unseen images and unseen semantic vectors during training. Prior works in this context propose to map high-dimensional visual features to the semantic domain, we believe contributes to the semantic gap. To bridge the gap, we propose a novel low-dimensional embedding of visual instances that is "visually semantic." Analogous to semantic data that quantifies the existence of an attribute in the presented instance, components of our visual embedding quantifies existence of a prototypical part-type in the pres…
Visual Semantic Embedding (VSE) models, which map images into a rich semantic embedding space, have been a milestone in object recognition and zero-shot learning. Current approaches to VSE heavily rely on static word em-bedding techniques. In this work, we propose a Visual Se-mantic Embedding Probe (VSEP) designed to probe the semantic information of contextualized word embeddings in visual semantic understanding tasks. We show that the knowledge encoded in transformer language models can be exploited for tasks requiring visual semantic understanding.The VSEP with contextual representations ca…
University of Southern California（南加州大学）；Google AI（谷歌人工智能）
We propose a learning model for the task of visual storytelling. The main idea is to predict anchor word embeddings from the images and use the embeddings and the image features jointly to generate narrative sentences. We use the embeddings of randomly sampled nouns from the groundtruth stories as the target anchor word embeddings to learn the predictor. To narrate a sequence of images, we use the predicted anchor word embeddings and the image features as the joint input to a seq2seq model. As opposed to state-of-the-art methods, the proposed model is simple in design, easy to optimize, and at…
On Aligning Hierarchical Standardized Embedding for Audio-visual Generalized Zero-shot Learning
Southeast University（东南大学）；The University of Hong Kong（香港大学）；Beijing Institute of Technology（北京理工大学）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education（新一代人工智能技术及其跨学科应用重点实验室（东南大学），教育部）；School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）
Zero-shot learning methods rely on fixed visual and semantic embeddings, extracted from independent vision and language models, both pre-trained for other large-scale tasks. This is a weakness of current zero-shot learning frameworks as such disjoint embeddings fail to adequately associate visual and textual information to their shared semantic content. Therefore, we propose to learn semantically grounded and enriched visual information by computing a joint image and text model with a two-stream network on a proxy task. To improve this alignment between image and textual representations, provi…
In this paper we present a deep learning architecture for extracting word embeddings for visual speech recognition. The embeddings summarize the information of the mouth region that is relevant to the problem of word recognition, while suppressing other types of variability such as speaker, pose and illumination. The system is comprised of a spatiotemporal convolutional layer, a Residual Network and bidirectional LSTMs and is trained on the Lipreading in-the-wild database. We first show that the proposed architecture goes beyond state-of-the-art on closed-set word identification, by attaining …
Layer-Aware Position Embeddings for Visual Token Pruning in Multimodal Large Language Models
Tongji University（同济大学）；University of California, Santa Cruz（加州大学圣克鲁兹分校）；East China Normal University（华东师范大学）；Shanghai Eye Disease Prevention and Treatment Center（上海市眼病防治中心）
University of Notre Dame（圣母大学）；Max-Planck-Institute for Informatics（马克斯·普朗克信息学研究所）
Understanding the structure of complex activities in untrimmed videos is a challenging task in the area of action recognition. One problem here is that this task usually requires a large amount of hand-annotated minute- or even hour-long video data, but annotating such data is very time consuming and can not easily be automated or scaled. To address this problem, this paper proposes an approach for the unsupervised learning of actions in untrimmed video sequences based on a joint visual-temporal embedding space. To this end, we combine a visual embedding based on a predictive U-Net architectur…
Zero shot learning (ZSL) has seen a surge in interest over the decade for its tight links with the mechanism making young children recognize novel objects. Although different paradigms of visual semantic embedding models are designed to align visual features and distributed word representations, it is unclear to what extent current ZSL models encode semantic information from distributed word representations. In this work, we introduce the split of tiered-ImageNet to the ZSL task, in order to avoid the structural flaws in the standard ImageNet benchmark. We build a unified framework for ZSL wit…
MINDsLab Inc.（MINDsLab 公司）；Agency for Defense Development（国防发展局）
Fully supervised semantic segmentation technologies bring a paradigm shift in scene understanding. However, the burden of expensive labeling cost remains as a challenge. To solve the cost problem, recent studies proposed language model based zero-shot semantic segmentation (L-ZSSS) approaches. In this paper, we address L-ZSSS has a limitation in generalization which is a virtue of zero-shot learning. Tackling the limitation, we propose a language-model-free zero-shot semantic segmentation framework, Spatial and Multi-scale aware Visual Class Embedding Network (SM-VCENet). Furthermore, leveragi…
Asymmetric Visual Semantic Embedding Framework for Efficient Vision-Language Alignment
College of Computer Science, Sichuan University（四川大学计算机学院）；State Key Laboratory of General Artificial Intelligence, Peking University（北京大学通用人工智能国家重点实验室）
We present our winning submission to the First International Workshop on Bodily Expressed Emotion Understanding (BEEU) challenge. Based on recent literature on the effect of context/environment on emotion, as well as visual representations with semantic meaning using word embeddings, we extend the framework of Temporal Segment Network to accommodate these. Our method is verified on the validation set of the Body Language Dataset (BoLD) and achieves 0.26235 Emotion Recognition Score on the test set, surpassing the previous best result of 0.2530.
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…
Detecting visual relationships, i.e. <Subject, Predicate, Object> triplets, is a challenging Scene Understanding task approached in the past via linguistic priors or spatial information in a single feature branch. We introduce a new deeply supervised two-branch architecture, the Multimodal Attentional Translation Embeddings, where the visual features of each branch are driven by a multimodal attentional mechanism that exploits spatio-linguistic similarities in a low-dimensional space. We present a variety of experiments comparing against all related approaches in the literature, as well as by …
Columbia University（哥伦比亚大学）；National University of Singapore（新加坡国立大学）
Visual relations, such as "person ride bike" and "bike next to car", offer a comprehensive scene understanding of an image, and have already shown their great utility in connecting computer vision and natural language. However, due to the challenging combinatorial complexity of modeling subject-predicate-object relation triplets, very little work has been done to localize and predict visual relations. Inspired by the recent advances in relational representation learning of knowledge bases and convolutional object detection networks, we propose a Visual Translation Embedding network (VTransE) f…
We propose a novel probabilistic model for visual question answering (Visual QA). The key idea is to infer two sets of embeddings: one for the image and the question jointly and the other for the answers. The learning objective is to learn the best parameterization of those embeddings such that the correct answer has higher likelihood among all possible answers. In contrast to several existing approaches of treating Visual QA as multi-way classification, the proposed approach takes the semantic relationships (as characterized by the embeddings) among answers into consideration, instead of view…
Due to the lack of large-scale datasets, the prevailing approach in visual sentiment analysis is to leverage models trained for object classification in large datasets like ImageNet. However, objects are sentiment neutral which hinders the expected gain of transfer learning for such tasks. In this work, we propose to overcome this problem by learning a novel sentiment-aligned image embedding that is better suited for subsequent visual sentiment analysis. Our embedding leverages the intricate relation between emojis and images in large-scale and readily available data from social media. Emojis …
Recent advances in Siamese network-based visual tracking methods have enabled high performance on numerous tracking benchmarks. However, extensive scale variations of the target object and distractor objects with similar categories have consistently posed challenges in visual tracking. To address these persisting issues, we propose novel TridentAlign and context embedding modules for Siamese network-based visual tracking methods. The TridentAlign module facilitates adaptability to extensive scale variations and large deformations of the target, where it pools the feature representation of the …
Zero-shot learning for visual recognition, e.g., object and action recognition, has recently attracted a lot of attention. However, it still remains challenging in bridging the semantic gap between visual features and their underlying semantics and transferring knowledge to semantic categories unseen during learning. Unlike most of the existing zero-shot visual recognition methods, we propose a stagewise bidirectional latent embedding framework to two subsequent learning stages for zero-shot visual recognition. In the bottom-up stage, a latent embedding space is first created by exploring the …
Transformer models have recently achieved impressive performance on NLP tasks, owing to new algorithms for self-supervised pre-training on very large text corpora. In contrast, recent literature suggests that simple average word models outperform more complicated language models, e.g., RNNs and Transformers, on cross-modal image/text search tasks on standard benchmarks, like MS COCO. In this paper, we show that dataset scale and training strategy are critical and demonstrate that transformer-based cross-modal embeddings outperform word average and RNN-based embeddings by a large margin, when t…
In this paper, a level-wise mixture model (LMM) is developed by embedding visual hierarchy with deep networks to support large-scale visual recognition (i.e., recognizing thousands or even tens of thousands of object classes), and a Bayesian approach is used to adapt a pre-trained visual hierarchy automatically to the improvements of deep features (that are used for image and object class representation) when more representative deep networks are learned along the time. Our LMM model can provide an end-to-end approach for jointly learning: (a) the deep networks to extract more discriminative d…
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）
Hateful memes are widespread in social media and convey negative information. The main challenge of hateful memes detection is that the expressive meaning can not be well recognized by a single modality. In order to further integrate modal information, we investigate a candidate solution based on complementary visual and linguistic network in Hateful Memes Challenge 2020. In this way, more comprehensive information of the multi-modality could be explored in detail. Both contextual-level and sensitive object-level information are considered in visual and linguistic embedding to formulate the co…
Peking University（北京大学）；University of Artois（阿尔图瓦大学）；University of Essex（埃塞克斯大学）；Cardiff University（卡迪夫大学）
Few-shot learning (FSL) is the task of learning to recognize previously unseen categories of images from a small number of training examples. This is a challenging task, as the available examples may not be enough to unambiguously determine which visual features are most characteristic of the considered categories. To alleviate this issue, we propose a method that additionally takes into account the names of the image classes. While the use of class names has already been explored in previous work, our approach differs in two key aspects. First, while previous work has aimed to directly predic…
In this paper, we explore Latent Dirichlet Allocation (LDA) and Polylingual Latent Dirichlet Allocation (PolyLDA), as a means to discover trending styles in Overstock from deep visual semantic features transferred from a pretrained convolutional neural network and text-based item attributes. To utilize deep visual semantic features in conjunction with LDA, we develop a method for creating a bag of words representation of unrolled image vectors. By viewing the channels within the convolutional layers of a Resnet-50 as being representative of a word, we can index these activations to create visu…
The task of fine-grained visual classification (FGVC) deals with classification problems that display a small inter-class variance such as distinguishing between different bird species or car models. State-of-the-art approaches typically tackle this problem by integrating an elaborate attention mechanism or (part-) localization method into a standard convolutional neural network (CNN). Also in this work the aim is to enhance the performance of a backbone CNN such as ResNet by including three efficient and lightweight components specifically designed for FGVC. This is achieved by using global k…
The dimensionality reduction has been widely introduced to use the high-dimensional data for regression, classification, feature analysis, and visualization. As the one technique of dimensionality reduction, a stochastic neighbor embedding (SNE) was introduced. The SNE leads powerful results to visualize high-dimensional data by considering the similarity between the local Gaussian distributions of high and low-dimensional space. To improve the SNE, a t-distributed stochastic neighbor embedding (t-SNE) was also introduced. To visualize high-dimensional data, the t-SNE leads to more powerful an…
SRI International（SRI国际）；University of California San Diego（加州大学圣迭戈分校）；Rutgers University（罗格斯大学）
We improve zero-shot learning (ZSL) by incorporating common-sense knowledge in DNNs. We propose Common-Sense based Neuro-Symbolic Loss (CSNL) that formulates prior knowledge as novel neuro-symbolic loss functions that regularize visual-semantic embedding. CSNL forces visual features in the VSE to obey common-sense rules relating to hypernyms and attributes. We introduce two key novelties for improved learning: (1) enforcement of rules for a group instead of a single concept to take into account class-wise relationships, and (2) confidence margins inside logical operators that enable implicit c…
Visual-semantic embedding is an interesting research topic because it is useful for various tasks, such as visual question answering (VQA), image-text retrieval, image captioning, and scene graph generation. In this paper, we focus on zero-shot image retrieval using sentences as queries and present a survey of the technological trends in this area. First, we provide a comprehensive overview of the history of the technology, starting with a discussion of the early studies of image-to-text matching and how the technology has evolved over time. In addition, a description of the datasets commonly …
Embedding Generalized Semantic Knowledge into Few-Shot Remote Sensing Segmentation
School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University（西北工业大学人工智能与光学电子学院（iOPEN））；Data Science in Earth Observation, Technical University of Munich（慕尼黑工业大学地球观测数据科学系）
University of Illinois at Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）
We propose to learn word embeddings from visual co-occurrences. Two words co-occur visually if both words apply to the same image or image region. Specifically, we extract four types of visual co-occurrences between object and attribute words from large-scale, textually-annotated visual databases like VisualGenome and ImageNet. We then train a multi-task log-bilinear model that compactly encodes word "meanings" represented by each co-occurrence type into a single visual word-vector. Through unsupervised clustering, supervised partitioning, and a zero-shot-like generalization analysis we show t…
We propose a model to learn visually grounded word embeddings (vis-w2v) to capture visual notions of semantic relatedness. While word embeddings trained using text have been extremely successful, they cannot uncover notions of semantic relatedness implicit in our visual world. For instance, although "eats" and "stares at" seem unrelated in text, they share semantics visually. When people are eating something, they also tend to stare at the food. Grounding diverse relations like "eats" and "stares at" into vision remains challenging, despite recent progress in vision. We note that the visual gr…
Text-visual (or called semantic-visual) embedding is a central problem in vision-language research. It typically involves mapping of an image and a text description to a common feature space through a CNN image encoder and a RNN language encoder. In this paper, we propose a new method for learning text-visual embedding using both image titles and click-through data from an image search engine. We also propose a new triplet loss function by modeling positive awareness of the embedding, and introduce a novel mini-batch-based hard negative sampling approach for better data efficiency in the learn…
Institute for Language, Cognition and Computation（语言、认知与计算研究所）；School of Informatics, University of Edinburgh（爱丁堡大学信息学院）
We introduce a new task, visual sense disambiguation for verbs: given an image and a verb, assign the correct sense of the verb, i.e., the one that describes the action depicted in the image. Just as textual word sense disambiguation is useful for a wide range of NLP tasks, visual sense disambiguation can be useful for multimodal tasks such as image retrieval, image description, and text illustration. We introduce VerSe, a new dataset that augments existing multimodal datasets (COCO and TUHOI) with sense labels. We propose an unsupervised algorithm based on Lesk which performs visual sense dis…
We study the problem of compositional zero-shot learning for object-attribute recognition. Prior works use visual features extracted with a backbone network, pre-trained for object classification and thus do not capture the subtly distinct features associated with attributes. To overcome this challenge, these studies employ supervision from the linguistic space, and use pre-trained word embeddings to better separate and compose attribute-object pairs for recognition. Analogous to linguistic embedding space, which already has unique and agnostic embeddings for object and attribute, we shift the…
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…
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 …
We present an approach called VisCode for embedding information into visualization images. This technology can implicitly embed data information specified by the user into a visualization while ensuring that the encoded visualization image is not distorted. The VisCode framework is based on a deep neural network. We propose to use visualization images and QR codes data as training data and design a robust deep encoder-decoder network. The designed model considers the salient features of visualization images to reduce the explicit visual loss caused by encoding. To further support large-scale e…
Information extraction (IE) from documents is an intensive area of research with a large set of industrial applications. Current state-of-the-art methods focus on scanned documents with approaches combining computer vision, natural language processing and layout representation. We propose to challenge the usage of computer vision in the case where both token style and visual representation are available (i.e native PDF documents). Our experiments on three real-world complex datasets demonstrate that using token style attributes based embedding instead of a raw visual embedding in LayoutLM mode…
