People from different parts of the globe describe objects and concepts in distinct manners. Visual appearance can thus vary across different geographic locations, which makes location a relevant contextual information when analysing visual data. In this work, we address the task of image retrieval related to a given tag conditioned on a certain location on Earth. We present LocSens, a model that learns to rank triplets of images, tags and coordinates by plausibility, and two training strategies to balance the location influence in the final ranking. LocSens learns to fuse textual and location information of multimodal queries to retrieve related images at different levels of location granularity, and successfully utilizes location information to improve image tagging.
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；University of Warwick（华威大学）
The social media explosion has populated the Internet with a wealth of images. There are two existing paradigms for image retrieval: 1) content-based image retrieval (CBIR), which has traditionally used visual features for similarity search (e.g., SIFT features), and 2) tag-based image retrieval (TBIR), which has relied on user tagging (e.g., Flickr tags). CBIR now gains semantic expressiveness by advances in deep-learning-based detection of visual labels. TBIR benefits from query-and-click logs to automatically infer more informative labels. However, learning-based tagging still yields noisy …
University of Tennessee, Knoxville（田纳西大学诺克斯维尔分校）；Department of Electrical Engineering and Computer Science（电气工程与计算机科学系）
Learning compact representation is vital and challenging for large scale multimedia data. Cross-view/cross-modal hashing for effective binary representation learning has received significant attention with exponentially growing availability of multimedia content. Most existing cross-view hashing algorithms emphasize the similarities in individual views, which are then connected via cross-view similarities. In this work, we focus on the exploitation of the discriminative information from different views, and propose an end-to-end method to learn semantic-preserving and discriminative binary rep…
Vision-language alignment learning for video-text retrieval arouses a lot of attention in recent years. Most of the existing methods either transfer the knowledge of image-text pretraining model to video-text retrieval task without fully exploring the multi-modal information of videos, or simply fuse multi-modal features in a brute force manner without explicit guidance. In this paper, we integrate multi-modal information in an explicit manner by tagging, and use the tags as the anchors for better video-text alignment. Various pretrained experts are utilized for extracting the information of m…
Image Retrieval with Intra-Sweep Representation Learning for Neck Ultrasound Scanning Guidance
The University of British Columbia（不列颠哥伦比亚大学）；Intuitive Surgical Inc.（直觉外科公司）；School of Biomedical Engineering, The University of British Columbia（不列颠哥伦比亚大学生物医学工程学院）
From Street to Orbit: Training-Free Cross-View Retrieval via Location Semantics and LLM Guidance
Ulsan National Institute of Science and Technology (UNIST)（蔚山科学技术院）；Electronics and Telecommunications Research Institute (ETRI)（电子通信研究院）；Kyungpook National University（庆北大学）
This paper contributes to cross-lingual image annotation and retrieval in terms of data and baseline methods. We propose COCO-CN, a novel dataset enriching MS-COCO with manually written Chinese sentences and tags. For more effective annotation acquisition, we develop a recommendation-assisted collective annotation system, automatically providing an annotator with several tags and sentences deemed to be relevant with respect to the pictorial content. Having 20,342 images annotated with 27,218 Chinese sentences and 70,993 tags, COCO-CN is currently the largest Chinese-English dataset that provid…
This paper addresses the problem of vehicle-mounted camera localization by matching a ground-level image with an overhead-view satellite map. Existing methods often treat this problem as cross-view image retrieval, and use learned deep features to match the ground-level query image to a partition (eg, a small patch) of the satellite map. By these methods, the localization accuracy is limited by the partitioning density of the satellite map (often in the order of tens meters). Departing from the conventional wisdom of image retrieval, this paper presents a novel solution that can achieve highly…
Lahore University of Management Sciences（拉合尔管理科学大学）
Cross-modal retrieval aims to measure the content similarity between different types of data. The idea has been previously applied to visual, text, and speech data. In this paper, we present a novel cross-modal retrieval method specifically for multi-view images, called Cross-view Image Retrieval CVIR. Our approach aims to find a feature space as well as an embedding space in which samples from street-view images are compared directly to satellite-view images (and vice-versa). For this comparison, a novel deep metric learning based solution "DeepCVIR" has been proposed. Previous cross-view ima…
Queensland University of Technology（昆士兰科技大学）；University of Queensland（昆士兰大学）
Learning embeddings that are invariant to the pose of the object is crucial in visual image retrieval and re-identification. The existing approaches for person, vehicle, or animal re-identification tasks suffer from high intra-class variance due to deformable shapes and different camera viewpoints. To overcome this limitation, we propose to align the image embedding with a predefined order of the keypoints. The proposed keypoint aligned embeddings model (KAE-Net) learns part-level features via multi-task learning which is guided by keypoint locations. More specifically, KAE-Net extracts channe…
Xi'an Jiaotong University（西安交通大学）；University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）
Aggregating deep convolutional features into a global image vector has attracted sustained attention in image retrieval. In this paper, we propose an efficient unsupervised aggregation method that uses an adaptive Gaussian filter and an elementvalue sensitive vector to co-weight deep features. Specifically, the Gaussian filter assigns large weights to features of region-of-interests (RoI) by adaptively determining the RoI's center, while the element-value sensitive channel vector suppresses burstiness phenomenon by assigning small weights to feature maps with large sum values of all locations.…
We present a similar image retrieval (SIR) platform that is used to quickly discover visually similar products in a catalog of millions. Given the size, diversity, and dynamism of our catalog, product search poses many challenges. It can be addressed by building supervised models to tagging product images with labels representing themes and later retrieving them by labels. This approach suffices for common and perennial themes like "white shirt" or "lifestyle image of TV". It does not work for new themes such as "e-cigarettes", hard-to-define ones such as "image with a promotional badge", or t…
Institute of Computer Graphics and Vision, Graz University of Technology, Austria（奥地利格拉茨工业大学计算机图形与视觉研究所）
We present Location Field Descriptors, a novel approach for single image 3D model retrieval in the wild. In contrast to previous methods that directly map 3D models and RGB images to an embedding space, we establish a common low-level representation in the form of location fields from which we compute pose invariant 3D shape descriptors. Location fields encode correspondences between 2D pixels and 3D surface coordinates and, thus, explicitly capture 3D shape and 3D pose information without appearance variations which are irrelevant for the task. This early fusion of 3D models and RGB images re…
The Graduate Center and City College, CUNY（纽约市立大学研究生中心与城市学院）
Indoor localization has many applications, such as commercial Location Based Services (LBS), robotic navigation, and assistive navigation for the blind. This paper formulates the indoor localization problem into a multimedia retrieving problem by modeling visual landmarks with a panoramic image feature, and calculating a user's location via GPU- accelerated parallel retrieving algorithm. To solve the scene similarity problem, we apply a multi-images based retrieval strategy and a 2D aggregation method to estimate the final retrieval location. Experiments on a campus building real data demonstr…
Often, videos are composed of multiple concepts or even genres. For instance, news videos may contain sports, action, nature, etc. Therefore, encoding the distribution of such concepts/genres in a compact and effective representation is a challenging task. In this sense, we propose the Bag of Genres representation, which is based on a visual dictionary defined by a genre classifier. Each visual word corresponds to a region in the classification space. The Bag of Genres video vector contains a summary of the activations of each genre in the video content. We evaluate the proposed method for vid…
To enhance research on multimodal knowledge base and multimodal information processing, we propose a new task called multimodal entity tagging (MET) with a multimodal knowledge base (MKB). We also develop a dataset for the problem using an existing MKB. In an MKB, there are entities and their associated texts and images. In MET, given a text-image pair, one uses the information in the MKB to automatically identify the related entity in the text-image pair. We solve the task by using the information retrieval paradigm and implement several baselines using state-of-the-art methods in NLP and CV.…
University of Leeds（利兹大学）；University Gustave Eiffel（古斯塔夫·埃菲尔大学）；IGN-ENSG（法国国家地理学院-国立地理科学学校）；Tongji University（同济大学）；Shandong University（山东大学）；Qingdao University of Science & Technology（青岛科技大学）
Location retrieval based on visual information is to retrieve the location of an agent (e.g. human, robot) or the area they see by comparing the observations with a certain form of representation of the environment. Existing methods generally require precise measurement and storage of the observed environment features, which may not always be robust due to the change of season, viewpoint, occlusion, etc. They are also challenging to scale up and may not be applicable for humans due to the lack of measuring/imaging devices. Considering that humans often use less precise but easily produced qual…
Sea-NExT Joint Lab（Sea-NExT联合实验室）；National University of Singapore（新加坡国立大学）；Hefei University of Technology（合肥工业大学）
We tackle the task of video moment retrieval (VMR), which aims to localize a specific moment in a video according to a textual query. Existing methods primarily model the matching relationship between query and moment by complex cross-modal interactions. Despite their effectiveness, current models mostly exploit dataset biases while ignoring the video content, thus leading to poor generalizability. We argue that the issue is caused by the hidden confounder in VMR, {i.e., temporal location of moments}, that spuriously correlates the model input and prediction. How to design robust matching mode…
University of Rochester（罗切斯特大学）；Adobe Research（Adobe研究院）
Font selection is one of the most important steps in a design workflow. Traditional methods rely on ordered lists which require significant domain knowledge and are often difficult to use even for trained professionals. In this paper, we address the problem of large-scale tag-based font retrieval which aims to bring semantics to the font selection process and enable people without expert knowledge to use fonts effectively. We collect a large-scale font tagging dataset of high-quality professional fonts. The dataset contains nearly 20,000 fonts, 2,000 tags, and hundreds of thousands of font-tag…
Information Technologies Institute, CERTH（希腊研究与技术中心信息技术研究所）
In this paper, we address the problem of global-scale image geolocation, proposing a mixed classification-retrieval scheme. Unlike other methods that strictly tackle the problem as a classification or retrieval task, we combine the two practices in a unified solution leveraging the advantages of each approach with two different modules. The first leverages the EfficientNet architecture to assign images to a specific geographic cell in a robust way. The second introduces a new residual architecture that is trained with contrastive learning to map input images to an embedding space that minimize…
Cornell University（康奈尔大学）；Facebook AI Research（Facebook人工智能研究院）
The variety, abundance, and structured nature of hashtags make them an interesting data source for training vision models. For instance, hashtags have the potential to significantly reduce the problem of manual supervision and annotation when learning vision models for a large number of concepts. However, a key challenge when learning from hashtags is that they are inherently subjective because they are provided by users as a form of self-expression. As a consequence, hashtags may have synonyms (different hashtags referring to the same visual content) and may be ambiguous (the same hashtag ref…
University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）
Cross-view image geo-localization aims to determine the locations of street-view query images by matching with GPS-tagged reference images from aerial view. Recent works have achieved surprisingly high retrieval accuracy on city-scale datasets. However, these results rely on the assumption that there exists a reference image exactly centered at the location of any query image, which is not applicable for practical scenarios. In this paper, we redefine this problem with a more realistic assumption that the query image can be arbitrary in the area of interest and the reference images are capture…
