Search

Visual phrase considers multiple visual words and captures extra spatial clues among them. Thus, visual phrase shows better discriminative power than single visual word in image retrieval and matching. Not withstanding their success, existing visual phrases still show obvious shortcomings: (1) limited flexibility, i.e., visual phrases are considered for matching only if they contain the same number of visual words; (2) large quantization error and low repeatability, i.e., quantization errors in visual words are aggregated in visual word combinations and visual phrases, making them harder to be matched than single visual words. To avoid these issues, we propose multi-order visual phrase (MVP) which contains two complementary clues: center visual word quantized from the local descriptor of each image keypoint and the visual and spatial clues of multiple nearby keypoints. Two MVPs are flexibly matched by first matching their center visual words, then estimating a match confidence by checking the spatial and visual consistency of their neighbor keypoints. Therefore, center visual word matching equals to traditional visual word matching, but the neighbor spatial and visual clues checking significantly boosts the discriminative power. MVP does not scarify the repeatability of single visual word and is more robust to quantization error than existing visual phrases. We test our approach in three image retrieval tasks on UKbench, Oxford5K, and 1 million distractor images collected from Flickr. Comparisons with recent retrieval approaches and existing visual phrase features clearly demonstrate the competitive accuracy and significantly better efficiency of MVP. [ABSTRACT FROM AUTHOR]

Diffusion process has advanced object retrieval greatly as it can capture the underlying manifold structure. Recent studies have experimentally demonstrated that tensor product diffusion can better reveal the intrinsic relationship between objects than other variants. However, the principle remains unclear, i.e., what kind of manifold structure is captured. In this paper, we propose a new affinity learning algorithm called Regularized Diffusion Process (RDP). By deeply exploring the properties of RDP, our first yet basic contribution is providing a manifold-based explanation for tensor product diffusion. A novel criterion measuring the smoothness of the manifold is defined, which simultaneously regularizes four vertices in the affinity graph. Inspired by this observation, we further contribute two variants towards two specific goals. While ARDP can learn similarities across heterogeneous domains, HRDP performs affinity learning on tensor product hypergraph, considering the relationships between objects are generally more complex than pairwise. Consequently, RDP, ARDP and HRDP constitute a generic tool for object retrieval in most commonly-used settings, no matter the input relationships between objects are derived from the same domain or not, and in pairwise formulation or not. Comprehensive experiments on 10 retrieval benchmarks, especially on large scale data, validate the effectiveness and generalization of our work. [ABSTRACT FROM AUTHOR]

In the early days, content-based image retrieval (CBIR) was studied with global features. Since 2003, image retrieval based on local descriptors (de facto SIFT) has been extensively studied for over a decade due to the advantage of SIFT in dealing with image transformations. Recently, image representations based on the convolutional neural network (CNN) have attracted increasing interest in the community and demonstrated impressive performance. Given this time of rapid evolution, this article provides a comprehensive survey of instance retrieval over the last decade. Two broad categories, SIFT-based and CNN-based methods, are presented. For the former, according to the codebook size, we organize the literature into using large/medium-sized/small codebooks. For the latter, we discuss three lines of methods, i.e., using pre-trained or fine-tuned CNN models, and hybrid methods. The first two perform a single-pass of an image to the network, while the last category employs a patch-based feature extraction scheme. This survey presents milestones in modern instance retrieval, reviews a broad selection of previous works in different categories, and provides insights on the connection between SIFT and CNN-based methods. After analyzing and comparing retrieval performance of different categories on several datasets, we discuss promising directions towards generic and specialized instance retrieval. [ABSTRACT FROM PUBLISHER]

This paper revisits the vector of locally aggregated descriptors (VLAD), which aggregates the residuals of local descriptors to their cluster centers. Since VLAD usually adopts a small-size codebook, the clusters are coarse and residuals not discriminative. To address this problem, this paper proposes to generate a number of residual codebooks descended from the original clusters. After quantizing local descriptors with these codebooks, we pool the resulting secondary residuals as well as the primary ones to obtain the fine residuals. We show that, with two-step aggregation, the fine-residual VLAD has the same dimension as the original. Experiments on two image search benchmarks confirm the improved discriminative power of our method: we observe consistent superiority to the baseline and competitive performance to the state-of-the-arts. [ABSTRACT FROM AUTHOR]

Exploring the multimedia techniques to assist scientists for their research is an interesting and meaningful topic. In this paper, we focus on the large-scale aurora image retrieval by leveraging the bag-of-visual words (BoVW) framework. To refine the unsuitable representation and improve the retrieval performance, the BoVW model is modified by embedding the polar information. The superiority of the proposed polar embedding method lies in two aspects. On the one hand, the polar meshing scheme is conducted to determine the interest points, which is more suitable for images captured by circular fisheye lens. Especially for the aurora image, the extracted polar scale-invariant feature transform (polar-SIFT) feature can also reflect the geomagnetic longitude and latitude, and thus facilitates the further data analysis. On the other hand, a binary polar deep local binary pattern (polar-DLBP) descriptor is proposed to enhance the discriminative power of visual words. Together with the 64-bit polar-SIFT code obtained via Hamming embedding, the multifeature index is performed to reduce the impact of false positive matches. Extensive experiments are conducted on the large-scale aurora image data set. The experimental result indicates that the proposed method improves the retrieval accuracy significantly with acceptable efficiency and memory cost. In addition, the effectiveness of the polar-SIFT scheme and polar-DLBP integration are separately demonstrated. [ABSTRACT FROM AUTHOR]

Cross-modal retrieval aims to identify relevant data across different modalities. In this work, we are dedicated to cross-modal retrieval between images and text sentences, which is formulated into similarity measurement for each image-text pair. To this end, we propose a Cross-modal Relation Guided Network (CRGN) to embed image and text into a latent feature space. The CRGN model uses GRU to extract text feature and ResNet model to learn the globally guided image feature. Based on the global feature guiding and sentence generation learning, the relation between image regions can be modeled. The final image embedding is generated by a relation embedding module with an attention mechanism. With the image embeddings and text embeddings, we conduct cross-modal retrieval based on the cosine similarity. The learned embedding space well captures the inherent relevance between image and text. We evaluate our approach with extensive experiments on two public benchmark datasets, i.e., MS-COCO and Flickr30K. Experimental results demonstrate that our approach achieves better or comparable performance with the state-of-the-art methods with notable efficiency. [ABSTRACT FROM AUTHOR]

Various kinds of features prove to be effective for content-based image retrieval. However, due to the diversity of image contents, a descriptor may achieve impressive performance on specific images while becoming invalid on others. Although some efforts have been made to combine features as complementary counterparts, proper weighting scheme is still a challenge for fast and accurate retrieval. In this paper, we propose an effective fusion method, termed as Topo-correlation (Topo), where the importance of each feature is measured by cross-view correlations on local affinity graphs. Specifically, the weights of similarities are node-sensitive as well as modality-sensitive, thus boosting the results of good cues while depressing adverse factors for individual images. By estimating the consensus of similarity scores with regard to a query-driven criterion, the weighted graphs are generated efficiently with low computational complexity. Extensive experimental results on four benchmarks demonstrate the superiority of the proposed approach over the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Online image hashing has attracted increasing research attention recently, which receives large-scale data in a streaming manner to update the hash functions on-the-fly. Its key challenge lies in the difficulty of balancing the learning timeliness and model accuracy. To this end, most works follow a supervised setting, i.e., using class labels to boost the hashing performance, which defects in two aspects: first, strong constraints, e.g., orthogonal or similarity preserving, are used, which however are typically relaxed and lead to large accuracy drops. Second, large amounts of training batches are required to learn the up-to-date hash functions, which largely increase the learning complexity. To handle the above challenges, a novel supervised online hashing scheme termed Hadamard Matrix Guided Online Hashing (HMOH) is proposed in this paper. Our key innovation lies in introducing Hadamard matrix, which is an orthogonal binary matrix built via Sylvester method. In particular, to release the need of strong constraints, we regard each column of Hadamard matrix as the target code for each class label, which by nature satisfies several desired properties of hashing codes. To accelerate the online training, LSH is first adopted to align the lengths of target code and to-be-learned binary code. We then treat the learning of hash functions as a set of binary classification problems to fit the assigned target code. Finally, extensive experiments on four widely-used benchmarks demonstrate the superior accuracy and efficiency of HMOH over various state-of-the-art methods. Codes can be available at https://github.com/lmbxmu/mycode. [ABSTRACT FROM AUTHOR]

Traditional Bag-of-Words (BoWs) model is commonly generated with many steps, including local feature extraction, codebook generation and feature quantization, etc. Those steps are relatively independent with each other and are hard to be jointly optimized. Moreover, the dependency on hand-crafted local feature makes BoWs model not effective in conveying high-level semantics. These issues largely hinder the performance of BoWs model in large-scale image applications. To conquer these issues, we propose an End-to-End BoWs (E2BoWs) model based on Deep Convolutional Neural Network (DCNN). Our model takes an image as input, then identifies and separates semantic objects in it, and finally outputs visual words with high semantic discriminative power. Specifically, our model firstly generates Semantic Feature Maps (SFMs) corresponding to different object categories through convolutional layers, then introduces Bag-of-Words Layers (BoWL) to generate visual words from each individual feature map. We also introduce a novel learning algorithm to reinforce the sparsity of the generated E2BoWs model, which further ensures the time and memory efficiency. We evaluate the proposed E2BoWs model on several image search datasets including MNIST, SVHN, CIFAR-10, CIFAR-100, MIRFLICKR-25K and NUS-WIDE. Experimental results show that our method achieves promising accuracy and efficiency compared with recent deep learning based retrieval works. [ABSTRACT FROM AUTHOR]

Image retagging aims to improve the tag quality of social images by completing the missing tags, rectifying the noise-corrupted tags, and assigning new high-quality tags. Recent approaches simultaneously explore visual, user and tag information to improve the performance of image retagging by mining the tag-image-user associations. However, such methods will become computationally infeasible with the rapidly increasing number of images, tags and users. It has been proven that the anchor graph can significantly accelerate large-scale graph-based learning by exploring only a small number of anchor points. Inspired by this, we propose a novel Social anchor-Unit GrAph Regularized Tensor Completion (SUGAR-TC) method to efficiently refine the tags of social images, which is insensitive to the scale of data. First, we construct an anchor-unit graph across multiple domains (e.g., image and user domains) rather than traditional anchor graph in a single domain. Second, a tensor completion based on Social anchor-Unit GrAph Regularization (SUGAR) is implemented to refine the tags of the anchor images. Finally, we efficiently assign tags to non-anchor images by leveraging the relationship between the non-anchor units and the anchor units. Experimental results on a real-world social image database well demonstrate the effectiveness and efficiency of SUGAR-TC, outperforming the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

As a post-processing procedure, the diffusion process has demonstrated its ability of substantially improving the performance of various visual retrieval systems. Whereas, great efforts are also devoted to similarity (or metric) fusion, seeing that only one individual type of similarity cannot fully reveal the intrinsic relationship between objects. This stimulates a great research interest of considering similarity fusion in the framework of the diffusion process (i.e., fusion with diffusion) for robust retrieval. In this paper, we first revisit representative methods about fusion with diffusion and provide new insights which are ignored by previous researchers. Then, observing that existing algorithms are susceptible to noisy similarities, the proposed regularized ensemble diffusion (RED) is bundled with an automatic weight learning paradigm, so that the negative impacts of noisy similarities are suppressed. Though formulated as a convex optimization problem, one advantage of RED is that it converts back into the iteration-based solver with the same computational complexity as the conventional diffusion process. At last, we integrate several recently-proposed similarities with the proposed framework. The experimental results suggest that we can achieve new state-of-the-art performances on various retrieval tasks, including 3D shape retrieval on the ModelNet data set, and image retrieval on the Holidays and Ukbench data sets. [ABSTRACT FROM AUTHOR]

Highlights • We propose a simple yet effective quantization to embed deep binary codes. • Activations from multiple CNN layers function together through weighted score fusion in the proposed framework. • Handcrafted local descriptor SIFT, as a kind of low level feature, can also be combined in our fusion procedure. • Regularized diffusion process are customized on the ranking list to make the similarity estimation vary smoothly. • Extensive experiments are conducted on four public datasets, and state-of-the-art results are obtained on Holidays and UKBench datasets. Abstract Convolutional Neural Networks (CNNs) have achieved a breakthrough on a large number of image retrieval benchmarks. However, most previous works make use of the CNNs following the image classification strategy, where the last fully connected layer activations of the whole image are occupied as a single holistic feature vector. To improve the representation power of CNNs, this paper proposes a Multi-layer Fusion (MF) approach to aggregate deep activations for image retrieval task. The key insight of our approach is that different layers of a CNN are sensitive to specific patterns, and are complementary with each other for image representation. Specifically, our approach transforms CNN activations to deep binary codes embedded in the inverted index of Bag-of-Words structure for fast retrieval. Those activations are derived from multiple layers of a CNN on local patches, for features from orderless local areas have proved superior to global ones in the low level handcrafted cases. Corresponding weights and diffusion process are thereafter utilized to penalize and re-rank the individual similarity scores of layers. Our method is efficient, which extracts visual features from different layers only once. Furthermore, the proposed MF approach can be easily extended to include SIFT features to enhance the representation power. Extensive experiments on four public retrieval datasets quantitatively evaluate the effectiveness of our contributions, and the proposed algorithm prove to be the new state-of-the-art on the Holidays and UKBench datasets. [ABSTRACT FROM AUTHOR]

Due to the ability of capturing the geometry structure of data manifold, context-sensitive similarity has demonstrated impressive performances in the retrieval task. The key idea of context-sensitive similarity is that the similarity between two data points can be more reliably estimated with the local context of other points in the affinity graph. Therefore, neighborhood selection is a crucial factor for those algorithms, which affects the performance dramatically. In this paper, we propose a new algorithm called Smooth Neighborhood (SN) that mines the neighborhood structure to satisfy the manifold assumption. By doing so, nearby points on the underlying manifold are guaranteed to yield similar neighbors as much as possible. Moreover, SN is adjusted to tackle multiple affinity graphs by imposing a weight learning paradigm, and this is the primary difference compared with related works which are only applicable with one affinity graph. Finally, we integrate SN with Sparse Contextual Activation (SCA), a representative context-sensitive similarity proposed recently. Extensive experimental results and comparisons manifest that with the neighborhood structure generated by SN, the proposed framework can yield state-of-the-art performances on shape retrieval, image retrieval and 3D model retrieval. [ABSTRACT FROM AUTHOR]

In content-based image retrieval, SIFT feature and the feature from deep convolutional neural network (CNN) have demonstrated promising performance. To fully explore both visual features in a unified framework for effective and efficient retrieval, we propose a collaborative index embedding method to implicitly integrate the index matrices of them. We formulate the index embedding as an optimization problem from the perspective of neighborhood sharing and solve it with an alternating index update scheme. After the iterative embedding, only the embedded CNN index is kept for on-line query, which demonstrates significant gain in retrieval accuracy, with very economical memory cost. Extensive experiments have been conducted on the public datasets with million-scale distractor images. The experimental results reveal that, compared with the recent state-of-the-art retrieval algorithms, our approach achieves competitive accuracy performance with less memory overhead and efficient query computation. [ABSTRACT FROM PUBLISHER]

The rapidly increasing number of images on the internet has further increased the need for efficient indexing for digital image searching of large databases. The design of a cloud service that provides high efficiency but compact image indexing remains challenging, partly due to the well-known semantic gap between user queries and the rich semantics of large-scale data sets. In this paper, we construct a novel joint semantic-visual space by leveraging visual descriptors and semantic attributes, which narrows the semantic gap by combining both attributes and indexing into a single framework. Such a joint space embraces the flexibility of coherent semantic-visual indexing, which employs binary codes to boost retrieval speed while maintaining accuracy. To solve the proposed model, we make the following contributions. First, we propose an interactive optimization method to find the joint semantic and visual descriptor space. Second, we prove convergence of our optimization algorithm, which guarantees a good solution after a certain number of iterations. Third, we integrate the semantic-visual joint space system with spectral hashing, which finds an efficient solution to search up to billion-scale data sets. Finally, we design an online cloud service to provide a more efficient online multimedia service. Experiments on two standard retrieval datasets (i.e., Holidays1M, Oxford5K) show that the proposed method is promising compared with the current state-of-the-art and that the cloud system significantly improves performance. [ABSTRACT FROM AUTHOR]

Traditional image resizing methods, such as uniform scaling and content-aware image retargeting, are designed to preserve the visually salient contents of an image while resizing it. In this paper, we propose a novel image resizing approach called recognition-oriented image retargeting. Its goal is to preserve the distinctive local features for recognition instead of the traditional visual saliency during resizing. Moreover, we also apply our approach to image matching and image retrieval applications to verify its performance. Meanwhile, using our approach to these applications is able to solve some of the challenging problems in their fields. In image matching application, we find that our approach shows promising preservation of local feature descriptors. In image retrieval task, extensive experiments on Oxford5K, Holidays, Paris, and Flickr100k data sets demonstrate that our approach consistently outperforms other image retargeting methods by large margins in the aspects of retrieval precision and query bits. [ABSTRACT FROM PUBLISHER]

The scale-invariant feature transform (SIFT) feature plays a very important role in multimedia content analysis, such as near-duplicate image and video retrieval. However, the storage and query costs of SIFT become unbearable for large-scale databases. In this paper, SIFT features are robustly encoded with temporal information by tracking the SIFT to generate temporal-concentration SIFT (TCSIFT), which highly compresses the quantity of local features to reduce visual redundancy, and keeps the advantages of SIFT as much as possible at the same time. On the basis of TCSIFT, a novel framework for large-scale video copy retrieval is proposed in which the processes of retrieval and validation are implemented at the feature and frame level. Experimental results for two different datasets, i.e., CC_WEB_VIDEO and TRECVID, demonstrate that our method can yield comparable accuracy, compact storage size, and more efficient execution time, as well as adapt to various video transformations. [ABSTRACT FROM AUTHOR]

In this paper, we investigate the problem of scalable visual feature matching in large-scale image search and propose a novel cascaded scalar quantization scheme in dual resolution. We formulate the visual feature matching as a range-based neighbor search problem and approach it by identifying hyper-cubes with a dual-resolution scalar quantization strategy. Specifically, for each dimension of the PCA-transformed feature, scalar quantization is performed at both coarse and fine resolutions. The scalar quantization results at the coarse resolution are cascaded over multiple dimensions to index an image database. The scalar quantization results over multiple dimensions at the fine resolution are concatenated into a binary super-vector and stored into the index list for efficient verification. The proposed cascaded scalar quantization (CSQ) method is free of the costly visual codebook training and thus is independent of any image descriptor training set. The index structure of the CSQ is flexible enough to accommodate new image features and scalable to index large-scale image database. We evaluate our approach on the public benchmark datasets for large-scale image retrieval. Experimental results demonstrate the competitive retrieval performance of the proposed method compared with several recent retrieval algorithms on feature quantization. [ABSTRACT FROM PUBLISHER]

In content-based image retrieval, inverted indexes allow fast access to database images and summarize all knowledge about the database. Indexing multiple clues of image contents allows retrieval algorithms search for relevant images from different perspectives, which is appealing to deliver satisfactory user experiences. However, when incorporating diverse image features during online retrieval, it is challenging to ensure retrieval efficiency and scalability. In this paper, for large-scale image retrieval, we propose a semantic-aware co-indexing algorithm to jointly embed two strong cues into the inverted indexes: 1) local invariant features that are robust to delineate low-level image contents, and 2) semantic attributes from large-scale object recognition that may reveal image semantic meanings. Specifically, for an initial set of inverted indexes of local features, we utilize semantic attributes to filter out isolated images and insert semantically similar images to this initial set. Encoding these two distinct and complementary cues together effectively enhances the discriminative capability of inverted indexes. Such co-indexing operations are totally off-line and introduce small computation overhead to online retrieval, because only local features but no semantic attributes are employed for the query. Hence, this co-indexing is different from existing image retrieval methods fusing multiple features or retrieval results. Extensive experiments and comparisons with recent retrieval methods manifest the competitive performance of our method. [ABSTRACT FROM PUBLISHER]

Recently, the bag-of-words representation is widely applied in the image retrieval applications. In this model, visual word is a core component. However, compared with text retrieval, one major problem associated with image retrieval consists in the visual word ambiguity, i.e., a trade-off between precision and recall of visual matching. To address this problem, this paper proposes a tensor index structure to improve precision and recall simultaneously. Essentially, the tensor index is a multi-dimensional index structure. It combines the strengths of two state-of-the-art indexing strategies, i.e., the inverted multi-index [Babenko and Lempitsky (Computer vision and pattern recognition (CVPR), 2012 IEEE Conference, 3069-3076, )] as well as the joint inverted index [Xia et al. (ICCV, )] which are initially designed for approximate nearest neighbor search problems. This paper, instead, exploits their usage in the scenario of image retrieval and provides insights into how to combine them effectively. We show that on the one hand, the multi-index enhances the discriminative power of visual words, thus improving precision; on the other hand, the introduction of multiple codebooks corrects quantization artifacts, thus improving recall. Extensive experiments on two benchmark datasets demonstrate that tensor index significantly improves the baseline approach. Moreover, when incorporating methods such as Hamming embedding, we achieve competitive performances compared to the state-of-the-art ones. [ABSTRACT FROM AUTHOR]

In this work, we propose an efficient image re-ranking method, without regional information of each indexed feature stored in the inverted file, to re-rank all retrieved images. The motivation of the proposed method is that, there are usually many visual words in the query image that only give votes to irrelevant images. With this observation, we propose to use visual words which are actually useful in finding relevant images to re-rank the retrieved images. To achieve this goal, we first initialize some images similar to the query by maximizing a quadratic function when giving an initial ranking of the retrieved images. The quadratic function is constructed by storing the similarities among a short-list of top ranked images into an affinity matrix, where the similarity between any two images is computed by the proposed graph diffusion. Then, we select a subset of visual words in the query with an alternating optimization strategy: (1) at each iteration, visual words are selected based on the set of similar images that we have found, (2) and in turn, the set of similar images is updated with the set of selected words. These two steps are repeated until convergence. Experimental results on standard benchmark datasets show that the proposed method achieves an order of magnitude speedups over the state-of-the-art spatial based re-ranking techniques, and obtains much better retrieval quality as well. [ABSTRACT FROM AUTHOR]

The objective of large-scale object retrieval systems is to search for images that contain the target object in an image database. Where state-of-the-art approaches rely on global image representations to conduct searches, we consider many boxes per image as candidates to search locally in a picture. In this paper, a feature quantization algorithm called binary quantization is proposed. In binary quantization, a scale-invariant feature transform (SIFT) feature is quantized into a descriptive and discriminative bit-vector, which allows itself to adapt to the classic inverted file structure for box indexing. The inverted file, which stores the bit-vector and box ID where the SIFT feature is located inside, is compact and can be loaded into the main memory for efficient box indexing. We evaluate our approach on available object retrieval datasets. Experimental results demonstrate that the proposed approach is fast and achieves excellent search quality. Therefore, the proposed approach is an improvement over state-of-the-art approaches for object retrieval. [ABSTRACT FROM AUTHOR]