Search

Recent works in image captioning have shown very promising raw performance. However, we realize that most of these encoder–decoder style networks with attention do not scale naturally to large vocabulary size, making them difficult to deploy on embedded systems with limited hardware resources. This is because the size of word and output embedding matrices grow proportionally with the size of vocabulary, adversely affecting the compactness of these networks. To address this limitation, this paper introduces a brand new idea in the domain of image captioning. That is, we tackle the problem of compactness of image captioning models which is hitherto unexplored. We showed that our proposed model, named COMIC for compact image captioning, achieves comparable results in five common evaluation metrics with state-of-the-art approaches on both MS-COCO and InstaPIC-1.1M datasets despite having an embedded vocabulary size that is 39×−99× smaller. [ABSTRACT FROM AUTHOR]

Recent adversarial attack works attempt to improve the transferability by applying various differentiable transformations on input images. Considering the differentiable transformations and the original model together as a new model, these methods can be regarded as model augmentation that effectively derives an ensemble of models from the single original model. Despite their impressive performance, the model augmentation policies used in these methods are manually designed by experimental attempts, leaving the design of model augmentation policy an open question. In this paper, we propose an Automatic Model Augmentation (AutoMA) approach to find a strong model augmentation policy for transferable adversarial attacks. Specifically, we design a discrete search space that contains various diffierentiable transformations with different parameters and adopt reinforcement learning to search for the strong augmentation policy. The sampled augmentation policies together with the rewards they obtain during the searching process reveal several valuable observations for designing more powerful attacks using model augmentation policy: 1) Augmentation transformations on color space are less effective; 2) The transformation type diversity matters; and 3) Using small distortion for geometric transformations while larger distortion for intensity transformations. Extensive experiments show that the augmentation policy found by AutoMA achieves superior performance than existing manually designed policies in a wide range of cases. [ABSTRACT FROM AUTHOR]

Whereas deep neural networks were first mostly used for classification tasks, they are rapidly expanding in the realm of structured output problems, where the observed target is composed of multiple random variables that have a rich joint distribution, given the input. In this paper we focus on the case where the input also has a rich structure and the input and output structures are somehow related. We describe systems that learn to attend to different places in the input, for each element of the output, for a variety of tasks: machine translation, image caption generation, video clip description, and speech recognition . All these systems are based on a shared set of building blocks: gated recurrent neural networks and convolutional neural networks , along with trained attention mechanisms. We report on experimental results with these systems, showing impressively good performance and the advantage of the attention mechanism. [ABSTRACT FROM PUBLISHER]

This study proposes a simple but strong baseline for deep person re-identification (ReID). Deep person ReID has achieved great progress and high performance in recent years. However, many state-of-the-art methods design complex network structures and concatenate multi-branch features. In the literature, some effective training tricks briefly appear in several papers or source codes. The present study collects and evaluates these effective training tricks in person ReID. By combining these tricks, the model achieves 94.5% rank-1 and 85.9% mean average precision on Market1501 with only using the global features of ResNet50. The performance surpasses all existing global- and part-based baselines in person ReID. We propose a novel neck structure named as batch normalization neck (BNNeck). BNNeck adds a batch normalization layer after global pooling layer to separate metric and classification losses into two different feature spaces because we observe they are inconsistent in one embedding space. Extended experiments show that BNNeck can boost the baseline, and our baseline can improve the performance of existing state-of-the-art methods. Our codes and models are available at: https://github.com/michuanhaohao/reid-strong-baseline [ABSTRACT FROM AUTHOR]

In recent years, the task of automatically generating image description has attracted a lot of attention in the field of artificial intelligence. Benefitting from the development of convolutional neural networks (CNNs) and recurrent neural networks (RNNs), many approaches based on the CNN-RNN framework have been proposed to solve this task and achieved remarkable process. However, two problems remain to be tackled in which the most existing methods use only the image-level representation. One problem is object missing, in which some important objects may be missing when generating the image description and the other is misprediction, when one object may be recognized in a wrong category. In this paper, to address these two problems, we propose a new method called global–local attention (GLA) for generating image description. The proposed GLA model utilizes an attention mechanism to integrate object-level features with image-level feature. Through this manner, our model can selectively pay attention to objects and context information concurrently. Therefore, our proposed GLA method can generate more relevant image description sentences and achieve the state-of-the-art performance on the well-known Microsoft COCO caption dataset with several popular evaluation metrics—CIDEr, METEOR, ROUGE-L and BLEU-1, 2, 3, 4. [ABSTRACT FROM PUBLISHER]

Robust image registration is a challenging problem, especially when dealing with severe changes in illumination and viewpoint. Previous methods assume a global geometric model (e.g., homography) and, hence, are only able to align images under predefined constraints (e.g., planar scenes and parallax-free camera motion). However, these constraints may not hold for natural scenes and uncontrolled imaging conditions. Therefore, this paper proposes a novel method which approximates image regions with planes by incorporating piecewise local geometric models. The approximated planar regions are obtained by exploiting a hierarchical figure-ground segmentation method. Each such planar region assumes an affine transformation. To achieve the alignment of the planar regions, an energy function is defined which employs intensity, a key-point descriptor, and geometric information under a global constraint. By re-segmenting and re-merging planar regions iteratively in an energy minimization framework, the method is able to align images even under significant changes in illumination and viewpoint. Experiments on two datasets show that the proposed method outperforms state-of-the-art, especially in the case of large appearance variations and it is, therefore, applicable to web-images (i.e., unconstrained setting) which are taken from the same scene with different viewpoints. [ABSTRACT FROM PUBLISHER]

Fine-grained object classification (FGOC) is a challenging research topic in multimedia computing with machine learning, which faces two pivotal conundrums: focusing attention on the discriminate part regions, and then processing recognition with the part-based features. Existing approaches generally adopt a unidirectional two-step structure, that first locate the discriminate parts and then recognize the part-based features. However, they neglect the truth that part localization and feature recognition can be reinforced in a bidirectional process. In this paper, we propose a novel bidirectional attention-recognition model (BARM) to actualize the bidirectional reinforcement for FGOC. The proposed BARM consists of one attention agent for discriminate part regions proposing and one recognition agent for feature extraction and recognition. Meanwhile, a feedback flow is creatively established to optimize the attention agent directly by recognition agent. Therefore, in BARM the attention agent and the recognition agent can reinforce each other in a bidirectional way and the overall framework can be trained end-to-end without neither object nor parts annotations. Moreover, a novel Multiple Random Erasing data augmentation is proposed, and it exhibits impressive pertinency and superiority for FGOC. Conducted on several extensive FGOC benchmarks, BARM outperforms the present state-of-the-art methods in classification accuracy. Furthermore, BARM exhibits a clear interpretability and keeps consistent with the human perception in visualization experiments. [ABSTRACT FROM AUTHOR]

Network quantization offers an effective solution to deep neural network compression for practical usage. Existing network quantization methods cannot theoretically guarantee the convergence. This paper proposes a novel iterative framework for network quantization with arbitrary bit-widths. We present two Lipschitz constraint based quantization strategies, namely width-level network quantization (WLQ) and multi-level network quantization (MLQ), for high-bit and extremely low-bit (ternary) quantization, respectively. In WLQ, Lipschitz based partition is developed to divide parameters in each layer into two groups: one for quantization and the other for re-training to eliminate the quantization loss. WLQ is further extended to MLQ by introducing layer partition to suppress the quantization loss for extremely low bit-widths. The Lipschitz based partition is proven to guarantee the convergence of the quantized networks. Moreover, the proposed framework is complementary to network compression methods such as activation quantization, pruning and efficient network architectures. The proposed framework is evaluated over extensive state-of-the-art deep neural networks, i.e., AlexNet, VGG-16, GoogleNet and ResNet18. Experimental results show that the proposed framework improves the performance of tasks like classification, object detection and semantic segmentation. [ABSTRACT FROM AUTHOR]

Recently, convolutional neural network (CNN) based models have shown great potential in the task of single image super-resolution (SISR). However, many state-of-the-art SISR solutions are reproducing some tricks proven effective in other vision tasks, such as pursuing a deeper model. In this paper, we propose a new solution (named as Multi-Receptive-Field Network - MRFN), which outperforms existing SISR solutions in three different aspects. First, from receptive field: a novel multi-receptive-field (MRF) module is proposed to extract and fuse features in different receptive fields from local to global. Integrating these hierarchical features can generate better mappings on recovering high-fidelity details at different scales. Second, from network architectures: both dense skip connections and deep supervision are utilized to combine features from the current MRF module and preceding ones for training more representative features. Moreover, a deconvolution layer is embedded at the end of the network to avoid artificial priors induced by numerical data pre-processing (e.g., bicubic stretching), and speed up the restoration process. Finally, from error modeling: different from $L1$ and $L2$ loss functions, we proposed a novel two-parameter training loss called Weighted Huber loss function which can adaptively adjust the value of back-propagated derivative according to the residual value, thus fit the reconstruction error more effectively. Extensive qualitative and quantitative evaluation results on benchmark datasets demonstrate that our proposed MRFN can achieve more accurate recovering results than most state-of-the-art methods with significantly less complexity. [ABSTRACT FROM AUTHOR]

When different target surfaces, in three-dimensional space, are mapped onto an image plane, they have different projections. These projections vary with the viewpoint. These local differences have influence on the accuracy of image stitching. Most of the existing image stitching methods divide an input image into a number of fixed-size cells, and the pixels within the same cell are then warped using the same local transformation model for the alignment. These methods are based on the hypothesis that the transformation models in one cell are consistent. However, this hypothesis does not hold in general. In this paper, we propose a novel projective-consistent plane based image stitching method (termed PCPS). It divides the overlapping regions of an input image into some projective-consistent planes according to the normal vectors’ orientations of local regions and the reprojection errors of aligned images. The local projective transformation model is estimated for each projective-consistent plane. And then, a hybrid warping model is estimated. For the pixels in overlapping regions, the local projective transformation models are adopted to achieve a better alignment. While for the pixels in non-overlapping regions, a global projective transformation model is estimated by using the inliers uniformly distributed in the projective-consistent planes to avoid distortion. Compared with the state-of-the-art image stitching methods, the experimental results on a number of challenging image sequences show that the projective transformation model estimated by the proposed PCPS method for each projective-consistent plane is more accurate, and the achieved stitching results have less seams and projective distortion. [ABSTRACT FROM AUTHOR]

Precise friend recommendation is an important problem in social media. Although most social websites provide some kinds of auto friend searching functions, their accuracies are not satisfactory. In this paper, we propose a more precise auto friend recommendation method with two stages. In the first stage, by utilizing the information of the relationship between texts and users, as well as the friendship information between users, we align different social networks and choose some “possible friends.” In the second stage, with the relationship between image features and users, we build a topic model to further refine the recommendation results. Because some traditional methods, such as variational inference and Gibbs sampling, have their limitations in dealing with our problem, we develop a novel method to find out the solution of the topic model based on series expansion. We conduct experiments on the Flickr dataset to show that the proposed algorithm recommends friends more precisely and faster than traditional methods. [ABSTRACT FROM PUBLISHER]

With the growing demand for easy and reliable generation of 3D models representing real-world or synthetic objects, new schemes for acquisition, storage, and transmission of 3D meshes are required. In principle, 3D meshes consist of vertex positions and vertex connectivity. Vertex position encoders are much more resource demanding than connectivity encoders, stressing the need for novel geometry compression schemes. The design of an accurate and efficient geometry compression system can be achieved by increasing the compression ratio without affecting the visual quality of the object and minimizing the computational complexity. In this paper, we present novel compression/reconstruction schemes that enable aggressive compression ratios, without significantly reducing the visual quality. The encoding is performed by simply executing additions/subtractions. The benefits of the proposed method become more apparent as the density of the meshes increases, while it provides a flexible framework to trade efficiency for reconstruction quality. We derive a novel Bayesian learning algorithm that models the most significant graph Fourier transform coefficients of each submesh, as a multivariate Gaussian distribution. Then we evaluate iteratively the distribution parameters using the expectation-maximization approach. To improve the performance of the proposed approach in highly under determined problems, we exploit the local smoothness of the partitioned surfaces. Extensive evaluation studies, carried out using a large collection of different 3D models, show that the proposed schemes, as compared to the state-of-the-art approaches, achieve competitive compression ratios, offering at the same time significantly lower encoding complexity. [ABSTRACT FROM PUBLISHER]

To enhance the visibility and usability of images captured in hazy conditions, many image dehazing algorithms (DHAs) have been proposed. With so many image DHAs, there is a need to evaluate and compare these DHAs. Due to the lack of the reference haze-free images, DHAs are generally evaluated qualitatively using real hazy images. But it is possible to perform quantitative evaluation using synthetic hazy images since the reference haze-free images are available and full-reference (FR) image quality assessment (IQA) measures can be utilized. In this paper, we follow this strategy and study DHA evaluation using synthetic hazy images systematically. We first build a synthetic haze removing quality (SHRQ) database. It consists of two subsets: regular and aerial image subsets, which include 360 and 240 dehazed images created from 45 and 30 synthetic hazy images using 8 DHAs, respectively. Since aerial imaging is an important application area of dehazing, we create an aerial image subset specifically. We then carry out subjective quality evaluation study on these two subsets. We observe that taking DHA evaluation as an exact FR IQA process is questionable, and the state-of-the-art FR IQA measures are not effective for DHA evaluation. Thus, we propose a DHA quality evaluation method by integrating some dehazing-relevant features, including image structure recovering, color rendition, and over-enhancement of low-contrast areas. The proposed method works for both types of images, but we further improve it for aerial images by incorporating its specific characteristics. Experimental results on two subsets of the SHRQ database validate the effectiveness of the proposed measures. [ABSTRACT FROM AUTHOR]

With the rapid development of deep learning models, their performances in various tasks have improved; meanwhile, their increasingly intricate architectures make them difficult to interpret. To tackle this challenge, model interpretability is essential and has been investigated in a wide range of applications. For end users, model interpretability can be used to build trust in the deployed machine learning models. For practitioners, interpretability plays a critical role in model explanation, model validation, and model improvement to develop a faithful model. In this paper, we propose a novel Multi-scale Interpretation (MINT) model for convolutional neural networks using both the perturbation-based and the gradient-based interpretation approaches. It learns the class-discriminative interpretable knowledge from the multi-scale perturbation of feature information in different layers of deep networks. The proposed MINT model provides the coarse-scale and the fine-scale interpretations for the attention in the deep layer and specific features in the shallow layer, respectively. Experimental results show that the MINT model presents the class-discriminative interpretation of the network decision and explains the significance of the hierarchical network structure. [ABSTRACT FROM AUTHOR]

Co-saliency detection aims to discover common and salient objects in an image group containing more than two relevant images. Moreover, depth information has been demonstrated to be effective for many computer vision tasks. In this paper, we propose a novel co-saliency detection method for RGBD images based on hierarchical sparsity reconstruction and energy function refinement. With the assistance of the intrasaliency map, the inter-image correspondence is formulated as a hierarchical sparsity reconstruction framework. The global sparsity reconstruction model with a ranking scheme focuses on capturing the global characteristics among the whole image group through a common foreground dictionary. The pairwise sparsity reconstruction model aims to explore the corresponding relationship between pairwise images through a set of pairwise dictionaries. In order to improve the intra-image smoothness and inter-image consistency, an energy function refinement model is proposed, which includes the unary data term, spatial smooth term, and holistic consistency term. Experiments on two RGBD co-saliency detection benchmarks demonstrate that the proposed method outperforms the state-of-the-art algorithms both qualitatively and quantitatively. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel interpretable shape model to encode object nonrigidity. We first use the initial frames of a monocular video to recover a rest shape, used later to compute a dissimilarity measure based on a distance matrix measurement. Spectral analysis is then applied to this matrix to obtain a reduced shape basis, that in contrast to existing approaches, can be physically interpreted. In turn, these precomputed shape bases are used to linearly span the deformation of a wide variety of objects. We introduce the low-rank basis into a sequential approach to recover both camera motion and nonrigid shape from the monocular video, by simply optimizing the weights of the linear combination using bundle adjustment. Since the number of parameters to optimize per frame is relatively small, specially when physical priors are considered, our approach is fast and can potentially run in real time. Validation is done in a wide variety of real-world objects, undergoing both inextensible and extensible deformations. Our approach achieves remarkable robustness to artifacts such as noisy and missing measurements and shows an improved performance to competing methods. [ABSTRACT FROM AUTHOR]

The continuous advances in the storage and transmission capabilities of smart devices have made them possible to share multimedia services with each other through device-to-device (D2D) communications. However, when D2D users transmit multimedia services in manner of cooperative communications, the relay users with non-cooperative behavior may lead to a sharp decline in the quality of services for the receivers. In this paper, a socially aware trust framework for multimedia delivery is proposed to choose the trustworthy D2D cooperative users from D2D relay users. By considering the different D2D cooperative scenarios, the trust relationships of entities in the network are divided into two cases: capability trust mainly from base station (BS) to relay users and social trust from sender to relay users. In particular, capability trust is quantified based on the service capability of a user, such as caching capability, processing capability, and transmission capability, and social trust is obtained based on the historical interactive behaviors among users, such as cooperative behavior, altruistic behavior, and reciprocal behavior. By analyzing such two types of trust, the trustworthy D2D cooperative users are selected from relay users to support different cooperative scenarios. The numerical results verify that the proposed trust framework can effectively identify the selfish users and notably enhance the delivery efficiency of multimedia services, such as delay and delivery success ratio. [ABSTRACT FROM AUTHOR]

Depth information plays an important role in human vision as it provides additional cues that distinguish objects from their backgrounds. This paper explores depth information for analyzing stereoscopic saliency and presents a computational model that predicts stereoscopic visual saliency based on three aspects of human vision: 1) the pop-out effect; 2) comfort zones; and 3) background effects. Through an analysis of these three phenomena, we find that most of the stereoscopic saliency region can be explained. Our model comprises three modules, each describing one aspect of saliency distribution, and a control function that can be used to adjust the three models independently. The relationship between the three models is not mutually exclusive. One, two, or three phenomena may appear in one image. Therefore, to accurately determine which phenomena the image conforms to, we have devised a selection strategy that chooses the appropriate combination of models based on the content of the image. Our approach is implemented within a framework based on the multifeature analysis. The framework considers surrounding regions, color/depth contrast, and points of interest. The selection strategy can improve the performance of the framework. A series of experiments on two recent eye-tracking datasets shows that our proposed method outperforms several state-of-the-art saliency models. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel structure-guided framework for exemplar-based image inpainting to maintain the neighborhood consistence and structure coherence of an inpainted region. The proposed method consists of a data term for pixel validity and boundary continuity, a smoothness term to depict the compatibility of neighboring pixels for contextual continuity, and a coherence term to investigate image inherent regularities to ensure image self-similarity. To better reconstruct image structures, the method utilizes image regularity statistics to extract dominant linear structures of the target image. Guided by these structures, homography transformations are estimated and combined to globally repair the missing region using the Markov random field model. To reduce computational complexity, a hierarchical process is implemented to utilize the regularity effectively. The experimental results demonstrate that our method yields better results for various real-world scenes than existing state-of-the-art image inpainting techniques. [ABSTRACT FROM AUTHOR]

This paper presents a novel space-time feature-based human activity analysis system. We detect Space Time Interest Points (STIP) and generate their description based on the facet model. The proposed approach detects interest points in video data using the three-dimensional facet model efficiently. Then we describe each interest point by three-dimensional Haar wavelet transform and time derivatives of different order obtained from said facet model. Here we represent each video clip following the bag-of-words approach by learning feature specific dictionary. Finally, classification is done using non-linear SVM with \chi^2-kernel. We evaluate the performance of our system on standard datasets like Weizmann, KTH, UCF sports, ICD, UCF YouTube, and UCF50 and get better, or at least comparable results compared to other state-of-the-art systems. [ABSTRACT FROM PUBLISHER]

Image stitching aims at generating high-quality panoramas with the lowest computational cost. In this paper, we propose a parallax-tolerant image stitching method based on robust elastic warping, which could achieve accurate alignment and efficient processing simultaneously. Given a group of point matches between images, an analytical warping function is constructed to eliminate the parallax errors. Then, the input images are warped according to the computed deformations over the meshed image plane. The seamless panorama is composed by directly reprojecting the warped images. As an important complement to the proposed method, a Bayesian model of feature refinement is proposed to adaptively remove the incorrect local matches. This ensures a more robust alignment than existing approaches. Moreover, our warp is highly compatible with different transformation types. A flexible strategy of combining it with the global similarity transformation is provided as an example. The performance of the proposed approach is demonstrated using several challenging cases. [ABSTRACT FROM AUTHOR]

Real-time object tracking has wide applications in time-critical multimedia processing areas such as motion analysis and human–computer interaction. It remains a hard problem to balance between accuracy and speed. In this paper, we present a fast real-time context-based visual tracking algorithm with a new saliency prior context (SPC) model. Based on the probability formulation, the tracking problem is solved by sequentially maximizing the computed confidence map of target location in each video frame. To handle the various cases of feature distributions generated from different targets and their contexts, we exploit low-level features as well as fast spectral analysis for saliency to build a new prior context model. Then, based on this model and a spatial context model learned online, a confidence map is computed and the target location is estimated. In addition, under this framework, the tracking procedure can be accelerated by the fast Fourier transform. Therefore, the new method generally achieves a real-time running speed. Extensive experiments show that our tracking algorithm based on the proposed SPC model achieves real-time computation efficiency with overall best performance comparing with other state-of-the-art methods. [ABSTRACT FROM PUBLISHER]

The view-based 3-D model retrieval system represents a 3-D model by its projected views. Most of the existing view-based 3-D model retrieval systems only analyze the features of the projected views, but not well consider the spatial arrangements of the viewpoints. Furthermore, most of these systems suffer from the high computational cost due to pairwise comparing the projected views of 3-D models. In this paper, we propose a new 3-D model descriptor called Sphere Image, which is defined as a collection of view features. A viewpoint of a 3-D model is regarded as a “pixel”: (1) The position of the viewpoint is denoted as the coordinate of the “pixel”. (2) The feature descriptor of the projected view is denoted as the value of the “pixel”. We also propose a probabilistic graphical model for 3-D model matching, and develop a 3-D model retrieval system to test our approach. We have conducted experiments based on the SHape REtrieval Contest (SHREC) 2012 generic 3-D model date set and the SHREC2009 partial 3-D model data set. Experimental results indicate that our system outperforms some state-of-the-art 3-D model retrieval systems. [ABSTRACT FROM PUBLISHER]

Social media has become a very popular way for people to share their photos with friends. Because most of the social images are attached with GPS (geo-tags), a photo's GPS information can be estimated with the help of the large geo-tagged image set while using a visual searching based approach. This paper proposes an unsupervised image GPS location estimation approach with hierarchical global feature clustering and local feature refinement. It consists of two parts: an offline system and an online system. In the offline system, a hierarchical structure is constructed for a large-scale offline social image set with GPS information. Representative images are selected for each GPS location refined cluster, and an inverted file structure is proposed. In the online system, when given an input image, its GPS information can be estimated by hierarchical global clusters selection and local feature refinement in the online system. Both the computational cost and GPS estimation performance demonstrates the effectiveness of the proposed hierarchical structure and inverted file structure in our approach. [ABSTRACT FROM PUBLISHER]

The background information is a significant prior for salient object detection, especially when images contain cluttered background and diverse object parts. In this paper, we propose a background-driven salient object detection (BD-SOD) method to more comprehensively exploit the background prior, aiming at generating more accurate and robust salient maps. To be specific, we first exploit the background prior to conduct the saliency estimation, i.e., computing the regional saliency values. In this stage, the background prior is utilized in threefold: restricting the reference regions to only the background regions, weighting the contribution of reference regions, and leveraging the importance of different features. Benefiting from such an explicit utilization, the proposed model can greatly mitigate the negative interference of the cluttered background and diverse object parts. We then embed the background prior into the optimization graph for saliency refinement. Specifically, two virtual supernodes (representing the background and foreground, respectively) are introduced with extra connections, and the nonlocal feature connections between similar regions are also set up. These connections enhance the power of optimization graph to alleviate the perturbations from diverse parts, and thus help to achieve the uniformity of saliency values. Finally, we provide systematical studies to investigate the effectiveness of the proposed BD-SOD in exploiting the valuable background prior. Experimental results on multiple public benchmark datasets, including MSRA-1000, THUS-10000, PASCAL-S, and ECSSD, clearly show that BD-SOD consistently outperforms the well-established baselines and achieves state-of-the-art performance. [ABSTRACT FROM PUBLISHER]

The combination of pixel and superpixel has been widely utilized in the interactive segmentation methods to overcome the sensitivity to the seeds’ quantity and quality. However, because of the introduction of more variables and variables’ interactions, the pixel–superpixel combination methods are still limited to the segmentation accuracy and computational complexity. To solve these problems, in this paper, we propose an interactive multilabel image segmentation method. In the proposed segmentation model, the multilayer relationships among the pixel layer, superpixel layer, and label layer are fused by the Markov random field framework to further improve the segmentation accuracy. During the optimization stage, the parallel partial optimality strategy is utilized to effectively solve the multilabel submodular energy function. Experimental results on challenging data sets demonstrate the competitiveness of the proposed method comparing with several state-of-the-art interactive algorithms. [ABSTRACT FROM PUBLISHER]

This paper addresses the problem of recognizing human skeletal interactions using multiview data captured from depth sensors. The interactions among people are important cues for group and crowd human behavior analysis. In this paper, we focus on modeling the person–person skeletal interactions for human activity recognition. First, we propose a novel graph model in each single-view case to encode class-specific person–person interaction patterns. Particularly, we model each person–person interaction by an attributed graph, which is designed to preserve the complex spatial structure among skeletal joints according to their activity levels as well as the spatio-temporal joint features. Then, combining the graph models for each single-view case, we propose the multigraph model to characterize each multiview interaction. Finally, we apply a general multiple kernel learning method to determine the optimal kernel weights for the proposed multigraph model while the optimal classifier is jointly learned. We evaluate the proposed approach on the M$^2$I dataset, the SBU Kinect interaction dataset, and our interaction dataset. The experimental results show that our proposed approach outperforms several existing interaction recognition methods. [ABSTRACT FROM PUBLISHER]

In this paper, we introduce a new model called Latent Mixture of Discriminative Experts which can automatically learn the temporal relationship between different modalities. Since, we train separate experts for each modality, LMDE is capable of improving the prediction performance even with limited amount of data. For model interpretation, we present a sparse feature ranking algorithm that exploits L1 regularization. An empirical evaluation is provided on the task of listener backchannel prediction (i.e., head nod). We introduce a new error evaluation metric called User-adaptive Prediction Accuracy that takes into account the difference in people's backchannel responses. Our results confirm the importance of combining five types of multimodal features: lexical, syntactic structure, part-of-speech, visual and prosody. Latent Mixture of Discriminative Experts model outperforms previous approaches. [ABSTRACT FROM PUBLISHER]

As an important solution for 3D shape retrieval, a multi-view shape descriptor has achieved impressive performance. One crucial part of view-based shape descriptors is to interpret 3D structures through various 2D observations. Most existing methods like MVCNN believe that a strong classification model trained with deep learning, can often provide an efficient shape embedding for 3D shape retrieval. However, these methods pay much attention to discriminative models and none of them necessarily incorporate the underlying 3D properties of the objects from 2D images. In this paper, we present a novel encoder-decoder recurrent feature aggregation network (ERFA-Net) to address this problem. Aiming at emphasizing the 3D properties of 3D shapes in the fusion of multiple view features, 3D properties prediction tasks are introduced into the 3D shape retrieval. Specifically, an image sequence of the shape is recurrently aggregated into a discriminative shape embedding based on LSTM network, and then this latent shape embedding is trained to predict the original voxel grids and estimate images of unseen viewpoints. This generation task gives an effective supervision which makes the network exploit 3D properties of shapes through various 2D images. Our method achieves the state-of-the-art performance for 3D shape retrieval, on two large-scale 3D shape datasets, ModelNet and ShapeNetCore55. Extensive experiments show that the proposed 3D representation performs robust discrimination against view occlusion, and strong generation ability for various 3D shape tasks. [ABSTRACT FROM AUTHOR]

Pose tracking from range image sequences remains a difficult task due to strong noise and serious self-occlusion of human body. Existing work either rely on extremely large and precisely annotated datasets, or rely on accurate human mesh model and GPU acceleration. In this paper, we propose an unsupervised real-time framework of pose tracking from range image sequences. Our framework consists of a visible hybrid model (VHM), a componentwise correspondence optimization (CCO) and a dynamic database lookup (DDL). VHM consists of component sphere sets and component visible spherical point sets which exhibits both simplicity and high accuracy. CCO converts the matching between VHM and input point cloud into several subproblems regarding local rotations of components and a global translation of body abdominal joint, each of which has an efficient closed form solution. DDL is designed to recover correct pose when tracking fails, which effectively mitigates accumulative error during tracking. Experiments on $\mathsf{SMMC}$ , $\mathsf{PDT}$ , $\mathsf{EVAL}$ datasets indicate that our framework not only achieves better or competitive precision compared with state-of-the-art methods, but also produces real-time efficiency in personal computers without GPU acceleration. [ABSTRACT FROM AUTHOR]

Feature matching is a fundamental problem in computer vision area. In many real applications, one can usually obtain some potential (candidate) matches $\mathcal {C}$ by using some discriminative feature descriptors, such as SIFT descriptor. Then, the feature matching problem can be formulated as the problem of trying to select the correct matches $\mathcal {S}$ from the potential match set $\mathcal {C}$. In this paper, we propose to solve matches selection by developing a novel intra-group sparse matching (IGSM) model. Our IGSM is motivated by a simple observation that the potential match set $\mathcal {C}$ can be divided into several non-overlapping groups $\mathcal {C}_i$ , among which the correct matches $\mathcal {S}$ are uniformly distributed. We thus develop an intra-group selection model to conduct matches selection at the intra-group level to incorporate the one-to-one matching constraint more in matches selection process. Our IGSM model has three main advantages: (1) The selection mechanism is parameter-free; (2) it generates an intra-group sparse solution which better maintains the one-to-one matching constraint in nature; (3) a simple yet effective update algorithm has been derived to solve IGSM model. The optimality and convergence of the algorithm are theoretically guaranteed. Experimental results on several image feature matching datasets show the effectiveness and efficiency of the proposed IGSM matching method. [ABSTRACT FROM AUTHOR]

Recently, due to the black box characteristics of deep learning techniques, the deep network-based computer-aided diagnosis (CADx) systems have encountered many difficulties in practical applications. The crux of the problem is that these models should be explainable the model should give doctors rationales that can explain the diagnosis. In this paper, we propose a visually interpretable network (VINet) which can generate diagnostic visual interpretations while making accurate diagnoses. VINet is an end-to-end model consisting of an importance estimation network and a classification network. The former produces a diagnostic visual interpretation for each case, and the classifier diagnoses the case. In the classifier, by exploring the information in the diagnostic visual interpretation, the irrelevant information in the feature maps is eliminated by our proposed feature destruction process. This allows the classification network to concentrate on the important features and use them as the primary references for classification. Through a joint optimization of higher classification accuracy and eliminating as many irrelevant features as possible, a precise, fine-grained diagnostic visual interpretation, along with an accurate diagnosis, can be produced by our proposed network simultaneously. Based on a computed tomography image dataset (LUNA16) on pulmonary nodule, extensive experiments have been conducted, demonstrating that the proposed VINet can produce state-of-the-art diagnostic visual interpretations compared with all baseline methods. [ABSTRACT FROM AUTHOR]

In this paper, we propose the multi-view saliency guided deep neural network (MVSG-DNN) for 3D object retrieval and classification. This method mainly consists of three key modules. First, the module of model projection rendering is employed to capture the multiple views of one 3D object. Second, the module of visual context learning applies the basic Convolutional Neural Networks for visual feature extraction of individual views and then employs the saliency LSTM to adaptively select the representative views based on multi-view context. Finally, with these information, the module of multi-view representation learning can generate the compile 3D object descriptors with the designed classification LSTM for 3D object retrieval and classification. The proposed MVSG-DNN has two main contributions: 1) It can jointly realize the selection of representative views and the similarity measure by fully exploiting multi-view context; 2) It can discover the discriminative structure of multi-view sequence without constraints of specific camera settings. Consequently, it can support flexible 3D object retrieval and classification for real applications by avoiding the required camera settings. Extensive comparison experiments on ModelNet10, ModelNet40, and ShapeNetCore55 demonstrate the superiority of MVSG-DNN against the state-of-art methods. [ABSTRACT FROM AUTHOR]

The password has become today's dominant method of authentication. While brute-force attack methods such as HashCat and John the Ripper have proven unpractical, the research then switches to password guessing. State-of-the-art approaches such as the Markov Model and probabilistic context-free grammar (PCFG) are all based on statistical probability. These approaches require a large amount of calculation, which is time-consuming. Neural networks have proven more accurate and practical in password guessing than traditional methods. However, a raw neural network model is not qualified for cross-site attacks because each dataset has its own features. Our work aims to generalize those leaked passwords and improves the performance in cross-site attacks. In this paper, we propose GENPass, a multi-source deep learning model for generating “general” password. GENPass learns from several datasets and ensures the output wordlist can maintain high accuracy for different datasets using adversarial generation. The password generator of GENPass is PCFG+LSTM (PL). We are the first to combine a neural network with PCFG. Compared with Long short-term memory (LSTM), PL increases the matching rate by 16%–30% in cross-site tests when learning from a single dataset. GENPass uses several PL models to learn datasets and generate passwords. The results demonstrate that the matching rate of GENPass is 20% higher than by simply mixing datasets in the cross-site test. Furthermore, we propose GENPass with probability (GENPass-pro), the updated version of GENPass, which can further increase the matching rate of GENPass. [ABSTRACT FROM AUTHOR]

The goal of image captioning is to automatically describe an image with a sentence, and the task has attracted research attention from both the computer vision and natural-language processing research communities. The existing encoder–decoder model and its variants, which are the most popular models for image captioning, use the image features in three ways: first, they inject the encoded image features into the decoder only once at the initial step, which does not enable the rich image content to be explored sufficiently while gradually generating a text caption; second, they concatenate the encoded image features with text as extra inputs at every step, which introduces unnecessary noise; and, third, they using an attention mechanism, which increases the computational complexity due to the introduction of extra neural nets to identify the attention regions. Different from the existing methods, in this paper, we propose a novel network, Recall Network, for generating captions that are consistent with the images. The recall network selectively involves the visual features by using a GridLSTM and, thus, is able to recall image contents while generating each word. By importing the visual information as the latent memory along the depth dimension LSTM, the decoder is able to admit the visual features dynamically through the inherent LSTM structure without adding any extra neural nets or parameters. The Recall Network efficiently prevents the decoder from deviating from the original image content. To verify the efficiency of our model, we conducted exhaustive experiments on full and dense image captioning. The experimental results clearly demonstrate that our recall network outperforms the conventional encoder–decoder model by a large margin and that it performs comparably to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Fine-grained image recognition is central to many multimedia tasks such as search, retrieval, and captioning. Unfortunately, these tasks are still challenging since the appearance of samples of the same class can be more different than those from different classes. This issue is mainly due to changes in deformation, pose, and the presence of clutter. In the literature, attention has been one of the most successful strategies to handle the aforementioned problems. Attention has been typically implemented in neural networks by selecting the most informative regions of the image that improve classification. In contrast, in this paper, attention is not applied at the image level but to the convolutional feature activations. In essence, with our approach, the neural model learns to attend to lower-level feature activations without requiring part annotations and uses those activations to update and rectify the output likelihood distribution. The proposed mechanism is modular, architecture-independent, and efficient in terms of both parameters and computation required. Experiments demonstrate that well-known networks such as wide residual networks and ResNeXt, when augmented with our approach, systematically improve their classification accuracy and become more robust to changes in deformation and pose and to the presence of clutter. As a result, our proposal reaches state-of-the-art classification accuracies in CIFAR-10, the Adience gender recognition task, Stanford Dogs, and UEC-Food100 while obtaining competitive performance in ImageNet, CIFAR-100, CUB200 Birds, and Stanford Cars. In addition, we analyze the different components of our model, showing that the proposed attention modules succeed in finding the most discriminative regions of the image. Finally, as a proof of concept, we demonstrate that with only local predictions, an augmented neural network can successfully classify an image before reaching any fully connected layer, thus reducing the computational amount up to 10%. [ABSTRACT FROM AUTHOR]

Cross-modal retrieval emphasizes understanding inter-modality semantic correlations, which is often achieved by designing a similarity function. Generally, one of the most important things considered by the similarity function is how to make the cross-modal similarity computable. In this paper, a deep and bidirectional representation learning model is proposed to address the issue of image–text cross-modal retrieval. Owing to the solid progress of deep learning in computer vision and natural language processing, it is reliable to extract semantic representations from both raw image and text data by using deep neural networks. Therefore, in the proposed model, two convolution-based networks are adopted to accomplish representation learning for images and texts. By passing the networks, images and texts are mapped to a common space, in which the cross-modal similarity is measured by cosine distance. Subsequently, a bidirectional network architecture is designed to capture the property of the cross-modal retrieval—the bidirectional search. Such architecture is characterized by simultaneously involving the matched and unmatched image–text pairs for training. Accordingly, a learning framework with maximum likelihood criterion is finally developed. The network parameters are optimized via backpropagation and stochastic gradient descent. A great deal of experiments are conducted to sufficiently evaluate the proposed method on three publicly released datasets: IAPRTC-12, Flickr30k, and Flickr8k. The overall results definitely show that the proposed architecture is effective and the learned representations have good semantics to achieve superior cross-modal retrieval performance. [ABSTRACT FROM PUBLISHER]

An ontology hierarchically encodes concepts and concept relationships, and has a variety of applications such as semantic understanding and information retrieval. Previous work for building ontologies has primarily relied on labor-intensive human contributions or focused on text-based extraction. In this paper, we consider the problem of automatically constructing a folksonomy-based visual ontology (FBVO) from the user-generated annotated images. A systematic framework is proposed consisting of three stages as concept discovery, concept relationship extraction, and concept hierarchy construction. The noisy issues of the user-generated tags are carefully addressed to guarantee the quality of derived FBVO. The constructed FBVO finally consists of 139 825 concept nodes and millions of concept relationships by mining more than 2.4 million Flickr images. Experimental evaluations show that the derived FBVO is of high quality and consistent with human perception. We further demonstrate the utility of the derived FBVO in applications of complex visual recognition and exploratory image search. [ABSTRACT FROM PUBLISHER]

Many visual applications have benefited from the outburst of web images, yet the imprecise and incomplete tags arbitrarily provided by users, as the thorn of the rose, may hamper the performance of retrieval or indexing systems relying on such data. In this paper, we propose a novel locality sensitive low-rank model for image tag completion, which approximates the global nonlinear model with a collection of local linear models. To effectively infuse the idea of locality sensitivity, a simple and effective pre-processing module is designed to learn suitable representation for data partition, and a global consensus regularizer is introduced to mitigate the risk of overfitting. Meanwhile, low-rank matrix factorization is employed as local models, where the local geometry structures are preserved for the low-dimensional representation of both tags and samples. Extensive empirical evaluations conducted on three datasets demonstrate the effectiveness and efficiency of the proposed method, where our method outperforms pervious ones by a large margin. [ABSTRACT FROM PUBLISHER]

The past few years have witnessed impressive progress on the research of salient object detection. Nevertheless , existing approaches still cannot perform satisfactorily in the case of complex scenes, particularly when the salient objects have non- uniform appearance or complicated shapes, and the background is complexly structured. One important reason for such limitations may be that these approaches commonly ignore the factor of perceptual grouping in saliency modeling. To address this issue, this paper presents a novel computational model for object -based visual saliency, which explicitly takes into consideration the connections between attention and perceptual grouping, and incorporates Gestalt grouping cues into saliency computation. Inspired by the sensory enhancement theory, we suggest a paradigm for object-based saliency modeling, that is, object-based saliency stems from spreading attention along Gestalt grouping cues. Computationally , three typical Gestalt cues, including proximity, similarity, and closure, are respectively extracted from the given image, which are then integrated by constructing a unified Gestalt graph. A new algorithm named personalized power iteration clustering is developed to effectively fulfill the spreading of attention information across the Gestalt graph. Intensive experiments have been carried out to demonstrate the superior performance of the proposed model in comparison to the state-of-the-art. [ABSTRACT FROM PUBLISHER]

3-D object retrieval has been a hot research topic in recent years. Within such a field, view-based approaches are attracting increasing attention because of the flexibility of data representation as well as the reported state-of-the-art performance. One of the most important issues related to view-based 3-D object retrieval is how to learn embedding features that are discriminative across classes while being compactly distributed within each class. In this paper, we analyze the difference between the two tasks of classification and retrieval, and propose a novel way to learn a view-pooling feature via a triplet network. In addition, we propose a new loss, named cube loss, which is able to sample a number of triplets equal to the cube of the samples in a batch. With the new loss, both hard-negative and hard-positive pairs can be effectively investigated. The experimental results on the ModelNet benchmark demonstrate that the proposed method achieves superior performance compared to state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Video generation is a challenging task due to the extremely high-dimensional distribution of the solution space. Good constraints in the solution domain would thus reduce the difficulty of approximating optimal solutions. In this paper, instead of directly generating high-dimensional video data, we propose using object landmarks as explicit structure constraints to address this issue. Specifically, we propose a two-stage framework for an action-conditioned video generation task. In our framework, the first stage aims to generate landmark sequences according to predefined motion types, and a recurrent model (RNN/LSTM) is adopted for this purpose. The landmark sequence can be regarded as a low-dimensional structure embedding of high-dimensional video data, and generating landmark sequences is much easier than generating videos. The second stage is inspired by a conditional generative adversarial network (CGAN), and we take the generated landmark sequence as a structure condition to learn a landmark-to-image translation network. Such a one-to-one translation framework avoids the difficulty of generating videos and instead transfers the video generation task to image generation, which is resolvable due to the maturity of current GAN-based models. The experimental results demonstrate that our model not only achieves promising results on rigid/nonrigid motion generation tasks but also can be extended to multiobject motion situations. [ABSTRACT FROM AUTHOR]

Shape representation for 3-D models is an important topic in computer vision, multimedia analysis, and computer graphics. Recent multiview-based methods demonstrate promising performance for 3-D shape recognition and retrieval. However, most multiview-based methods ignore the correlations of multiple views or suffer from high computional cost. In this paper, we propose a novel multiview-based network architecture for 3-D shape recognition and retrieval. Our network combines convolutional neural networks (CNNs) with long short-term memory (LSTM) to exploit the correlative information from multiple views. Well-pretrained CNNs with residual connections are first used to extract a low-level feature of each view image rendered from a 3-D shape. Then, a LSTM and a sequence voting layer are employed to aggregate these features into a shape descriptor. The highway network and a three-step training strategy are also adopted to boost the optimization of the deep network. Experimental results on two public datasets demonstrate that the proposed method achieves promising performance for 3-D shape recognition and the state-of-the-art performance for the 3-D shape retrieval. [ABSTRACT FROM AUTHOR]

Saliency integration has attracted much attention on unifying saliency maps from multiple saliency models. Previous offline integration methods usually face two challenges: 1) if most of the candidate saliency models misjudge the saliency on an image, the integration result will lean heavily on those inferior candidate models; and 2) an unawareness of the ground truth saliency labels brings difficulty in estimating the expertise of each candidate model. To address these problems, in this paper, we propose an arbitrator model (AM) for saliency integration. First, we incorporate the consensus of multiple saliency models and the external knowledge into a reference map to effectively rectify the misleading by candidate models. Second, our quest for ways of estimating the expertise of the saliency models without ground truth labels gives rise to two distinct online model-expertise estimation methods. Finally, we derive a Bayesian integration framework to reconcile the saliency models of varying expertise and the reference map. To extensively evaluate the proposed AM model, we test 27 state-of-the-art saliency models, covering both traditional and deep learning ones, on various combinations over four datasets. The evaluation results show that the AM model improves the performance substantially compared to the existing state-of-the-art integration methods, regardless of the chosen candidate saliency models. [ABSTRACT FROM AUTHOR]

Semantically-rich photos contain a rich variety of semantic objects (e.g., pedestrians and bicycles). Retargeting these photos is a challenging task since each semantic object has fixed geometric characteristics. Shrinking these objects simultaneously during retargeting is prone to distortion. In this paper, we propose to retarget semantically-rich photos by detecting photo semantics from image tags, which are predicted by a multi-label SVM. The key technique is a generative model termed latent stability discovery (LSD). It can robustly localize various semantic objects in a photo by making use of the predicted noisy image tags. Based on LSD, a feature fusion algorithm is proposed to detect salient regions at both the low-level and high-level. These salient regions are linked into a path sequentially to simulate human visual perception . Finally, we learn the prior distribution of such paths from aesthetically pleasing training photos. The prior enforces the path of a retargeted photo to be maximally similar to those from the training photos. In the experiment, we collect 217 1600 \times 1200 photos, each containing over seven salient objects. Comprehensive user studies demonstrate the competitiveness of our method. [ABSTRACT FROM PUBLISHER]

Appearance change of moving targets is a challenging problem in visual tracking. In this paper, we present a novel visual object tracking algorithm based on the observation dependent hidden Markov model (OD-HMM) framework. The observation dependency is computed by structure complexity coefficients (SCC) which is defined to predict the target appearance change. Unlike conventional methods addressing the appearance change problem by investigating different online appearance models, we handle this problem by addressing the fundamental reason of motion -related appearance change during visual tracking. Based on the analysis of motion-related appearance change, we investigate the relationship between the structure of the object surface and the appearance stability. The appearance of complex structural regions is easier to change compared with that of smooth structural regions with object moving. Based on this, we define SCC to predict the appearance stability of moving objects. Different from the standard HMM-based tracking algorithms where observations between different frames are assumed to be independent, we consider the observation dependency between consecutive frames with the information provided by SCC. Moreover , we present a novel outlier removing method in appearance model updating which helps to avoid error accumulation. Experimental results on challenging video sequences demonstrate that the proposed visual tracking algorithm with OD-HMM and SCC achieves better performance than existing related tracking algorithms. [ABSTRACT FROM PUBLISHER]

Attribute-based image representation, which represents an image by projecting it into a space spanned by attributes, has attracted increasing attention from both computer vision and multimedia communities for its compactness and potential to bridge the semantic gap. While many works focus on learning attribute models and utilizing them in image recognition and retrieval, few touch on the problem of how to effectively construct a vocabulary of attributes, which is an essential part of effective attribute-based representation. Most existing approaches define the attribute vocabulary by human experts or through existing ontology, which is often limited in coverage of general concept space. In this paper, we propose automatically constructing the attribute vocabulary by mining latent topics from the click-through log of a commercial image search engine. These attributes are referred to as latent topic attributes (LTA), which take advantage of tens of millions of interactions between user submitted queries and images, thereby providing better coverage for the concept space than existing approaches. The mining of latent topics from the click log is formulated as a matrix factorization problem, and further improved by weighted terms-based matrix factorization to address the extreme sparsity of the click-through matrix. Both qualitative results of the mined LTA and quantitative results on the standard image recognition benchmark demonstrate the mined LTA’s effectiveness. [ABSTRACT FROM PUBLISHER]

This paper presents a computational study of head motion in human interaction, notably of its role in conveying interlocutors’ behavioral characteristics. Head motion is physically complex and carries rich information; current modeling approaches based on visual signals, however , are still limited in their ability to adequately capture these important properties. Guided by the methodology of kinesics , we propose a data-driven approach to identify typical head motion patterns. The approach follows the steps of first segmenting motion events, then parametrically representing the motion by linear predictive features, and finally generalizing the motion types using Gaussian mixture models. The proposed approach is experimentally validated using video recordings of communication sessions from real couples involved in a couples therapy study. In particular we use the head motion model to classify binarized expert judgments of the interactants’ specific behavioral characteristics where entrainment in head motion is hypothesized to play a role: Acceptance, Blame, Positive, and Negative behavior. We achieve accuracies in the range of 60% to 70% for the various experimental settings and conditions. In addition, we describe a measure of motion similarity between the interaction partners based on the proposed model. We show that the relative change of head motion similarity during the interaction significantly correlates with the expert judgments of the interactants’ behavioral characteristics. These findings demonstrate the effectiveness of the proposed head motion model, and underscore the promise of analyzing human behavioral characteristics through signal processing methods. [ABSTRACT FROM PUBLISHER]

As the large online repositories of image and video data has emerged and continued to grow in number, the visual variations in such repositories has also increased dramatically. For example, the visual scene of a photograph can be changed into different colors by image editing tools or depicted by multiple representations, such as a painting and a hand-drawn sketch. The large visual variations tend to cause ambiguities for the existing computer vision algorithms to recognize the visual analogies of these images and often limit the potential of related applications. In this paper, therefore, we propose a new approach for detecting reliable visual features from images, with a particular focus on improving the repeatability of the local features in those images containing the same semantic contents (e.g., a landmark) but in different visual styles (e.g., a photo and a painting). We proposed a novel method for establishing visual correspondences between images based on the Gestalt theory, a psychological study of how human visions organize the visual perception. Experiments demonstrated the outperformance of our approach over the state-of-the-art local features in various computer vision tasks, such as cross domain image matching and retrieval. [ABSTRACT FROM PUBLISHER]

Singing is a popular social activity and a pleasant way of expressing one’s feelings. One important reason for unsuccessful singing performance is because the singer fails to choose a suitable song. In this paper, we propose a novel competence-based song recommendation framework for the purpose of singing. It is distinguished from most existing music recommendation systems which rely on the computation of listeners’ interests or similarity. We model a singer’s vocal competence as a singer profile, which takes voice pitch, intensity, and quality into consideration. Then we propose techniques to acquire singer profiles. We also present a song profile model which is used to construct a human annotated song database. Then we propose a learning-to-rank scheme for recommending songs by a singer profile. Finally, we introduce a reduced singer profile which can greatly simplify the vocal competence modelling process. The experimental study on real singers demonstrates the effectiveness of our approach and its advantages over two baseline methods. [ABSTRACT FROM PUBLISHER]