ICCV 2015 论文列表

A limitation in color constancy research is the inability to establish ground truth colors for evaluating corrected images. Many existing datasets contain images of scenes with a color chart included; however, only the chart's neutral colors (grayscale patches) are used to provide the ground truth for illumination estimation and correction. This is because the corrected neutral colors are known to lie along the achromatic line in the camera's color space (i.e. R=G=B) ; the correct RGB values of the other color patches are not known. As a result, most methods estimate a 3*3 diagonal matrix that ensures only the neutral colors are correct. In this paper, we describe how to overcome this limitation. Specifically, we show that under certain illuminations, a diagonal 3*3 matrix is capable of correcting not only neutral colors, but all the colors in a scene. This finding allows us to find the ground truth RGB values for the color chart in the camera's color space. We show how to use this information to correct all the images in existing datasets to have correct colors. Working from these new color corrected datasets, we describe how to modify existing color constancy algorithms to perform better image correction.

Occlusion is a main challenge for human pose estimation, which is largely ignored in popular tree structure models. The tree structure model is simple and convenient for exact inference, but short in modeling the occlusion coherence especially in the case of self-occlusion. We propose an occlusion aware graphical model which is able to model both self-occlusion and occlusion by the other objects simultaneously. The proposed model structure can encode the interactions between human body parts and objects, and hence enable it to learn occlusion coherence from data discriminatively. We evaluate our model on several public benchmarks for human pose estimation including challenging subsets featuring significant occlusion. The experimental results show that our method obtains comparable accuracy with the state-of-the-arts, and achieves promising performance in 2D human pose estimation with occlusion.

State-of-the-art image-set matching techniques typically implicitly model each image-set with a Gaussian distribution. Here, we propose to go beyond these representations and model image-sets as probability distribution functions (PDFs) using kernel density estimators. To compare and match image-sets, we exploit Csiszar f-divergences, which bear strong connections to the geodesic distance defined on the space of PDFs, i.e., the statistical manifold. Furthermore, we introduce valid positive definite kernels on the statistical manifolds, which let us make use of more powerful classification schemes to match image-sets. Finally, we introduce a supervised dimensionality reduction technique that learns a latent space where f-divergences reflect the class labels of the data. Our experiments on diverse problems, such as video-based face recognition and dynamic texture classification, evidence the benefits of our approach over the state-of-the-art image-set matching methods.

Covariance matrix has recently received increasing attention in computer vision by leveraging Riemannian geometry of symmetric positive-definite (SPD) matrices. Originally proposed as a region descriptor, it has now been used as a generic representation in various recognition tasks. However, covariance matrix has shortcomings such as being prone to be singular, limited capability in modeling complicated feature relationship, and having a fixed form of representation. This paper argues that more appropriate SPD-matrix-based representations shall be explored to achieve better recognition. It proposes an open framework to use the kernel matrix over feature dimensions as a generic representation and discusses its properties and advantages. The proposed framework significantly elevates covariance representation to the unlimited opportunities provided by this new representation. Experimental study shows that this representation consistently outperforms its covariance counterpart on various visual recognition tasks. In particular, it achieves significant improvement on skeleton-based human action recognition, demonstrating the state-of-the-art performance over both the covariance and the existing non-covariance representations.

We propose a novel approach to human action recognition, with motion capture data (MoCap), based on grouping sub-body parts. By representing configurations of actions as manifolds, joint positions are mapped on a subspace via principal geodesic analysis. The reduced space is still highly informative and allows for classification based on a non-parametric Bayesian approach, generating behaviors for each sub-body part. Having partitioned the set of joints, poses relative to a sub-body part are exchangeable, given a specified prior and can elicit, in principle, infinite behaviors. The generation of these behaviors is specified by a Dirichlet process mixture. We show with several experiments that the recognition gives very promising results, outperforming methods requiring temporal alignment.

The problem of transfer learning is considered in the domain of crowd counting. A solution based on Bayesian model adaptation of Gaussian processes is proposed. This is shown to produce intuitive model updates, which are tractable, and lead to an adapted model (predictive distribution) that accounts for all information in both training and adaptation data. The new adaptation procedure achieves significant gains over previous approaches, based on multi-task learning, while requiring much less computation to deploy. This makes it particularly suited for the problem of expanding the capacity of crowd counting camera networks. A large video dataset for the evaluation of adaptation approaches to crowd counting is also introduced. This contains a number of adaptation tasks, involving information transfer across video collected by 1) a single camera under different scene conditions (different times of the day) and 2) video collected from different cameras. Evaluation of the proposed model adaptation procedure in this dataset shows good performance in realistic operating conditions.

We present an automatic thumbnail generation technique based on two essential considerations: how well they visually represent the original photograph, and how well the foreground can be recognized after the cropping and downsizing steps of thumbnailing. These factors, while important for the image indexing purpose of thumbnails, have largely been ignored in previous methods, which instead are designed to highlight salient content while disregarding the effects of downsizing. We propose a set of image features for modeling these two considerations of thumbnails, and learn how to balance their relative effects on thumbnail generation through training on image pairs composed of photographs and their corresponding thumbnails created by an expert photographer. Experiments show the effectiveness of this approach on a variety of images, as well as its advantages over related techniques.

Humans connect language and vision to perceive the world. How to build a similar connection for computers? One possible way is via visual concepts, which are text terms that relate to visually discriminative entities. We propose an automatic visual concept discovery algorithm using parallel text and visual corpora; it filters text terms based on the visual discriminative power of the associated images, and groups them into concepts using visual and semantic similarities. We illustrate the applications of the discovered concepts using bidirectional image and sentence retrieval task and image tagging task, and show that the discovered concepts not only outperform several large sets of manually selected concepts significantly, but also achieves the state-of-the-art performance in the retrieval task.

The human face is a primary medium of human communication and a prominent source of information used to infer various attributes. In this paper, we study a fully automated system that can infer the perceived traits of a person from his face -- social dimensions, such as "intelligence," "honesty," and "competence" -- and how those traits can be used to predict the outcomes of real-world social events that involve long-term commitments, such as political elections, job hires, and marriage engagements. To this end, we propose a hierarchical model for enduring traits inferred from faces, incorporating high-level perceptions and intermediate-level attributes. We show that our trained model can successfully classify the outcomes of two important political events, only using the photographs of politicians' faces. Firstly, it classifies the winners of a series of recent U.S. elections with the accuracy of 67.9% (Governors) and 65.5% (Senators). We also reveal that the different political offices require different types of preferred traits. Secondly, our model can categorize the political party affiliations of politicians, i.e., Democrats vs. Republicans, with the accuracy of 62.6% (male) and 60.1% (female). To the best of our knowledge, our paper is the first to use automated visual trait analysis to predict the outcomes of real-world social events. This approach is more scalable and objective than the prior behavioral studies, and opens for a range of new applications.

We propose a new method for fine-grained object recognition that employs part-level annotations and deep convolutional neural networks (CNNs) in a unified framework. Although both schemes have been widely used to boost recognition performance, due to the difficulty in acquiring detailed part annotations, strongly supervised fine-grained datasets are usually too small to keep pace with the rapid evolution of CNN architectures. In this paper, we solve this problem by exploiting inexhaustible web data. The proposed method improves classification accuracy in two ways: more discriminative CNN feature representations are generated using a training set augmented by collecting a large number of part patches from weakly supervised web images; and more robust object classifiers are learned using a multi-instance learning algorithm jointly on the strong and weak datasets. Despite its simplicity, the proposed method delivers a remarkable performance improvement on the CUB200-2011 dataset compared to baseline part-based R-CNN methods, and achieves the highest accuracy on this dataset even in the absence of test image annotations.

In this paper, we are interested in developing compositional models to explicit representing pose, parts and attributes and tackling the tasks of attribute recognition, pose estimation and part localization jointly. This is different from the recent trend of using CNN-based approaches for training and testing on these tasks separately with a large amount of data. Conventional attribute models typically use a large number of region-based attribute classifiers on parts of pre-trained pose estimator without explicitly detecting the object or its parts, or considering the correlations between attributes. In contrast, our approach jointly represents both the object parts and their semantic attributes within a unified compositional hierarchy. We apply our attributed grammar model to the task of human parsing by simultaneously performing part localization and attribute recognition. We show our modeling helps performance improvements on pose-estimation task and also outperforms on other existing methods on attribute prediction task.

We propose a novel image representation, termed Attribute-Graph, to rank images by their semantic similarity to a given query image. An Attribute-Graph is an undirected fully connected graph, incorporating both local and global image characteristics. The graph nodes characterise objects as well as the overall scene context using mid-level semantic attributes, while the edges capture the object topology. We demonstrate the effectiveness of Attribute-Graphs by applying them to the problem of image ranking. We benchmark the performance of our algorithm on the 'rPascal' and 'rImageNet' datasets, which we have created in order to evaluate the ranking performance on complex queries containing multiple objects. Our experimental evaluation shows that modelling images as Attribute-Graphs results in improved ranking performance over existing techniques.

We present a novel detection method using a deep convolutional neural network (CNN), named AttentionNet. We cast an object detection problem as an iterative classification problem, which is the most suitable form of a CNN. AttentionNet provides quantized weak directions pointing a target object and the ensemble of iterative predictions from AttentionNet converges to an accurate object boundary box. Since AttentionNet is a unified network for object detection, it detects objects without any separated models from the object proposal to the post bounding-box regression. We evaluate AttentionNet by a human detection task and achieve the state-of-the-art performance of 65% (AP) on PASCAL VOC 2007/2012 with an 8-layered architecture only.

The objective of Shape-from-Template (SfT) is to infer an object's shape from a single image and a 3D object tem- plate. Existing methods are called thin-shell SfT as they represent the object by its outer surface. This may be an open surface for thin objects such as a piece of paper or a closed surface for thicker objects such as a ball. We pro- pose volumetric SfT, which specifically handles objects of the latter kind. Volumetric SfT uses the object's full volume to express the deformation constraints and reconstructs the object's surface and interior deformation. This is a chal- lenging problem because for opaque objects, only a part of the outer surface is visible in the image. Inspired by mesh- editing techniques, we use an As-Rigid-As-Possible (ARAP) deformation model that softly imposes local rigidity. We formalise ARAP isometric SfT as a constrained variational optimisation problem which we solve using iterative opti- misation. We present strategies to find an initial solution based on thin-shell SfT and volume propagation. Experi- ments with synthetic and real data show that our method has a typical maximum relative error of 5% in reconstruct- ing the deformation of an entire object, including its back and interior for which no visual data is available.

The pervasiveness of massive data repositories has led to much interest in efficient methods for indexing, search, and retrieval. For image data, a rapidly developing body of work for these applications shows impressive performance with methods that broadly fall under the umbrella term of Binary Hashing. Given a distance matrix, a binary hashing algorithm solves for a binary code for the given set of examples, whose Hamming distance nicely approximates the original distances. The formulation is non-convex-- so existing solutions adopt spectral relaxations or perform coordinate descent (or quantization) on a surrogate objective that is numerically more tractable. In this paper, we first derive an Augmented Lagrangian approach to optimize the standard binary Hashing objective (i.e.,maintain fidelity with a given distance matrix). With appropriate step sizes, we find that this scheme already yields results that match or substantially outperform state of the art methods on most benchmarks used in the literature. Then, to allow the model to scale to large datasets, we obtain an interesting reformulation of the binary hashing objective as a non negative matrix factorization. Later, this leads to a simple multiplicative updates algorithm -- whose parallelization properties are exploited to obtain a fast GPU based implementation. We give a probabilistic analysis of our initialization scheme and present a range of experiments to show that the method is simple to implement and competes favorably with available methods (both for optimization and generalization).

Detecting highly articulated objects such as humans is a challenging problem. This paper proposes a novel part-based model built upon poselets, a notion of parts, and Markov Random Field (MRF) for modelling the human body structure under the variation of human poses and viewpoints. The problem of human detection is then formulated as maximum a posteriori (MAP) estimation in the MRF model. Variational mean field method, a robust statistical inference, is adopted to approximate the MAP estimation. The proposed method was evaluated and compared with existing methods on different test sets including H3D and PASCAL VOC 2007-2009. Experimental results have favourbly shown the robustness of the proposed method in comparison to the state-of-the-art.

We explore the redundancy of parameters in deep neural networks by replacing the conventional linear projection in fully-connected layers with the circulant projection. The circulant structure substantially reduces memory footprint and enables the use of the Fast Fourier Transform to speed up the computation. Considering a fully-connected neural network layer with d input nodes, and d output nodes, this method improves the time complexity from O(d^2) to O(dlogd) and space complexity from O(d^2) to O(d). The space savings are particularly important for modern deep convolutional neural network architectures, where fully-connected layers typically contain more than 90% of the network parameters. We further show that the gradient computation and optimization of the circulant projections can be performed very efficiently. Our experiments on three standard datasets show that the proposed approach achieves this significant gain in storage and efficiency with minimal increase in error rate compared to neural networks with unstructured projections.

In this paper, we address the problem of estimating noise level from a single image contaminated by additive zero-mean Gaussian noise. We first provide rigorous analysis on the statistical relationship between the noise variance and the eigenvalues of the covariance matrix of patches within an image, which shows that many state-of-the-art noise estimation methods underestimate the noise level of an image. To this end, we derive a new nonparametric algorithm for efficient noise level estimation based on the observation that patches decomposed from a clean image often lie around a low-dimensional subspace. The performance of our method has been guaranteed both theoretically and empirically. Specifically, our method outperforms existing state-of-the-art algorithms on estimating noise level with the least executing time in our experiments. We further demonstrate that the denoising algorithm BM3D algorithm achieves optimal performance using noise variance estimated by our algorithm.

We propose an efficient method for estimating the motion of a multi-camera rig from a minimal set of feature correspondences. Existing methods for solving the multi-camera relative pose problem require extra correspondences, are slow to compute, and/or produce a multitude of solutions. Our solution uses a first-order approximation to relative pose in order to simplify the problem and produce an accurate estimate quickly. The solver is applicable to sequential multi-camera motion estimation and is fast enough for real-time implementation in a random sampling framework. Our experiments show that our approach is both stable and efficient on challenging test sequences.