CVPR 2015 论文列表

In this paper, we analyze the fashion of clothing of a large social website. Our goal is to learn and predict how fashionable a person looks on a photograph and suggest subtle improvements the user could make to improve her/his appeal. We propose a Conditional Random Field model that jointly reasons about several fashionability factors such as the type of outfit and garments the user is wearing, the type of the user, the photograph's setting (e.g., the scenery behind the user), and the fashionability score. Importantly, our model is able to give rich feedback back to the user, conveying which garments or even scenery she/he should change in order to improve fashionability. We demonstrate that our joint approach significantly outperforms a variety of intelligent baselines. We additionally collected a novel heterogeneous dataset with 144,169 user posts containing diverse image, textual and meta information which can be exploited for our task. We also provide a detailed analysis of the data, showing different outfit trends and fashionability scores across the globe and across a span of 6 years.

A nested motion descriptor is a spatiotemporal representation of motion that is invariant to global camera translation, without requiring an explicit estimate of optical flow or camera stabilization. This descriptor is a natural spatiotemporal extension of the nested shape descriptor to the representation of motion. We demonstrate that the quadrature steerable pyramid can be used to pool phase, and that pooling phase rather than magnitude provides an estimate of camera motion. This motion can be removed using the log-spiral normalization as introduced in the nested shape descriptor. Furthermore, this structure enables an elegant visualization of salient motion using the reconstruction properties of the steerable pyramid. We compare our descriptor to local motion descriptors, HOG-3D and HOG-HOF, and show improvements on three activity recognition datasets.

With the increasing interest in pedestrian detection, pedestrian datasets have also been the subject of research in the past decades. However, most existing datasets focus on a color channel, while a thermal channel is helpful for detection even in a dark environment. With this in mind, we propose a multispectral pedestrian dataset which provides well aligned color-thermal image pairs, captured by beam splitter-based special hardware. The color-thermal dataset is as large as previous color-based datasets and provides dense annotations including temporal correspondences. With this dataset, we introduce multispectral ACF, which is an extension of aggregated channel features (ACF) to simultaneously handle color-thermal image pairs. Multispectral ACF reduces the average miss rate of ACF by 15%, and achieves another breakthrough in the pedestrian detection task.

A graph-based system to simulate the movements and interactions of multiple random walkers (MRW) is proposed in this work. In the MRW system, multiple agents traverse a single graph simultaneously. To achieve desired interactions among those agents, a restart rule can be designed, which determines the restart distribution of each agent according to the probability distributions of all agents. In particular, we develop the repulsive rule for data clustering. We illustrate that the MRW clustering can segment real images reliably. Furthermore, we propose a novel image cosegmentation algorithm based on the MRW clustering. Specifically, the proposed algorithm consists of two steps: inter-image concurrence computation and intra-image MRW clustering. Experimental results demonstrate that the proposed algorithm provides promising cosegmentation performance.

A generalized formulation of the multiple instance learning problem is considered. Under this formulation, both positive and negative bags are soft, in the sense that negative bags can also contain positive instances. This reflects a problem setting commonly found in practical applications, where labeling noise appears on both positive and negative training samples. A novel bag-level representation is introduced, using instances that are most likely to be positive (denoted top instances), and its ability to separate soft bags, depending on their relative composition in terms of positive and negative instances, is studied. This study inspires a new large-margin algorithm for soft-bag classification, based on a latent support vector machine that efficiently explores the combinatorial space of bag compositions. Empirical evaluation on three datasets is shown to confirm the main findings of the theoretical analysis and the effectiveness of the proposed soft-bag classifier.

The notion of multihypothesis trajectory analysis (MTA) for robust visual tracking is proposed in this work. We employ multiple component trackers using texture, color, and illumination invariant features, respectively. Each component tracker traces a target object forwardly and then backwardly over a time interval. By analyzing the pair of the forward and backward trajectories, we measure the robustness of the component tracker. To this end, we extract the geometry similarity, the cyclic weight, and the appearance similarity from the forward and backward trajectories. We select the optimal component tracker to yield the maximum robustness score, and use its forward trajectory as the final tracking result. Experimental results show that the proposed MTA tracker improves the robustness and the accuracy of tracking, outperforming the state-of-the-art trackers on a recent benchmark dataset.

We address the problem of integrating object reasoning with supervoxel labeling in multiclass semantic video segmentation. To this end, we first propose an object-augmented dense CRF in spatio-temporal domain, which captures long-range dependency between supervoxels, and imposes consistency between object and supervoxel labels. We develop an efficient mean field inference algorithm to jointly infer the supervoxel labels, object activations and their occlusion relations for a moderate number of object proposals. To scale up our method, we adopt an active inference strategy to improve the efficiency, which adaptively selects object subgraphs in the object-augmented dense CRF. We formulate the problem as a Markov Decision Process, which learns an approximate optimal policy based on a reward of accuracy improvement and a set of well-designed model and input features. We evaluate our method on three publicly available multiclass video semantic segmentation datasets and demonstrate superior efficiency and accuracy.

We frame the problem of local representation of imaging data as the computation of minimal sufficient statistics that are invariant to nuisance variability induced by viewpoint and illumination. We show that, under very stringent conditions, these are related to "feature descriptors" commonly used in Computer Vision. Such conditions can be relaxed if multiple views of the same scene are available. We propose a sampling-based and a point-estimate based approximation of such a representation, compared empirically on image-to-(multiple)image matching, for which we introduce a multi-view wide-baseline matching benchmark, consisting of a mixture of real and synthetic objects with ground truth camera motion and dense three-dimensional geometry.

Given the tremendous growth of online videos, video thumbnail, as the common visualization form of video content, is becoming increasingly important to influence user's browsing and searching experience. However, conventional methods for video thumbnail selection often fail to produce satisfying results as they ignore the side semantic information (e.g., title, description, and query) associated with the video. As a result, the selected thumbnail cannot always represent video semantics and the click-through rate is adversely affected even when the retrieved videos are relevant. In this paper, we have developed a multi-task deep visual-semantic embedding model, which can automatically select query-dependent video thumbnails according to both visual and side information. Different from most existing methods, the proposed approach employs the deep visual-semantic embedding model to directly compute the similarity between the query and video thumbnails by mapping them into a common latent semantic space, where even unseen query-thumbnail pairs can be correctly matched. In particular, we train the embedding model by exploring the large-scale and freely accessible click-through video and image data, as well as employing a multi-task learning strategy to holistically exploit the query-thumbnail relevance from these two highly related datasets. Finally, a thumbnail is selected by fusing both the representative and query relevance scores. The evaluations on 1,000 query-thumbnail dataset labeled by 191 workers in Amazon Mechanical Turk have demonstrated the effectiveness of our proposed method.

This paper formulates face labeling as a conditional random field with unary and pairwise classifiers. We develop a novel multi-objective learning method that optimizes a single unified deep convolutional network with two distinct non-structured loss functions: one encoding the unary label likelihoods and the other encoding the pairwise label dependencies. Moreover, we regularize the network by using a nonparametric prior as new input channels in addition to the RGB image, and show that significant performance improvements can be achieved with a much smaller network size. Experiments on both the LFW and Helen datasets demonstrate state-of-the-art results of the proposed algorithm, and accurate labeling results on challenging images can be obtained by the proposed algorithm for real-world applications.

In this paper, we propose a multi-manifold deep metric learning (MMDML) method for image set classification, which aims to recognize an object of interest from a set of image instances captured from varying viewpoints or under varying illuminations. Motivated by the fact that manifold can be effectively used to model the nonlinearity of samples in each image set and deep learning has demonstrated superb capability to model the nonlinearity of samples, we propose a MMDML method to learn multiple sets of nonlinear transformations, one set for each object class, to nonlinearly map multiple sets of image instances into a shared feature subspace, under which the manifold margin of different class is maximized, so that both discriminative and class-specific information can be exploited, simultaneously. Our method achieves the state-of-the-art performance on five widely used datasets.

We present a multi-instance object segmentation algorithm to tackle occlusions. As an object is split into two parts by an occluder, it is nearly impossible to group the two separate regions into an instance by purely bottom-up schemes. To address this problem, we propose to incorporate top-down category specific reasoning and shape prediction through exemplars into an intuitive energy minimization framework. We perform extensive evaluations of our method on the challenging PASCAL VOC 2012 segmentation set. The proposed algorithm achieves favorable results on the joint detection and segmentation task against the state-of-the-art method both quantitatively and qualitatively.

In this paper, a multi-feature max-margin hierarchical Bayesian model (M3HBM) is proposed for action recognition. Different from existing methods which separate representation and classification into two steps, M3HBM jointly learns a high-level representation by combining a hierarchical generative model (HGM) and discriminative max-margin classifiers in a unified Bayesian framework. Specifically, HGM is proposed to represent actions by distributions over latent spatial temporal patterns (STPs) which are learned from multiple feature modalities and shared among different classes. For recognition, we employ Gibbs classifiers to minimize the expected loss function based on the max-margin principle and use the classifiers as regularization terms of M3HBM to perform Bayeisan estimation for classifier parameters together with the learning of STPs. In addition, multi-task learning is applied to learn the model from multiple feature modalities for different classes. For test videos, we obtain the representations by the inference process and perform action recognition by the learned Gibbs classifiers. For the learning and inference process, we derive an efficient Gibbs sampling algorithm to solve the proposed M3HBM. Extensive experiments on several datasets demonstrate both the representation power and the classification capability of our approach for action recognition.

Dense local motion features such as dense trajectories have been widely used in action recognition. For most actions, only a few local features (e.g., critical movements of the hand, arm, leg etc.) are responsible to the action label. Therefore, discovering important motion part will lead to a more discriminative and compact action representation. Inspired by the recent advance in sentence regularization for text classification, we introduce a Motion Part Regularization framework to mining discriminative semi-local groups of dense trajectories. First, motion part candidates are generated by spatio-temporal grouping of densely sampled trajectories. Then, we develop a learning objective function which encourages sparse selection for these trajectory groups in conjunction with a discriminative term. We propose an alternative optimization algorithm to efficiently solve this objective function by introducing a set of auxiliary variables. The learned trajectory group weights are further utilized for weighted bag-of-feature representation for unknown action samples. The proposed motion part regularization framework achieves the state-of-the-art performances on several action recognition benchmarks.

This paper takes a step forward in image and video coding by extending the well-known Vector of Locally Aggregated Descriptors (VLAD) onto an extensive space of curved Riemannian manifolds. We provide a comprehensive mathematical framework that formulates the aggregation problem of such manifold data into an elegant solution. In particular, we consider structured descriptors from visual data, namely Region Covariance Descriptors and linear subspaces that reside on the manifold of Symmetric Positive Definite matrices and the Grassmannian manifolds, respectively. Through rigorous experimental validation, we demonstrate the superior performance of this novel Riemannian VLAD descriptor on several visual classification tasks including video-based face recognition, dynamic scene recognition, and head pose classification.

In this paper we present a method to capture video-wide temporal information for action recognition. We postulate that a function capable of ordering the frames of a video temporally (based on the appearance) captures well the evolution of the appearance within the video. We learn such ranking functions per video via a ranking machine and use the parameters of these as a new video representation. The proposed method is easy to interpret and implement, fast to compute and effective in recognizing a wide variety of actions. We perform a large number of evaluations on datasets for generic action recognition (Hollywood2 and HMDB51), fine-grained actions (MPII- cooking activities) and gestures (Chalearn). Results show that the proposed method brings an absolute improvement of 7-10\%, while being compatible with and complementary to further improvements in appearance and local motion based methods.

Subspace models have been very successful at modeling the appearance of structured image datasets when the visual objects have been aligned in the images (e.g., faces). Even with extensions that allow for global transformations or dense warps of the image, the set of visual objects whose appearance may be modeled by such methods is limited. They are unable to account for visual objects where occlusion leads to changing visibility of different object parts (without a strict layered structure) and where a one-to-one mapping between parts is not preserved. For example bunches of bananas contain different numbers of bananas but each individual banana shares an appearance subspace. In this work we remove the image space alignment limitations of existing subspace models by conditioning the models on a shape dependent context that allows for the complex, non-linear structure of the appearance of the visual object to be captured and shared. This allows us to exploit the advantages of subspace appearance models with non-rigid, deformable objects whilst also dealing with complex occlusions and varying numbers of parts. We demonstrate the effectiveness of our new model with examples of structured inpainting and appearance transfer.

Deep Convolutional Neural Networks (DCNNs) achieve invariance to domain transformations (deformations) by using multiple 'max-pooling' (MP) layers. In this work we show that alternative methods of modeling deformations can improve the accuracy and efficiency of DCNNs. First, we introduce epitomic convolution as an alternative to the common convolution-MP cascade of DCNNs, that comes with the same computational cost but favorable learning properties. Second, we introduce a Multiple Instance Learning algorithm to accommodate global translation and scaling in image classification, yielding an efficient algorithm that trains and tests a DCNN in a consistent manner. Third we develop a DCNN sliding window detector that explicitly, but efficiently, searches over the object's position, scale, and aspect ratio. We provide competitive image classification and localization results on the ImageNet dataset and object detection results on Pascal VOC2007.

We propose a single-image super-resolution method based on the gradient reconstruction. To predict the gradient field, we collect a dictionary of gradient patterns from an external set of images. We observe that there are patches representing singular primitive structures (e.g. a single edge), and non-singular ones (e.g. a triplet of edges). Based on the fact that singular primitive patches are more invariant to the scale change (i.e. have less ambiguity across different scales), we represent the non-singular primitives as compositions of singular ones, each of which is allowed some deformation. Both the input patches and dictionary elements are decomposed to contain only singular primitives. The compositional aspect of the model makes the gradient field more reliable. The deformable aspect makes the dictionary more expressive. As shown in our experimental results, the proposed method outperforms the state-of-the-art methods.