CVPR 2017 论文列表

Retrieving 3D shapes with sketches is a challenging problem since 2D sketches and 3D shapes are from two heterogeneous domains, which results in large discrepancy between them. In this paper, we propose to learn barycenters of 2D projections of 3D shapes for sketch-based 3D shape retrieval. Specifically, we first use two deep convolutional neural networks (CNNs) to extract deep features of sketches and 2D projections of 3D shapes. For 3D shapes, we then compute the Wasserstein barycenters of deep features of multiple projections to form a barycentric representation. Finally, by constructing a metric network, a discriminative loss is formulated on the Wasserstein barycenters of 3D shapes and sketches in the deep feature space to learn discriminative and compact 3D shape and sketch features for retrieval. The proposed method is evaluated on the SHREC'13 and SHREC'14 sketch track benchmark datasets. Compared to the state-of-the-art methods, our proposed method can significantly improve the retrieval performance.

In this paper, we introduce a novel approach to regulate receptive field in deep image parsing network automatically. Unlike previous works which have stressed much importance on obtaining better receptive fields using manually selected dilated convolutional kernels, our approach uses two affine transformation layers in the network's backbone and operates on feature maps. Feature maps will be inflated/shrinked by the new layer and therefore receptive fields in following layers are changed accordingly. By end-to-end training, the whole framework is data-driven without laborious manual intervention. The proposed method is generic across dataset and different tasks. We conduct extensive experiments on both general parsing task and face parsing task as concrete examples to demonstrate the method's superior regulation ability over manual designs.

We address the problem of large scale image geo-localization where the location of an image is estimated by identifying geo-tagged reference images depicting the same place. We propose a novel model for learning image representations that integrates context-aware feature reweighting in order to effectively focus on regions that positively contribute to geo-localization. In particular, we introduce a Contextual Reweighting Network (CRN) that predicts the importance of each region in the feature map based on the image context. Our model is learned end-to-end for the image geo-localization task, and requires no annotation other than image geo-tags for training. In experimental results, the proposed approach significantly outperforms the previous state-of-the-art on the standard geo-localization benchmark datasets. We also demonstrate that our CRN discovers task-relevant contexts without any additional supervision.

We introduce a method to greatly reduce the amount of redundant annotations required when crowdsourcing annotations such as bounding boxes, parts, and class labels. For example, if two Mechanical Turkers happen to click on the same pixel location when annotating a part in a given image--an event that is very unlikely to occur by random chance--, it is a strong indication that the location is correct. A similar type of confidence can be obtained if a single Turker happened to agree with a computer vision estimate. We thus incrementally collect a variable number of worker annotations per image based on online estimates of confidence. This is done using a sequential estimation of risk over a probabilistic model that combines worker skill, image difficulty, and an incrementally trained computer vision model. We develop specialized models and algorithms for binary annotation, part keypoint annotation, and sets of bounding box annotations. We show that our method can reduce annotation time by a factor of 4-11 for binary filtering of websearch results, 2-4 for annotation of boxes of pedestrians in images, while in many cases also reducing annotation error. We will make an end-to-end version of our system publicly available.

In this paper, we propose a novel Latent Multi-view Subspace Clustering (LMSC) method, which clusters data points with latent representation and simultaneously explores underlying complementary information from multiple views. Unlike most existing single view subspace clustering methods that reconstruct data points using original features, our method seeks the underlying latent representation and simultaneously performs data reconstruction based on the learned latent representation. With the complementarity of multiple views, the latent representation could depict data themselves more comprehensively than each single view individually, accordingly makes subspace representation more accurate and robust as well. The proposed method is intuitive and can be optimized efficiently by using the Augmented Lagrangian Multiplier with Alternating Direction Minimization (ALM-ADM) algorithm. Extensive experiments on benchmark datasets have validated the effectiveness of our proposed method.

Structured output support vector machine (SVM) based tracking algorithms have shown favorable performance recently. Nonetheless, the time-consuming candidate sampling and complex optimization limit their real-time applications. In this paper, we propose a novel large margin object tracking method which absorbs the strong discriminative ability from structured output SVM and speeds up by the correlation filter algorithm significantly. Secondly, a multimodal target detection technique is proposed to improve the target localization precision and prevent model drift introduced by similar objects or background noise. Thirdly, we exploit the feedback from high-confidence tracking results to avoid the model corruption problem. We implement two versions of the proposed tracker with the representations from both conventional hand-crafted and deep convolution neural networks (CNNs) based features to validate the strong compatibility of the algorithm. The experimental results demonstrate that the proposed tracker performs superiorly against several state-of-the-art algorithms on the challenging benchmark sequences while runs at speed in excess of 80 frames per second.

Convolution Neural Network (CNN) has boosted the per- formanceofalotofcomputervisiontasks, likeimageclassi- fication [31], segmentation [25], and detection [28]. Based on the observations from [31, 32, 14], recent model design- ers prefer to employ stacking of small kernels, like 3 x 3 over large-size filters. However, in the field of semantic seg- mentation, where we need to perform dense per-pixel pre- diction, we find that large kernel plays an important role to relieve the contradictories when optimizing the classi- fication and localization tasks simultaneously. Following the design principle of large-size kernel, We propose the Global Convolutional Network to address both the classi- fication and localization issue in the semantic segmentation task. To further refine the object category boundaries, we presentBoundaryRefinementblockbasedonresidualstruc- ture. Qualitatively, our model achieves state-of-art perfor- mance on two public benchmarks and outperforms previous results on a large margin, 82.2% (vs 80.2%) on PASCAL VOC 2012 dataset and 76.9% (vs 71.8%) on Cityscapes dataset.

Behavior analysis provides a crucial non-invasive and easily accessible diagnostic tool for biomedical research. A detailed analysis of posture changes during skilled motor tasks can reveal distinct functional deficits and their restoration during recovery. Our specific scenario is based on a neuroscientific study of rodents recovering from a large sensorimotor cortex stroke and skilled forelimb grasping is being recorded. Given large amounts of unlabeled videos that are recorded during such long-term studies, we seek an approach that captures fine-grained details of posture and its change during rehabilitation without costly manual supervision. Therefore, we utilize self-supervision to automatically learn accurate posture and behavior representations for analyzing motor function. Learning our model depends on the following fundamental elements: (i) limb detection based on a fully convolutional network is ini- tialized solely using motion information, (ii) a novel self- supervised training of LSTMs using only temporal permu- tation yields a detailed representation of behavior, and (iii) back-propagation of this sequence representation also im- proves the description of individual postures. We establish a novel test dataset with expert annotations for evaluation of fine-grained behavior analysis. Moreover, we demonstrate the generality of our approach by successfully applying it to self-supervised learning of human posture on two standard benchmark datasets.

We propose an end-to-end architecture for joint 2D and 3D human pose estimation in natural images. Key to our approach is the generation and scoring of a number of pose proposals per image, which allows us to predict 2D and 3D pose of multiple people simultaneously. Hence, our approach does not require an approximate localization of the humans for initialization. Our architecture, named LCR-Net, contains 3 main components: 1) the pose proposal generator that suggests potential poses at different locations in the image; 2) a classifier that scores the different pose proposals; and 3) a regressor that refines pose proposals both in 2D and 3D. All three stages share the convolutional feature layers and are trained jointly. The final pose estimation is obtained by integrating over neighboring pose hypotheses, which is shown to improve over a standard non maximum suppression algorithm. Our approach significantly outperforms the state of the art in 3D pose estimation on Human3.6M, a controlled environment. Moreover, it shows promising results on real images for both single and multi-person subsets of the MPII 2D pose benchmark.

Porting state of the art deep learning algorithms to resource constrained compute platforms (e.g. VR, AR, wearables) is extremely challenging. We propose a fast, compact, and accurate model for convolutional neural networks that enables efficient learning and inference. We introduce LCNN, a lookup-based convolutional neural network that encodes convolutions by few lookups to a dictionary that is trained to cover the space of weights in CNNs. Training LCNN involves jointly learning a dictionary and a small set of linear combinations. The size of the dictionary naturally traces a spectrum of trade-offs between efficiency and accuracy. Our experimental results on ImageNet challenge show that LCNN can offer 3.2x speedup while achieving 55.1% top-1 accuracy using AlexNet architecture. Our fastest LCNN offers 37.6x speed up over AlexNet while maintaining 44.3% top-1 accuracy. LCNN not only offers dramatic speed ups at inference, but it also enables efficient training. In this paper, we show the benefits of LCNN in few-shot learning and few-iteration learning, two crucial aspects of on-device training of deep learning models.

The research focus of designing local patch descriptors has gradually shifted from handcrafted ones (e.g., SIFT) to learned ones. In this paper, we propose to learn high per- formance descriptor in Euclidean space via the Convolu- tional Neural Network (CNN). Our method is distinctive in four aspects: (i) We propose a progressive sampling strat- egy which enables the network to access billions of train- ing samples in a few epochs. (ii) Derived from the ba- sic concept of local patch matching problem, we empha- size the relative distance between descriptors. (iii) Extra supervision is imposed on the intermediate feature maps. (iv) Compactness of the descriptor is taken into account. The proposed network is named as L2-Net since the out- put descriptor can be matched in Euclidean space by L2 distance. L2-Net achieves state-of-the-art performance on the Brown datasets [16], Oxford dataset [18] and the new- ly proposed Hpatches dataset [11]. The good generaliza- tion ability shown by experiments indicates that L2-Net can serve as a direct substitution of the existing handcrafted de- scriptors. The pre-trained L2-Net is publicly available.

Humans possess an extraordinary ability to learn new skills and new knowledge for problem solving. Such learning ability is also required by an automatic model to deal with arbitrary, open-ended questions in the visual world. We propose a neural-based approach to acquiring task- driven information for visual question answering (VQA). Our model proposes queries to actively acquire relevant information from external auxiliary data. Supporting evidence from either human-curated or automatic sources is encoded and stored into a memory bank. We show that acquiring task-driven evidence effectively improves model performance on both the Visual7W and VQA datasets; moreover, these queries offer certain level of interpretability in our iterative QA model.

Attention-based neural encoder-decoder frameworks have been widely adopted for image captioning. Most methods force visual attention to be active for every generated word. However, the decoder likely requires little to no visual information from the image to predict non-visual words such as "the" and "of". Other words that may seem visual can often be predicted reliably just from the language model e.g., "sign" after "behind a red stop" or "phone" following "talking on a cell". In this paper, we propose a novel adaptive attention model with a visual sentinel. At each time step, our model decides whether to attend to the image (and if so, to which regions) or to the visual sentinel. The model decides whether to attend to the image and where, in order to extract meaningful information for sequential word generation. We test our method on the COCO image captioning 2015 challenge dataset and Flickr30K. Our approach sets the new state-of-the-art by a significant margin.

We introduce a geometry-driven approach for real-time 3D reconstruction of deforming surfaces from a single RGB-D stream without any templates or shape priors. To this end, we tackle the problem of non-rigid registration by level set evolution without explicit correspondence search. Given a pair of signed distance fields (SDFs) representing the shapes of interest, we estimate a dense deformation field that aligns them. It is defined as a displacement vector field of the same resolution as the SDFs and is determined iteratively via variational minimization. To ensure it generates plausible shapes, we propose a novel regularizer that imposes local rigidity by requiring the deformation to be a smooth and approximately Killing vector field, i.e. generating nearly isometric motions. Moreover, we enforce that the level set property of unity gradient magnitude is preserved over iterations. As a result, KillingFusion reliably reconstructs objects that are undergoing topological changes and fast inter-frame motion. In addition to incrementally building a model from scratch, our system can also deform complete surfaces. We demonstrate these capabilities on several public datasets and introduce our own sequences that permit both qualitative and quantitative comparison to related approaches.

Zepeda and Perez have recently demonstrated the promise of the exemplar SVM (ESVM) as a feature encoder for image retrieval. This paper extends this approach in several directions: We first show that replacing the hinge loss by the square loss in the ESVM cost function significantly reduces encoding time with negligible effect on accuracy. We call this model square-loss exemplar machine, or SLEM. We then introduce a kernelized SLEM which can be implemented efficiently through low-rank matrix decomposition, and displays improved performance. Both SLEM variants exploit the fact that the negative examples are fixed, so most of the SLEM computational complexity is relegated to an offline process independent of the positive examples. Our experiments establish the performance and computational advantages of our approach using a large array of base features and standard image retrieval datasets.

Convolutional Neural Networks (CNNs) with Bilinear Pooling, initially in their full form and later using compact representations, have yielded impressive performance gains on a wide range of visual tasks, including fine-grained visual categorization, visual question answering, face recognition, and description of texture and style. The key to their success lies in the spatially invariant modeling of pairwise (2nd order) feature interactions. In this work, we propose a general pooling framework that captures higher order interactions of features in the form of kernels. We demonstrate how to approximate kernels such as Gaussian RBF up to a given order using compact explicit feature maps in a parameter-free manner. Combined with CNNs, the composition of the kernel can be learned from data in an end-to-end fashion via error back-propagation. The proposed kernel pooling scheme is evaluated in terms of both kernel approximation error and visual recognition accuracy. Experimental evaluations demonstrate state-of-the-art performance on commonly used fine-grained recognition datasets.

Physiological signals such as heart rate can provide valuable information about an individual's state and activity. However, existing work on computer vision has not yet explored leveraging these signals to enhance egocentric video understanding. In this work, we propose a model for reasoning on multimodal data to jointly predict activities and energy expenditures. We use heart rate signals as privileged self-supervision to derive energy expenditure in a training stage. A multitask objective is used to jointly optimize the two tasks. Additionally, we introduce a dataset that contains 31 hours of egocentric video augmented with heart rate and acceleration signals. This study can lead to new applications such as a visual calorie counter.

Deep learning models such as convolutional neural network have been widely used in 3D biomedical segmentation and achieve state-of-the-art performance. However, most of them often adapt a single modality or stack multiple modalities as different input channels, which ignores the correlations among them. To leverage the multi-modalities, we propose a deep convolution encoder-decoder structure with fusion layers to incorporate different modalities of MRI data. In addition, we exploit convolutional LSTM (convLSTM) to model a sequence of 2D slices, and jointly learn the multi-modalities and convLSTM in an end-to-end manner. To avoid converging to the certain labels, we adopt a re-weighting scheme and two phase training to handle the label imbalance. Experimental results on BRATS-2015 show that our method outperforms state-of-the-art biomedical segmentation approaches.

Recent advances in deep learning have resulted in human-level performances on popular unconstrained face datasets including Labeled Faces in the Wild and YouTube Faces. To further advance research, IJB-A benchmark was recently introduced with more challenges especially in the form of extreme head poses. Registration of such faces is quite demanding and often requires laborious procedures like facial landmark localization. In this paper, we propose a Convolutional Neural Networks based data-driven approach which learns to simultaneously register and represent faces. We validate the proposed scheme on template based unconstrained face identification. Here, a template contains multiple media in the form of images and video frames. Unlike existing methods which synthesize all template media information at feature level, we propose to keep the template media intact. Instead, we represent gallery templates by their trained one-vs-rest discriminative models and then employ a Bayesian strategy which optimally fuses decisions of all medias in a query template. We demonstrate the efficacy of the proposed scheme on IJB-A, YouTube Celebrities and COX datasets where our approach achieves significant relative performance boosts of 3.6%, 21.6% and 12.8% respectively.