ICCV 2015 Papers

We address the problem of statistical learning of shape models which are invariant to translation, rotation and scale in compositional hierarchies when data spaces of measurements and shape spaces are not topological manifolds. In practice, this problem is observed while modeling shapes having multiple disconnected components, e.g. partially occluded shapes in cluttered scenes. We resolve the aforementioned problem by first reformulating the relationship between data and shape spaces considering the interaction between Receptive Fields (RFs) and Shape Manifolds (SMs) in a compositional hierarchical shape vocabulary. Then, we suggest a method to model the topological structure of the SMs for statistical learning of the geometric transformations of the shapes that are defined by group actions on the SMs. For this purpose, we design a disjoint union topology using an indexing mechanism for the formation of shape models on SMs in the vocabulary, recursively. We represent the topological relationship between shape components using graphs, which are aggregated to construct a hierarchical graph structure for the shape vocabulary. To this end, we introduce a framework to implement the indexing mechanisms for the employment of the vocabulary for structural shape classification. The proposed approach is used to construct invariant shape representations. Results on benchmark shape classification outperform state-of-the-art methods.

We introduce a novel framework for modeling articulated objects based on the aspects of their components. By decomposing the object into components, we divide the problem in smaller modeling tasks. After obtaining 3D models for each component aspect by employing a shape deformation paradigm, we merge them together, forming the object components. The final model is obtained by assembling the components using an optimization scheme which fits the respective 3D models to the corresponding apparent contours in a reference pose. The results suggest that our approach can produce realistic 3D models of articulated objects in reasonable time.

In this paper, we present a novel multi-image motion deblurring method utilizing the coded exposure technique. The key idea of our work is to capture video frames with a set of complementary fluttering patterns to preserve spatial frequency details. We introduce an algorithm for generating a complementary set of binary sequences based on the modern communication theory and implement the coded exposure video system with an off-the-shelf machine vision camera. The effectiveness of our method is demonstrated on various challenging examples with quantitative and qualitative comparisons to other computational image capturing methods used for image deblurring.

Generating captions to describe images is a fundamental problem that combines computer vision and natural language processing. Recent works focus on descriptive phrases, such as "a white dog" to explain the visual composites of an input image. The phrases can not only express objects, attributes, events, and their relations but can also reduce visual complexity. A caption for an input image can be generated by connecting estimated phrases using a grammar model. However, because phrases are combinations of various words, the number of phrases is much larger than the number of single words. Consequently, the accuracy of phrase estimation suffers from too few training samples per phrase. In this paper, we propose a novel phrase-learning method: Common Subspace for Model and Similarity (CoSMoS). In order to overcome the shortage of training samples, CoSMoS obtains a subspace in which (a) all feature vectors associated with the same phrase are mapped as mutually close, (b) classifiers for each phrase are learned, and (c) training samples are shared among co-occurring phrases. Experimental results demonstrate that our system is more accurate than those in earlier work and that the accuracy increases when the dataset from the web increases.

Wearable cameras, such as Google Glass and Go Pro, enable video data collection over larger areas and from different views. In this paper, we tackle a new problem of locating the co-interest person (CIP), i.e., the one who draws attention from most camera wearers, from temporally synchronized videos taken by multiple wearable cameras. Our basic idea is to exploit the motion patterns of people and use them to correlate the persons across different videos, instead of performing appearance-based matching as in traditional video co-segmentation/localization. This way, we can identify CIP even if a group of people with similar appearance are present in the view. More specifically, we detect a set of persons on each frame as the candidates of the CIP and then build a Conditional Random Field (CRF) model to select the one with consistent motion patterns in different videos and high spacial-temporal consistency in each video. We collect three sets of wearable-camera videos for testing the proposed algorithm. All the involved people have similar appearances in the collected videos and the experiments demonstrate the effectiveness of the proposed algorithm.

We propose a cluster-based approach to point set saliency detection, a challenge since point sets lack topological information. A point set is first decomposed into small clusters, using fuzzy clustering. We evaluate cluster uniqueness and spatial distribution of each cluster and combine these values into a cluster saliency function. Finally, the probabilities of points belonging to each cluster are used to assign a saliency to each point. Our approach detects fine-scale salient features and uninteresting regions consistently have lower saliency values. We evaluate the proposed saliency model by testing our saliency-based keypoint detection against a 3D interest point detection benchmark. The evaluation shows that our method achieves a good balance between false positive and false negative error rates, without using any topological information.

Multidimensional-scaling (MDS) is an information analysis tool. It involves the evaluation of distances between data points, which is a quadratic space-time problem. Then, MDS procedures find an embedding of the points in a low dimensional Euclidean (flat) domain, optimizing for the similarity of inter-points distances. We present an efficient solver for Classical Scaling (a specific MDS model) by extending the distances measured from a subset of the points to the rest, while exploiting the smoothness property of the distance functions. The smoothness is measured by the L2 norm of the Laplace-Beltrami operator applied to the unknown distance function. The Laplace Beltrami reflects the local differential relations between points, and can be computed in linear time. Classical-scaling is thereby reformulated into a quasi-linear space-time complexities procedure.

In image deblurring, a fundamental problem is that the blur kernel suppresses a number of spatial frequencies that are difficult to recover reliably. In this paper, we explore the potential of a class-specific image prior for recovering spatial frequencies attenuated by the blurring process. Specifically, we devise a prior based on the class-specific subspace of image intensity responses to band-pass filters. We learn that the aggregation of these subspaces across all frequency bands serves as a good class-specific prior for the restoration of frequencies that cannot be recovered with generic image priors. In an extensive validation, our method, equipped with the above prior, yields greater image quality than many state-of-the-art methods by up to 5 dB in terms of image PSNR, across various image categories including portraits, cars, cats, pedestrians and household objects.

Existing human action recognition systems for 3D sequences obtained from the depth camera are designed to cope with only one action category, either single-person action or two-person interaction, and are difficult to be extended to scenarios where both action categories co-exist. In this paper, we propose the category-blind human recognition method (CHARM) which can recognize a human action without making assumptions of the action category. In our CHARM approach, we represent a human action (either a single-person action or a two-person interaction) class using a co-occurrence of motion primitives. Subsequently, we classify an action instance based on matching its motion primitive co-occurrence patterns to each class representation. The matching task is formulated as maximum clique problems. We conduct extensive evaluations of CHARM using three datasets for single-person actions, two-person interactions, and their mixtures. Experimental results show that CHARM performs favorably when compared with several state-of-the-art single-person action and two-person interaction based methods without making explicit assumptions of action category.

A novel efficient method for extraction of object proposals is introduced. Its "objectness" function exploits deep spatial pyramid features, a novel fast-to-compute HoG-based edge statistic and the EdgeBoxes score. The efficiency is achieved by the use of spatial bins in a novel combination with sparsity-inducing group normalized SVM. State-of-the-art recall performance is achieved on Pascal VOC07, significantly outperforming methods with comparable speed. Interestingly, when only 100 proposals per image are considered the method attains 78 % recall on VOC07. The method improves mAP of the RCNN class-specific detector, increasing it by 10 points when only 50 proposals are used in each image. The system trained on twenty classes performs well on the two hundred class ILSVRC2013 set confirming generalization capability.

Advanced Driver Assistance Systems (ADAS) have made driving safer over the last decade. They prepare vehicles for unsafe road conditions and alert drivers if they perform a dangerous maneuver. However, many accidents are unavoidable because by the time drivers are alerted, it is already too late. Anticipating maneuvers beforehand can alert drivers before they perform the maneuver and also give ADAS more time to avoid or prepare for the danger. In this work we anticipate driving maneuvers a few seconds before they occur. For this purpose we equip a car with cameras and a computing device to capture the driving context from both inside and outside of the car. We propose an Autoregressive Input-Output HMM to model the contextual information alongwith the maneuvers. We evaluate our approach on a diverse data set with 1180 miles of natural freeway and city driving and show that we can anticipate maneuvers 3.5 seconds before they occur with over 80% F1-score in real-time.

This paper presents a patch-based approach for crowd density estimation in public scenes. We formulate the problem of estimating density in a structured learning framework applied to random decision forests. Our approach learns the mapping between patch features and relative locations of all objects inside each patch, which contribute to generate the patch density map through Gaussian kernel density estimation. We build the forest in a coarse-to-fine manner with two split node layers, and further propose a crowdedness prior and an effective forest reduction method to improve the estimation accuracy and speed. Moreover, we introduce a semi-automatic training method to learn the estimator for a specific scene. We achieved state-of-the-art results on the public Mall dataset and UCSD dataset, and also proposed two potential applications in traffic counts and scene understanding with promising results.

Satellite imagery of cloud cover is extremely important for understanding and predicting weather. We demonstrate how this imagery can be constructed "from the ground up" without requiring expensive geo-stationary satellites. This is accomplished through a novel approach to approximate continental-scale cloud maps using only ground-level imagery from publicly-available webcams. We collected a year's worth of satellite data and simultaneously-captured, geo-located outdoor webcam images from 4388 sparsely distributed cameras across the continental USA. The satellite data is used to train a dynamic model of cloud motion alongside 4388 regression models (one for each camera) to relate ground-level webcam data to the satellite data at the camera's location. This novel application of large-scale computer vision to meteorology and remote sensing is enabled by a smoothed, hierarchically-regularized dynamic texture model whose system dynamics are driven to remain consistent with measurements from the geo-located webcams. We show that our hierarchical model is better able to incorporate sparse webcam measurements resulting in more accurate cloud maps in comparison to a standard dynamic textures implementation. Finally, we demonstrate that our model can be successfully applied to other natural image sequences from the DynTex database, suggesting a broader applicability of our method.

We propose a new method for turning an Internet-scale corpus of categorized images into a small set of human-interpretable discriminative visual elements using powerful tools based on deep learning. A key challenge with deep learning methods is generating human-interpretable models. To address this, we propose a new technique that uses bubble images -- images where most of the content has been obscured -- to identify spatially localized, discriminative content in each image. By modifying the model training procedure to use both the source imagery and these bubble images, we can arrive at final models which retain much of the original classification performance, but are much more amenable to identifying interpretable visual elements. We apply our algorithm to a wide variety of datasets, including two new Internet-scale datasets of people and places, and show applications to visual mining and discovery. Our method is simple, scalable, and produces visual elements that are highly representative compared to prior work.

Recent leading approaches to semantic segmentation rely on deep convolutional networks trained with human-annotated, pixel-level segmentation masks. Such pixel-accurate supervision demands expensive labeling effort and limits the performance of deep networks that usually benefit from more training data. In this paper, we propose a method that achieves competitive accuracy but only requires easily obtained bounding box annotations. The basic idea is to iterate between automatically generating region proposals and training convolutional networks. These two steps gradually recover segmentation masks for improving the networks, and vise versa. Our method, called "BoxSup", produces competitive results (e.g., 62.0% mAP for validation) supervised by boxes only, on par with strong baselines (e.g., 63.8% mAP) fully supervised by masks under the same setting. By leveraging a large amount of bounding boxes, BoxSup further yields state-of-the-art results on PASCAL VOC 2012 and PASCAL-CONTEXT.

Regions-with-convolutional-neural-network (RCNN) is now a commonly employed object detection pipeline. Its main steps, i.e., proposal generation and convolutional neural network (CNN) feature extraction, have been intensively investigated. We focus on the last step of the system to aggregate thousands of scored box proposals into final object prediction, which we call proposal decimation. We show this step can be enhanced with a very simple box aggregation function by considering statistical properties of proposals with respect to ground truth objects. Our method is with extremely light-weight computation, while it yields an improvement of 3.7% in mAP on PASCAL VOC 2007 test. We explain why it works using some statistics in this paper.

Computer vision in general, and object proposals in particular, are nowadays strongly influenced by the databases on which researchers evaluate the performance of their algorithms. This paper studies the transition from the Pascal Visual Object Challenge dataset, which has been the benchmark of reference for the last years, to the updated, bigger, and more challenging Microsoft Common Objects in Context. We first review and deeply analyze the new challenges, and opportunities, that this database presents. We then survey the current state of the art in object proposals and evaluate it focusing on how it generalizes to the new dataset. In sight of these results, we propose various lines of research to take advantage of the new benchmark and improve the techniques. We explore one of these lines, which leads to an improvement over the state of the art of +5.2%.

3D human body shape matching has large potential on many real world applications, especially with the recent advances in the 3D range sensing technology. We address this problem by proposing a novel holistic human body shape descriptor called BodyPrint. To compute the bodyprint for a given body scan, we fit a deformable human body mesh and project the mesh parameters to a low-dimensional subspace which improves discriminability across different persons. Experiments are carried out on three real-world human body datasets to demonstrate that BodyPrint is robust to pose variation as well as missing information and sensor noise. It improves the matching accuracy significantly compared to conventional 3D shape matching techniques using local features. To facilitate practical applications where the shape database may grow over time, we also extend our learning framework to handle online updates.

Defocus blur usually causes performance degradation in establishing the visual correspondence between stereo images. We propose a blur-aware disparity estimation method that is robust to the mismatch of focus in stereo images. The relative blur resulting from the mismatch of focus between stereo images is approximated as the difference of the square diameters of the blur kernels. Based on the defocus and stereo model, we propose the relative blur versus disparity (RBD) model that characterizes the relative blur as a second-order polynomial function of disparity. Our method alternates between RBD model update and disparity update in each iteration. The RBD model in return refines the disparity estimation by updating the matching cost and aggregation weight to compensate the mismatch of focus. Experiments using both synthesized and real datasets demonstrate the effectiveness of our proposed algorithm.