We propose a novel approach for solving the perceptual grouping problem in vision. Rather than focusing on local features and their consistencies in the image data, our approach aims at extracting the global impression of an image. We treat image segmentation as a graph partitioning problem and propose a novel global criterion, the normalized cut, for segmenting the graph. The normalized cut criterion measures both the total dissimilarity between the different groups as well as the total similarity within the groups. We show that an efficient computational technique based on a generalized eigenvalue problem can be used to optimize this criterion. We have applied this approach to segmenting static images, as well as motion sequences, and found the results to be very encouraging. This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Pennsylvania's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to pubs-permissions@ieee.org. By choosing to view this document, you agree to all provisions of the copyright laws protecting it. AbstractÐWe propose a novel approach for solving the perceptual grouping problem in vision. Rather than focusing on local features and their consistencies in the image data, our approach aims at extracting the global impression of an image. We treat image segmentation as a graph partitioning problem and propose a novel global criterion, the normalized cut, for segmenting the graph. The normalized cut criterion measures both the total dissimilarity between the different groups as well as the total similarity within the groups. We show that an efficient computational technique based on a generalized eigenvalue problem can be used to optimize this criterion. We have applied this approach to segmenting static images, as well as motion sequences, and found the results to be very encouraging.

Abstract. This paper provides an algorithm for partitioning grayscale images into disjoint regions of coherent brightness and texture. Natural images contain both textured and untextured regions, so the cues of contour and texture differences are exploited simultaneously. Contours are treated in the intervening contour framework, while texture is analyzed using textons. Each of these cues has a domain of applicability, so to facilitate cue combination we introduce a gating operator based on the texturedness of the neighborhood at a pixel. Having obtained a local measure of how likely two nearby pixels are to belong to the same region, we use the spectral graph theoretic framework of normalized cuts to find partitions of the image into regions of coherent texture and brightness. Experimental results on a wide range of images are shown.

No abstract

Contour detection has been a fundamental component in many image segmentation and object detection systems. Most previous work utilizes low-level features such as texture or saliency to detect contours and then use them as cues for a higher-level task such as object detection. However, we claim that recognizing objects and predicting contours are two mutually related tasks. Contrary to traditional approaches, we show that we can invert the commonly established pipeline: instead of detecting contours with low-level cues for a higher-level recognition task, we exploit objectrelated features as high-level cues for contour detection. We achieve this goal by means of a multi-scale deep network that consists of five convolutional layers and a bifurcated fully-connected sub-network. The section from the input layer to the fifth convolutional layer is fixed and directly lifted from a pre-trained network optimized over a largescale object classification task. This section of the network is applied to four different scales of the image input. These four parallel and identical streams are then attached to a bifurcated sub-network consisting of two independentlytrained branches. One branch learns to predict the contour likelihood (with a classification objective) whereas the other branch is trained to learn the fraction of human labelers agreeing about the contour presence at a given point (with a regression criterion).We show that without any feature engineering our multiscale deep learning approach achieves state-of-the-art results in contour detection.

We present FoveaBox, an accurate, flexible and completely anchor-free framework for object detection. While almost all state-of-the-art object detectors utilize the predefined anchors to enumerate possible locations, scales and aspect ratios for the search of the objects, their performance and generalization ability are also limited to the design of anchors. Instead, FoveaBox directly learns the object existing possibility and the bounding box coordinates without anchor reference. This is achieved by: (a) predicting category-sensitive semantic maps for the object existing possibility, and (b) producing category-agnostic bounding box for each position that potentially contains an object. The scales of target boxes are naturally associated with feature pyramid representations for each input image.Without bells and whistles, FoveaBox achieves state-ofthe-art single model performance of 42.1 AP on the standard COCO detection benchmark. Specially for the objects with arbitrary aspect ratios, FoveaBox brings in significant improvement compared to the anchor-based detectors. More surprisingly, when it is challenged by the stretched testing images, FoveaBox shows great robustness and generalization ability to the changed distribution of bounding box shapes. The code will be made publicly available.

The limitations of current state-of-the-art methods for single-view depth estimation and semantic segmentations are closely tied to the property of perspective geometry, that the perceived size of the objects scales inversely with the distance.In this paper, we show that we can use this property to reduce the learning of a pixel-wise depth classifier to a much simpler classifier predicting only the likelihood of a pixel being at an arbitrarily fixed canonical depth. The likelihoods for any other depths can be obtained by applying the same classifier after appropriate image manipulations. Such transformation of the problem to the canonical depth removes the training data bias towards certain depths and the effect of perspective. The approach can be straight-forwardly generalized to multiple semantic classes, improving both depth estimation and semantic segmentation performance by directly targeting the weaknesses of independent approaches. Conditioning the semantic label on the depth provides a way to align the data to their physical scale, allowing to learn a more discriminative classifier. Conditioning depth on the semantic class helps the classifier to distinguish between ambiguities of the otherwise ill-posed problem.We tested our algorithm on the KITTI road scene dataset and NYU2 indoor dataset and obtained obtained results that significantly outperform current state-of-the-art in both single-view depth and semantic segmentation domain.

BackgroundCisplatin resistance is a major challenge for advanced head and neck cancer (HNC). Understanding the underlying mechanisms and developing effective strategies against cisplatin resistance are highly desired in the clinic. However, how tumor stroma modulates HNC growth and chemoresistance is unclear.ResultsWe show that cancer-associated fibroblasts (CAFs) are intrinsically resistant to cisplatin and have an active role in regulating HNC cell survival and proliferation by delivering functional miR-196a from CAFs to tumor cells via exosomes. Exosomal miR-196a then binds novel targets, CDKN1B and ING5, to endow HNC cells with cisplatin resistance. Exosome or exosomal miR-196a depletion from CAFs functionally restored HNC cisplatin sensitivity. Importantly, we found that miR-196a packaging into CAF-derived exosomes might be mediated by heterogeneous nuclear ribonucleoprotein A1 (hnRNPA1). Moreover, we also found that high levels of plasma exosomal miR-196a are clinically correlated with poor overall survival and chemoresistance.ConclusionsThe present study finds that CAF-derived exosomal miR-196a confers cisplatin resistance in HNC by targeting CDKN1B and ING5, indicating miR-196a may serve as a promising predictor of and potential therapeutic target for cisplatin resistance in HNC.Electronic supplementary materialThe online version of this article (10.1186/s13059-018-1604-0) contains supplementary material, which is available to authorized users.

Our goal is to establish a simple baseline method for human identification based on body shape and gait. This baseline recognition method provides a lower bound against which to evaluate more complicated procedures. We present a viewpoint dependent technique based on template matching of body silhouettes. Cyclic gait analysis is performed to extract key frames from a test sequence. These frames are compared to training frames using normalized correlation, and subject classification is performed by nearest neighbor matching among correlation scores. The approach implicitly captures biometric shape cues such as body height, width, and body-part proportions, as well as gait cues such as stride length and amount of arm swing. We evaluate the method on four databases with varying viewing angles, background conditions (indoors and outdoors), walk styles and pixels on target.Keywords biometrics (access control), computer vision, correlation methods, gait analysis, image classification, image matching, image motion analysis, image sequences, shape measurement, video databases, arm swing, background conditions, baseline recognition method, biometric shape cues, body height, body shape, body width, body-part proportions, correlation scores, cyclic gait analysis, databases, gait cues, indoor conditions, key frame extraction, lower bound, nearest-neighbor matching, normalized correlation, outdoor conditions, pixels, silhouette-based human identification, stride length, subject classification, template matching, test image sequence, training frames, viewing angles, viewpoint-dependent technique, walking styles This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Pennsylvania's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to pubs-permissions@ieee.org. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.