Deformable part models have achieved impressive performance for object detection, even on difficult image datasets. This paper explores the generalization of deformable part models from 2D images to 3D spatiotemporal volumes to better study their effectiveness for action detection in video. Actions are treated as spatiotemporal patterns and a deformable part model is generated for each action from a collection of examples. For each action model, the most discriminative 3D subvolumes are automatically selected as parts and the spatiotemporal relations between their locations are learned. By focusing on the most distinctive parts of each action, our models adapt to intra-class variation and show robustness to clutter. Extensive experiments on several video datasets demonstrate the strength of spatiotemporal DPMs for classifying and localizing actions.

In this paper, we address the problem of cross-view image geo-localization. Specifically, we aim to estimate the GPS location of a query street view image by finding the matching images in a reference database of geotagged bird's eye view images, or vice versa. To this end, we present a new framework for cross-view image geolocalization by taking advantage of the tremendous success of deep convolutional neural networks (CNNs) in image classification and object detection. First, we employ the Faster R-CNN [16] to detect buildings in the query and reference images. Next, for each building in the query image, we retrieve the k nearest neighbors from the reference buildings using a Siamese network trained on both positive matching image pairs and negative pairs. To find the correct NN for each query building, we develop an efficient multiple nearest neighbors matching method based on dominant sets. We evaluate the proposed framework on a new dataset that consists of pairs of street view and bird's eye view images. Experimental results show that the proposed method achieves better geo-localization accuracy than other approaches and is able to generalize to images at unseen locations.

In this paper we show that multiple object tracking (MOT) can be formulated in a framework, where the detection and data-association are performed simultaneously. Our method allows us to overcome the confinements of data association based MOT approaches; where the performance is dependent on the object detection results provided at input level. At the core of our method lies structured learning which learns a model for each target and infers the best location of all targets simultaneously in a video clip. The inference of our structured learning is done through a new Target Identity-aware Network Flow (TINF), where each node in the network encodes the probability of each target identity belonging to that node. The proposed Lagrangian relaxation optimization finds the high quality solution to the network. During optimization a soft spatial constraint is enforced between the nodes of the graph which helps reducing the ambiguity caused by nearby targets with similar appearance in crowded scenarios. We show that automatically detecting and tracking targets in a single framework can help resolve the ambiguities due to frequent occlusion and heavy articulation of targets. Our experiments involve challenging yet distinct datasets and show that our method can achieve results better than the state-of-art.

In this work, we propose a tracker that differs from most existing multi-target trackers in two major ways. Firstly, our tracker does not rely on a pre-trained object detector to get the initial object hypotheses. Secondly, our tracker's final output is the fine contours of the targets rather than traditional bounding boxes. Therefore, our tracker simultaneously solves three main problems: detection, data association and segmentation. This is especially important because the output of each of those three problems are highly correlated and the solution of one can greatly help improve the others. The proposed algorithm consists of two main components: structured learning and Lagrange dual decomposition. Our structured learning based tracker learns a model for each target and infers the best locations of all targets simultaneously in a video clip. The inference of our structured learning is achieved through a new Target Identity-aware Network Flow (TINF). The second component is Lagrange dual decomposition, which combines the structured learning tracker with a multi-label Conditional Random Field (CRF) based segmentation algorithm. This leads to more accurate segmentation results and also helps better resolve typical difficulties in multiple target tracking, such as occlusion handling, ID-switch and track drifting.

No abstract

No abstract

No abstract

Surgery is the most commonly used method of curing inverted papilloma (IP) or nasal polyp (NP). Although accurate preoperative recognition by computed tomography (CT) is a critical aspect of surgical planning, the minor CT imaging differences in such lesions may be a challenge. Therefore, we have devised a deep learning framework for automatic recognition of IP and NP in CT. The proposed framework involves two major steps: (a) use of a convolutional neural network (CNN) to preclassify lesions and (b) automatic IP/NP recognition. The preclassify CNN enables classification of CT slices according to anatomic structure. Separate networks are then implemented to differentiate IP and NP accordingly. Once the framework was trained using a CT dataset (5681 slices) from 136 patients, it outperformed other methods during evaluation, achieving 89.30% accuracy (area under the curve [AUC]=0.95) in classification. The proposed framework has clear potential as a clinical tool, enabling effective and highly accurate preoperative recognition of IP and NP. INDEX TERMS Deep learning, inverted papilloma, nasal polyp, pre-classify, recognition.