With an increasing number of new summarization systems proposed in recent years, an automatic text evaluation metric that can accurately and reliably rate the performance of summarization systems has been a pressing need. However, current automatic text evaluation metrics can only measure one or certain aspects of the quality between two summary texts and do not agree with human judgments consistently. In this paper, we show that combining multiple well-chosen evaluation metrics and training predictive models using human annotated datasets can lead to more reliable evaluation scores than using any individual automatic metric. Our predictive models trained on a human annotated subset of the CNN/DailyMail corpus demonstrate significant improvements (e.g. approximately 25% along coherence dimension) over selected individual metrics. Furthermore, a concise meta-evaluation on automatic metrics is provided along with an analysis of the performance of 12 predictive models. We also investigate the sensitivity of automatic metrics when mixed together for training these models. We have made the code, the instructions for experiment setup, and the trained models available as a tool for comparing and evaluating text summarization systems. a a https://github.com/bzhao2718/ReliableSummEvalReg .

Increasingly, machines are interacting with people through human action recognition from video streams. Video data can naturally be represented as a third-order data tensor. Although many tensor-based approaches have been proposed for action recognition, the geometry of the tensor space is seldom regarded as an important aspect. In this paper, we stress that a data tensor is related to a tangent bundle on a special manifold. Using a manifold charting, we can extract discriminating information between actions. Data tensors are first factorized using high-order singular value decomposition, where each factor is projected onto a tangent space and the intrinsic distance is computed from a tangent bundle for action classification. We examine a standard manifold charting and some alternative chartings on special manifolds, particularly, the special orthogonal group, Stiefel manifolds, and Grassmann manifolds. Because the proposed paradigm frames the classification scheme as a nearest neighbor based on the intrinsic distance, prior training is unnecessary. We evaluate our method on three public action databases including the Cambridge gesture, the UMD Keck body gesture, and the UCF sport datasets. The empirical results reveal that our method is highly competitive with the current state-of-the-art methods, robust to small alignment errors, and yet simpler.

Common human actions are instantly recognizable by people and increasingly machines need to understand this language if they are to engage smoothly with people. Here we introduce a new method for automated human action recognition. The proposed method represents videos as a tangent bundle on a Grassmann manifold. Videos are expressed as third order tensors and factorized to a set of tangent spaces. Tangent vectors are then computed between elements on a Grassmann manifold and exploited for action classification. In particular, logarithmic mapping is applied to map a point from the manifold to tangent vectors centered at a given element. The canonical metric is used to induce the intrinsic distance for a set of tangent spaces. Empirical results show that our method is effective on both uniform and non-uniform backgrounds for action classification. We achieve recognition rates of 91% on the Cambridge gesture dataset, 88% on the UCF sport dataset, and 97% on the KTH human action dataset. Additionally, our method does not require prior training.

This paper analyzes completely unsupervised clustering of human expressions, gestures, and actions in video. Lacking any supervision, there is nothing except the inherent biases of a given technique to guide grouping of video clips along semantically meaningful partitions. This paper evaluates two contemporary behavior recognition methods, Bag of Features (BOF) and Product Manifolds (PM), for clustering video clips of human facial expressions, hand gestures, and full-body actions. Our goal is to better understand how well these very different approaches to behavior recognition produce semantically useful clustering of relevant data. We show that PM yields superior results when measuring the alignment between the generated clusters over a range of K-values (number of clusters) and the nominal class labelling of the data set. A key result is that unsupervised clustering with PM yields accuracy comparable to state-of-the-art supervised classification methods on KTH Actions. At the same time, BOF experiences a substantial drop in performance between unsupervised and supervised implementations on the same data sets, indicating a greater reliance on supervision for achieving high performance. We also found that while gross motions were easily clustered by both methods, the lack of preservation of structural information inherent to the BOF representation leads to limitations that are not easily overcome without supervised training. This was evidenced by the poor separation of shape labels in the hand gestures data by BOF, and the overall poor performance on full-body actions.

The Good, the Bad, & the Ugly Face Challenge Problem was created to encourage the development of algorithms that are robust to recognition across changes that occur in still frontal faces. The Good, the Bad, & the Ugly consists of three partitions. The Good partition contains pairs of images that are considered easy to recognize. On the Good partition, the base verification rate (VR) is 0.98 at a false accept rate (FAR) of 0.001. The Bad partition contains pairs of images of average difficulty to recognize. For the Bad partition, the VR is 0.80 at a FAR of 0.001. The Ugly partition contains pairs of images considered difficult to recognize, with a VR of 0.15 at a FAR of 0.001. The base performance is from fusing the output of three of the top performers in the FRVT 2006. The design of the Good, the Bad, & the Ugly controls for pose variation, subject aging, and subject “recognizability.” Subject recognizability is controlled by having the same number of images of each subject in every partition. This implies that the differences in performance among the partitions are result of how a face is presented in each image.

Although not commonly used, correlation filters can track complex objects through rotations, occlusions and other distractions at over 20 times the rate of current state-of-the-art techniques. The oldest and simplest correlation filters use simple templates and generally fail when applied to tracking. More modern approaches such as ASEF and UMACE perform better, but their training needs are poorly suited to tracking. Visual tracking requires robust filters to be trained from a single frame and dynamically adapted as the appearance of the target object changes. This paper presents a new type of correlation filter, a Minimum Output Sum of Squared Error (MOSSE) filter, which produces stable correlation filters when initialized using a single frame. A tracker based upon MOSSE filters is robust to variations in lighting, scale, pose, and nonrigid deformations while operating at 669 frames per second. Occlusion is detected based upon the peak-to-sidelobe ratio, which enables the tracker to pause and resume where it left off when the object reappears.

Videos can be naturally represented as multidimensional arrays known as tensors. However, the geometry of the tensor space is often ignored. In this paper, we argue that the underlying geometry of the tensor space is an important property for action classification. We characterize a tensor as a point on a product manifold and perform classification on this space. First, we factorize a tensor relating to each order using a modified High Order Singular Value Decomposition (HOSVD). We recognize each factorized space as a Grassmann manifold. Consequently, a tensor is mapped to a point on a product manifold and the geodesic distance on a product manifold is computed for tensor classification. We assess the proposed method using two public video databases, namely Cambridge-Gesture gesture and KTH human action data sets. Experimental results reveal that the proposed method performs very well on these data sets. In addition, our method is generic in the sense that no prior training is needed.

We present an adaptive framework for condensation algorithms in the context of human-face tracking. We attack the face tracking problem by making factored sampling more efficient and appearance update more effective. An adaptive affine cascade factored sampling strategy is introduced to sample the parameter space such that coarse face locations are located first, followed by a fine factored sampling with a small number of particles. In addition, the local linearity of an appearance manifold is used in conjunction with a new criterion to select a tangent plane for updating an appearance in face tracking. Our proposed method seeks the best linear variety from the selected tangent plane to form a reference image. We demonstrate the effectiveness and efficiency of the proposed method on a number of challenging videos. These test video sequences show that our method is robust to illumination, appearance, and pose changes, as well as temporary occlusions. Quantitatively, our method achieves the average root-mean-square error at 4.98 on the well-known dudek video sequence while maintaining a proficient speed at 8.74 fps. Finally, while our algorithm is adaptive during execution, no training is required.

This paper summarizes a study carried out on data from the Face Recognition Vendor Test 2006 (FRVT 2006). The finding of greatest practical importance is the discovery of a strong connection between a relatively simple measure of image quality and performance of state-of-the-art vendor algorithms in FRVT 2006. The image quality measure quantifies edge density and likely relates to focus. This effect is part of a larger four-way interaction observed between edge density, face size and whether images are acquired indoors our outdoors. This finding illustrates the broader potential for statistical modeling of empirical data to play an important role in finding and codifying biometric quality measures.

An image-set based face recognition algorithm is proposed that exploits the full geometrical interpretation of Canonical Correlation Analysis (CCA). CCA maximizes the correlation between two linear subspaces associated with image-sets, where an image-set is assumed to contain multiple images of a person's face. When these linear subspaces are viewed as points on a Grassmann manifold, then geodesic distance on the manifold becomes the natural way to compare image-sets. The proposed method is tested on the ORL data set where it achieves a rank one identification rate of 98.75%. The proposed method is also tested on a subset of the Face Recognition Grand Challenge Experiment 4 data. Specifically, 82 probe and 230 gallery subjects with 32 images per probe and gallery image-set. Our algorithm achieves a rank one identification rate of 87% and a verification rate of 81% at a false accept rate of 1/1;000. These results on FRGC are significantly better than the well-known image-set matching algorithm, Mutual Subspace Method (MSM), which does not use geodesic distance. Another important finding is that cohort normalization boosts verification performance by 50% when used in conjunction with image-set matching. These results suggest that excellent levels of face recognition performance are possible when using image-sets, geodesic distance and cohort normalization. Finally, the proposed approach is generic in the sense that no training is required.

Many electronic watermarks for still images and video content are sensitive to geometric distortions. For example, simple rotation, scaling, and/or translation (RST) of an image can prevent blind detection of a public watermark. In this paper, we propose a watermarking algorithm that is robust to RST distortions. The watermark is embedded into a one-dimensional (1-D) signal obtained by taking the Fourier transform of the image, resampling the Fourier magnitudes into log-polar coordinates, and then summing a function of those magnitudes along the log-radius axis. Rotation of the image results in a cyclical shift of the extracted signal. Scaling of the image results in amplification of the extracted signal, and translation of the image has no effect on the extracted signal. We can therefore compensate for rotation with a simple search, and compensate for scaling by using the correlation coefficient as the detection measure. False positive results on a database of 10,000 images are reported. Robustness results on a database of 2000 images are described. It is shown that the watermark is robust to rotation, scale, and translation. In addition, we describe tests examining the watermarks resistance to cropping and JPEG compression.

Breast cancer continues to be a significant public health problem in the United States. Approximately, 182,000 new cases of breast cancer are diagnosed and 46,000 women die of breast cancer each year. Even more disturbing is the fact that one out of eight women in the United States will develop breast cancer at some point during her lifetime. Since the cause of breast cancer remains unknown, primary prevention becomes impossible. Computer-aided mammography is an important and challenging task in automated diagnosis. It has great potential over traditional interpretation of film-screen mammography in terms of efficiency and accuracy. Microcalcifications are the earliest sign of breast carcinomas and their detection is one of the key issues for breast cancer control. In this study, a novel approach to microcalcification detection based on fuzzy logic technique is presented. Microcalcifications are first enhanced based on their brightness and nonuniformity. Then, the irrelevant breast structures are excluded by a curve detector. Finally, microcalcifications are located using an iterative threshold selection method. The shapes of microcalcifications are reconstructed and the isolated pixels are removed by employing the mathematical morphology technique. The essential idea of the proposed approach is to apply a fuzzified image of a mammogram to locate the suspicious regions and to interact the fuzzified image with the original image to preserve fidelity. The major advantage of the proposed method is its ability to detect microcalcifications even in very dense breast mammograms. A series of clinical mammograms are employed to test the proposed algorithm and the performance is evaluated by the free-response receiver operating characteristic curve. The experiments aptly show that the microcalcifications can be accurately detected even in very dense mammograms using the proposed approach.