Search

Binary optimization problems (BOPs) arise naturally in many fields, such as information retrieval, computer vision, and machine learning. Most existing binary optimization methods either use continuous relaxation which can cause large quantization errors, or incorporate a highly specific algorithm that can only be used for particular loss functions. To overcome these difficulties, we propose a novel generalized optimization method, named Alternating Binary Matrix Optimization (ABMO), for solving BOPs. ABMO can handle BOPs with/without orthogonality or linear constraints for a large class of loss functions. ABMO involves rewriting the binary, orthogonality and linear constraints for BOPs as an intersection of two closed sets, then iteratively dividing the original problems into several small optimization problems that can be solved as closed forms. To provide a strict theoretical convergence analysis, we add a sufficiently small perturbation and translate the original problem to an approximated problem whose feasible set is continuous. We not only provide rigorous mathematical proof for the convergence to a stationary and feasible point, but also derive the convergence rate of the proposed algorithm. The promising results obtained from four binary optimization tasks validate the superiority and the generality of ABMO compared with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

1064 nm six-junction laser power converters (LPCs) with InGaAsP absorption layers are designed and fabricated. I-V characteristics of the LPCs with an aperture of 8.32 mm2 are investigated as a function of laser power and temperature. Both the open-circuit voltage ($\text{V}_{oc}$) and conversion efficiency ($\eta $) improve with increasing laser power, and reach 4.694 V and 41.2 ± 2%, respectively, under the 1064 nm laser illumination of 1.676 W. The conversion efficiency decreases with the temperature at a rate of −0.09%abs/K independent of laser power. The temperature coefficient of the open-circuit voltage is determined to be −9.77 mV/K at a laser power of 0.174 W and decreases slightly with incident power. This piece of work extends the spectral range for laser power transmission and demonstrates the possibility of even higher voltage 1064 nm LPCs. [ABSTRACT FROM AUTHOR]

With the current exponential growth of video-based social networks, video retrieval using natural language is receiving ever-increasing attention. Most existing approaches tackle this task by extracting individual frame-level spatial features to represent the whole video, while ignoring visual pattern consistencies and intrinsic temporal relationships across different frames. Furthermore, the semantic correspondence between natural language queries and person-centric actions in videos has not been fully explored. To address these problems, we propose a novel binary representation learning framework, named Semantics-aware Spatial-temporal Binaries ($\text{S}^{2}$ Bin), which simultaneously considers spatial-temporal context and semantic relationships for cross-modal video retrieval. By exploiting the semantic relationships between two modalities, $\text{S}^{2}$ Bin can efficiently and effectively generate binary codes for both videos and texts. In addition, we adopt an iterative optimization scheme to learn deep encoding functions with attribute-guided stochastic training. We evaluate our model on three video datasets and the experimental results demonstrate that $\text{S}^{2}$ Bin outperforms the state-of-the-art methods in terms of various cross-modal video retrieval tasks. [ABSTRACT FROM AUTHOR]

In certain scenarios, such as detection of unexploded ordnance (UXO), submarines, and intruders, magnetic anomaly detection (MAD) is an effective method due to the magnetic field advantages of small operating power, strong penetrability, and strong anti-interference ability. However, variability in the background geomagnetic field and low signal-to-noise ratio (SNR) in MAD cannot be avoided. In this article, we propose a MAD method employing an improved orthogonal basis function (OBF) for the magnetic tensor contraction decomposition. The orthogonal basis decomposition approach makes the best use of modeling the MAD output signal, whereas the magnetic tensor contraction aid in avoiding the background field problem. Furthermore, by increasing the baseline length of the magnetic gradiometer, the SNR can also be improved in some manner. A dual magnetic gradiometer framework is introduced to fulfill the demand of the magnetic anomaly localization. From our simulation results, the proposed method improves the SNR of the MAD raw signal and is capable of detecting and locating the magnetic anomaly. Moreover, field test has been carried out to evaluate the performance of the proposed method. [ABSTRACT FROM AUTHOR]

Zero-shot learning (ZSL) is a challenging task due to the lack of unseen class data during training. Existing works attempt to establish a mapping between the visual and class spaces through a common intermediate semantic space. The main limitation of existing methods is the strong bias towards seen class, known as the domain shift problem, which leads to unsatisfactory performance in both conventional and generalized ZSL tasks. To tackle this challenge, we propose to convert ZSL to the conventional supervised learning by generating features for unseen classes. To this end, a joint generative model that couples variational autoencoder (VAE) and generative adversarial network (GAN), called Zero-VAE-GAN, is proposed to generate high-quality unseen features. To enhance the class-level discriminability, an adversarial categorization network is incorporated into the joint framework. Besides, we propose two self-training strategies to augment unlabeled unseen features for the transductive extension of our model, addressing the domain shift problem to a large extent. Experimental results on five standard benchmarks and a large-scale dataset demonstrate the superiority of our generative model over the state-of-the-art methods for conventional, especially generalized ZSL tasks. Moreover, the further improvement of the transductive setting demonstrates the effectiveness of the proposed self-training strategies. [ABSTRACT FROM AUTHOR]

In real life, group activity recognition plays a significant and fundamental role in a variety of applications, e.g. sports video analysis, abnormal behavior detection, and intelligent surveillance. In a complex dynamic scene, a crucial yet challenging issue is how to better model the spatio-temporal contextual information and inter-person relationship. In this paper, we present a novel attentive semantic recurrent neural network (RNN), namely, stagNet, for understanding group activities and individual actions in videos, by combining the spatio-temporal attention mechanism and semantic graph modeling. Specifically, a structured semantic graph is explicitly modeled to express the spatial contextual content of the whole scene, which is further incorporated with the temporal factor through structural-RNN. By virtue of the “factor sharing” and “message passing” mechanisms, our stagNet is capable of extracting discriminative and informative spatio-temporal representations and capturing inter-person relationships. Moreover, we adopt a spatio-temporal attention model to focus on key persons/frames for improved recognition performance. Besides, a body-region attention and a global-part feature pooling strategy are devised for individual action recognition. In experiments, four widely-used public datasets are adopted for performance evaluation, and the extensive results demonstrate the superiority and effectiveness of our method. [ABSTRACT FROM AUTHOR]

Sports video analysis has received increasing attention in recent years. Athlete tracking and action recognition are its two major issues that are highly related to each other; however, they are individually considered and processed in the existing studies. In this paper, we propose a joint framework for athlete tracking and action recognition in sports videos. In athlete tracking, we propose a scaling and occlusion robust tracker, named scaling and occlusion robust compressive tracking (CT), to localize the position of specific athlete in each frame. It follows the approach of CT but extends it in two aspects, i.e., scale refinement as well as occlusion recovery. For the former, an objectness method, edge box, is adopted to generate proposals, which replace the fixed sampling boxes in CT and better fit the scales of the candidate objects. For the latter, a candidate obstruction-based solution is presented, which brings in additional trackers to detect possible obstructions and to relocate the target as occlusion ends. Regarding action recognition, we propose a long-term recurrent region-guided convolutional network, which recognizes pre-defined actions by modeling discriminative temporal cues of the tracking results. We employ SPP-net to extract the robust feature of the tracked region of each frame. The features of all the frames are then fed into a stack of recurrent sequence models to capture the long-term region-level information. We extensively evaluate the proposed approach on a newly collected sports video benchmark and on the off-the-shelf UIUC2 dataset, and the experimental results clearly show its effectiveness. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel unsupervised Nonnegative Adaptive Feature Extraction (NAFE) algorithm for data representation and classification. The formulation of NAFE integrates the sparsity constrained nonnegative matrix factorization (NMF), representation learning, and adaptive reconstruction weight learning into a unified model. Specifically, NAFE performs feature and weight learning over the new robust representations of NMF for more accurate measure and representation. For nonnegative adaptive feature extraction, our NAFE first utilizes the sparsity constrained NMF to obtain the new and robust representations of the original data. To preserve the manifold structures of the learnt new representations, we also incorporate a neighborhood reconstruction error over the weight matrix for joint minimization. Note that to further improve the representation power, the weights are jointly shared in the new low-dimensional nonnegative representation space, low-dimensional nonlinear manifold space, and low-dimensional projective subspace, i.e., local neighborhood information is clearly preserved in different feature spaces so that informative representations and features can be jointly obtained. To enable NAFE to extract features from new data, we also include a feature approximation error by a linear projection so that the learnt extractor can obtain features from new data efficiently. Extensive simulations show that our formulation can deliver state-of-the-art results on several public databases for feature extraction and classification, compared with several related methods. [ABSTRACT FROM AUTHOR]