Deep learning advances have propelled common object detection development. However, small object detection in aerial images remains inaccurate. Intersection-over-Union (IoU) has limitations in handling the separation or inclusion cases of prediction and ground truth boxes, especially in small object detection, which significantly hampers the process of bounding box regression. To tackle the issue, we propose Balanced Corner-IoU (BC-IoU) loss, which incorporates both corner point distances and IoU metric, while simultaneously introducing the instance area as a component of loss terms. Moreover, Point Offset Module (POM) branch is developed to generate additional positive samples for small object regression by dynamically controlling anchor point generation. With the above designs, Scale Adaptive Network (SAN) provides a solution to bounding box regression of small objects. Experiments on the small object detection dataset show that BC-IoU loss outperforms other IoU loss variants and that SAN significantly improves performance over the Fully Convolutional One-Stage (FCOS) baseline.

How to integrate multimodal information sources for face naming in multimodal news is a hot and yet challenging problem. A novel deep cross-modal face naming scheme is developed in this paper to facilitate more effective people news retrieval for large-scale multimodal news. This scheme integrates deep multimodal analysis, cross-modal correlation learning, and multimodal information mining, in which the efficient naming mechanism aims to cluster the deep features of different modalities into a common space to explore their inter-related correlations, and a special Web mining pattern is designed to optimize the name-face matching for rare non-celebrity. Such a cross-modal face naming model can be treated as a problem of bi-media semantic mapping and modeled as an inter-related correlation distribution over deep representations of multimodal news, in which the most important is to create more effective cross-modal name-face correlation and measure to what degree they are correlated. The experiments on a large number of public data from Yahoo! News have obtained very positive results and demonstrated the effectiveness of the proposed model.

Visual and semantic saliency are important in image captioning. However, single-phase image captioning benefits little from limited saliency without a saliency predictor. In this paper, a novel saliency-enhanced re-captioning framework via two-phase learning is proposed to enhance the single-phase image captioning. In the framework, visual saliency and semantic saliency are distilled from the first-phase model and fused with the second-phase model for model self-boosting. The visual saliency mechanism can generate a saliency map and a saliency mask for an image without learning a saliency map predictor. The semantic saliency mechanism sheds some lights on the properties of words with part-of-speech Noun in a caption. Besides, another type of saliency, sample saliency is proposed to explicitly compute the saliency degree of each sample, which helps for more robust image captioning. In addition, how to combine the above three types of saliency for further performance boost is also examined. Our framework can treat an image captioning model as a saliency extractor, which may benefit other captioning models and related tasks. The experimental results on both the Flickr30k and MSCOCO datasets show that the saliency-enhanced models can obtain promising performance gains.

Automatically generating natural language description for video is an extremely complicated and challenging task. To tackle the obstacles of traditional LSTM-based model for video captioning, we propose a novel architecture to generate the optimal descriptions for videos, which focuses on constructing a new network structure that can generate sentences superior to the basic model with LSTM, and establishing special attention mechanisms that can provide more useful visual information for caption generation. This scheme discards the traditional LSTM, and exploits the fully convolutional network with coarse-to-fine and inherited attention designed according to the characteristics of fully convolutional structure. Our model cannot only outperform the basic LSTM-based model, but also achieve the comparable performance with those of state-of-the-art methods

How to deal with matrix game under uncertainty is an open issue. Compared with the Dempster-Shafer structure, the insignificant deviation caused by the subjectivity of the expert is effectively eliminated generalized Dempster-Shafer structures. In this paper, a new matrix game with payoffs of generalized Dempster-Shafer structures is presented. Generalized Dempster-Shafer structures presents probability nonspecificity and inaccuracy as interval values. Then payoff is determined by linear programming. A zero-sum matrix game is illustrated the efficiency of the proposed method.

A novel hierarchical multimodal attention-based model is developed in this paper to generate more accurate and descriptive captions for images. Our model is an "end-to-end" neural network which contains three related sub-networks: a deep convolutional neural network to encode image contents, a recurrent neural network to identify the objects in images sequentially, and a multimodal attention-based recurrent neural network to generate image captions. The main contribution of our work is that the hierarchical structure and multimodal attention mechanism is both applied, thus each caption word can be generated with the multimodal attention on the intermediate semantic objects and the global visual content. Our experiments on two benchmark datasets have obtained very positive results.

We propose an optimal approach to solve the problem of multi-degree reduction of C-Bézier surfaces in the norm L 2 with prescribed constraints. The control points of the degree-reduced C-Bézier surfaces can be explicitly obtained by using a matrix operation that is based on the transfer matrix of the C-Bézier basis. With prescribed boundary constraints, this method can be applied to piecewise continuous patches or to a single patch with the combination of surface subdivision. The resulting piecewise approximating patches are globally G 1 continuous. Finally, numerical examples are presented to show the effectiveness of the method.

Power control and rate allocation are two radio resource management functions that can be used to enhance system utilization. In a time-varying environment, these functions need to be made adaptive. We consider certain implementation restrictions which cause deviations from ideal conditions in adaptive processing. An integrated power control and rate allocation approach to enhance system throughput is proposed. Simulation results show that by using closed-loop power control in conjunction with rate allocation in the presence of the Doppler effect and delay in feeding back channel state information (CSI), significant throughput and BER performance improvement over rate adaptation alone is obtained.