We propose a novel unsupervised game-theoretic salient object detection algorithm that does not require labeled training data. First, saliency detection problem is formulated as a non-cooperative game, hereinafter referred to as Saliency Game, in which image regions are players who choose to be ”background” or ”foreground” as their pure strategies. A payoff function is constructed by exploiting...

Salient object detection has increasingly become a popular topic in cognitive and computational sciences, including computer vision and artificial intelligence research. In this paper, we propose integrating semantic priors into the salient object detection process. Our algorithm consists of three basic steps. Firstly, the explicit saliency map is obtained based on the semantic segmentation ref...

Saliency map samples for eye fixation prediction are shown in Fig 1-2; saliency map samples for salient object detection are shown in Fig 3-7. A model of saliency-based visual attention for rapid scene analysis.

We present a novel spatiotemporal saliency detection method to estimate salient regions in videos based on the gradient flow field and energy optimization. The proposed gradient flow field incorporates two distinctive features: 1) intra-frame boundary information and 2) inter-frame motion information together for indicating the salient regions. Based on the effective utilization of both intra-f...

In this paper, a method of constructing saliency map based on learning method is proposed. The saliency map is constructed by nonlinear combination of features, and the nonlinear function is approached through a feed forward artificial neutral network (ANN) whose weight is trained by examples. The efficiency of the proposed method is verified in the eye detection problem. Experiments show that ...

Visual tracking in aerial videos is a challenging task in computer vision and remote sensing technologies due to appearance variation difficulties. Appearance variations are caused by camera and target motion, low resolution noisy images, scale changes, and pose variations. Various approaches have been proposed to deal with appearance variation difficulties in aerial videos, and amongst these m...

—Traditional saliency models usually adopt hand-crafted image features and human-designed mechanisms to calculate local or global contrast. In this paper, we propose a novel computational saliency model, i.e., deep spatial contextual long-term recurrent convolutional network (DSCLRCN) to predict where people looks in natural scenes. DSCLRCN first automatically learns saliency related local feat...

Salient region detection is a challenge problem in computer vision, which is useful in image segmentation, region-based image retrieval, and so on. In this paper we present a multi-resolution salient region detection method in frequency domain which can highlight salient regions with well-defined boundaries of object. The original image is sub-sampled into three multi-resolution layers, and for...

In order to accurately evaluate the video quality and make it consistent with the subjective evaluation result, a saliency region and motion characteristics combined video quality assessment is proposed in this paper. This method is based on traditional SSIM and improves its assessment performance. According to the relationship between human visual attention and video’s region of saliency, fram...

Saliency detection is an important yet challenging task in computer vision. In this report we investigate the use of sparse coding over redundant dictionary for saliency detection. We attempt to present a small fraction of the growing knowledge regarding sparse representation over redundant dictionary and discuss some potential usage of this powerful tool for saliency detection task. We propose...