In the past few years, Generative Adversarial Network (GAN) became a prevalent research topic. By defining two convolutional neural networks (GNetwork and D-Network) and introducing an adversarial procedure between them during the training process, GAN has ability to generate good quality images that look like natural images from a random vector. Besides image generation, GAN may have potential...

A decision-theoretic formulation of visual saliency, first proposed for top-down processing (object recognition) in (Gao & Vasconcelos, 2005) is extended to the problem of bottom-up saliency. Under this formulation, optimality is defined in the minimum probability of error sense, under a constraint of computational parsimony. The saliency of the visual features at a given location of the visual...

In this paper we propose an effective non-rigid object tracking method based on spatial-temporal consistent saliency detection. In contrast to most existing trackers that use a bounding box to specify the tracked target, the proposed method can extract the accurate regions of the target as tracking output, which achieves better description of the non-rigid objects while reduces background pollu...

This paper presents a spatiotemporal saliency visual attention model based on maximum entropy. A dynamic saliency map is created by calculating entropies in every corresponding local region between the current and some previous frames in a short video. In the same time, four low-level visual features including color contrast, intensity contrast, orientation and texture, are extracted and are co...

Human vision system actively seeks salient regions and movements in video sequences to reduce the search effort. Modeling computational visual saliency map provides important information for semantic understanding in many real world applications. In this paper, we propose a novel video saliency detection model for detecting the attended regions that correspond to both interesting objects and do...

Finding the salient regions in videos has been a very active topic. In this work we compare the modelisation of visual attention on egocentric video recordings for two different points of view. We are interested in finding the relation between the visual saliency maps of the viewer of visual content and the actors (person executing the actions). This question is of importance because the buildi...

A target-oriented visual saliency detection model for optical satellite images is proposed in this paper. This model simulates the structure of the human vision system and provides a feasible way to integrate top-down and bottom-up mechanism in visual saliency detection. Firstly, low-level visual features are extracted to generate a low-level visual saliency map. After that, an attention shift ...

The problem of object localization and recognition on autonomous mobile robots is still an active topic. In this context, we tackle the problem of learning a model of visual saliency directly on a robot. This model, learned and improved on-the-fly during the robot’s exploration provides an efficient tool for localizing relevant objects within their environment. The proposed approach includes tw...

Improved points (each point contributes 1~3pt improvement) Fully Convolutional Net Guided back propagation [2] Use the derivatives of multiple intermediate layers Aggregate multi-scale class saliency maps (3 scales) Assumption Raw saliency maps are affected by both class-specific saliency and generic object-ness The degree of class saliency factors should be larger than the generic object-ness ...