Since the middle and late 18th century,as Chinese civilization entered a downward trajectory,the social image of China built by the Western society before modern times as a land of wisdom,virtue and faith with vast te...Since the middle and late 18th century,as Chinese civilization entered a downward trajectory,the social image of China built by the Western society before modern times as a land of wisdom,virtue and faith with vast territory,abundant resources,prosperity and inclusive civilization had gradually collapsed.As peregrinators to China had a deeper understanding of China,the overall disappearance of urban and rural poetry and the overall decline of social groups constituted the historical base map for peregrinators to construct the social image of modern China.展开更多
The explosive increase in the number of images on the Internet has brought with it the great challenge of how to effectively index, retrieve, and organize these resources. Assigning proper tags to the visual content i...The explosive increase in the number of images on the Internet has brought with it the great challenge of how to effectively index, retrieve, and organize these resources. Assigning proper tags to the visual content is key to the success of many applications such as image retrieval and content mining. Although recent years have witnessed many advances in image tagging, these methods have limitations when applied to high-quality and large-scale training data that are expensive to obtain. In this paper, we propose a novel semantic neighbor learning method based on user-contributed social image datasets that can be acquired from the Web＇s inexhaustible social image content. In contrast to existing image tagging approaches that rely on high-quality image-tag supervision, we acquire weak supervision of our neighbor learning method by progressive neighborhood retrieval from noisy and diverse user-contributed image collections. The retrieved neighbor images are not only visually alike and partially correlated but also semantically related. We offer a step-by-step and easy-to-use implementation for the proposed method. Extensive experimentation on several datasets demonstrates that the performance of the proposed method significantly outperforms others.展开更多
基金“Twelfth Five-year Plan”Program of Guangdong Provincial Philosophy and Social Sciences(GD15XLS07)Science and Technology Innovation Research Team Program of Zhaoqing University(2021)Tourism Management Key Discipline Construction Program of Zhaoqing University(2022).
文摘Since the middle and late 18th century,as Chinese civilization entered a downward trajectory,the social image of China built by the Western society before modern times as a land of wisdom,virtue and faith with vast territory,abundant resources,prosperity and inclusive civilization had gradually collapsed.As peregrinators to China had a deeper understanding of China,the overall disappearance of urban and rural poetry and the overall decline of social groups constituted the historical base map for peregrinators to construct the social image of modern China.
基金supported in part by the National Natural Science Foundation of China(Nos.61502094 and 61402099)Natural Science Foundation of Heilongjiang Province of China(Nos.F2016002 and F2015020)
文摘The explosive increase in the number of images on the Internet has brought with it the great challenge of how to effectively index, retrieve, and organize these resources. Assigning proper tags to the visual content is key to the success of many applications such as image retrieval and content mining. Although recent years have witnessed many advances in image tagging, these methods have limitations when applied to high-quality and large-scale training data that are expensive to obtain. In this paper, we propose a novel semantic neighbor learning method based on user-contributed social image datasets that can be acquired from the Web＇s inexhaustible social image content. In contrast to existing image tagging approaches that rely on high-quality image-tag supervision, we acquire weak supervision of our neighbor learning method by progressive neighborhood retrieval from noisy and diverse user-contributed image collections. The retrieved neighbor images are not only visually alike and partially correlated but also semantically related. We offer a step-by-step and easy-to-use implementation for the proposed method. Extensive experimentation on several datasets demonstrates that the performance of the proposed method significantly outperforms others.
