Xiangang Cheng

Learn More
Large-scale dataset construction will require a significant large amount of well labeled ground truth. For the NUS-WIDE dataset, a less labor-intensive annotation process was used and this paper will focuses on improving the semi-manual annotation method used. For the NUS-WIDE dataset, improving the average accuracy for top retrievals of individual concepts(More)
—This paper presents an efficient and effective solution for retrieving image near-duplicate (IND) from image database. We introduce the coherent phrase model which incorporates the coherency of local regions to reduce the quantization error of the bag-of-words (BoW) model. In this model, local regions are characterized by visual phrase of multiple(More)
The current volume of videos available for distribution or viewing on the internet is increasing exponentially, there is an urgent need for designing effective and efficient video management systems. However, due to the tremendous amounts of video data, it is highly likely that any large scale video systems will provide query results with near-duplicates(More)
Retinal landmark detection is a key step in retinal screening and computer-aided diagnosis for different types of eye diseases, such as glaucomma, age-related macular degeneration(AMD) and diabetic retinopathy. In this paper, we propose a semantic image transformation(SIT) approach for retinal representation and automatic landmark detection. The proposed(More)
Keywords: Large-scale dataset Concept prediction Mid-level visual feature Concept-tag co-occurrence matrix K-nearest neighbor Tag understanding Precision and Recall Grouping a b s t r a c t This paper focuses on improving the semi-manual method for web image concept annotation. By sufficiently studying the characteristics of tag and visual feature, we(More)