Visual-Textual Joint Relevance Learning for Tag-Based Social Image Search
Citations
3,653 citations
Cites background from "Visual-Textual Joint Relevance Lear..."
...adaptive compression of images [6], content-aware image editing [7], [8], image retrieval [9]–[11], etc....
[...]
3,097 citations
770 citations
Cites background from "Visual-Textual Joint Relevance Lear..."
...In recent years, researchers have developed many computational models for salient object detection and applied them to benefit many other applications, such as image summarization [1], segmentation [2], retrieval [3], and editing [4]....
[...]
527 citations
Cites methods from "Visual-Textual Joint Relevance Lear..."
...In (Gao et al. 2013), a l2 regularize on the weights is introduced to learn optimal hyperedge weights....
[...]
382 citations
Cites background from "Visual-Textual Joint Relevance Lear..."
...tures are integrated in terms of a linear model, and the visual features are considered in terms of a hypergraph regularizer [22], [33], [34], [36]–[38], [51] which captures high-order relationships in building the graph....
[...]
References
46,906 citations
6,447 citations
4,337 citations
"Visual-Textual Joint Relevance Lear..." refers methods in this paper
...Here we illustrate not only the NDCG measurements of each query but also the average NDCG measurements of the 52 queries....
[...]
...We also illustrate the NDCG results obtained by the other six methods in the figure for comparison....
[...]
...6 illustrates the average NDCG measurements at different depths....
[...]
...The Normalized Discounted Cumulative Gain (NDCG) [62] is employed for performance evaluation....
[...]
4,205 citations
3,653 citations