Learn to Rank Images: A Unified Probabilistic Hypergraph Model for Visual Search

Abstract

In visual search systems, it is important to address the issue of how to leverage the rich contextual information in a visual computational model to build more robust visual search systems and to better satisfy the user’s need and intention. In this paper, we introduced a ranking model by understanding the complex relations within product visual and textual information in visual search systems. To understand their complex relations, we focused on using graph-based paradigms to model the relations among product images, product category labels, and product names and descriptions. We developed a unified probabilistic hypergraph ranking algorithm, which, modeling the correlations among product visual features and textual features, extensively enriches the description of the image. We conducted experiments on the proposed ranking algorithm on a dataset collected from a real e-commerce website. The results of our comparison demonstrate that our proposed algorithm extensively improves the retrieval performance over the visual distance based ranking.

Networks beyond pairwise interactions: structure and dynamics

“…They obtain the ranking of different scientists according to a hypergraph where hyperedges represent articles and the authors have weights which reflect their appearance order (first/last or middle authors), and they compare such ranking to that obtained by a random walk on the corresponding edge-independent hypergraph. Other applications of edge-dependent hypergraphs include e-commerce [329], text ranking [87], image visualisation and processing [330][331][332][333][334].…”

Random Walks on Hypergraphs with Edge-Dependent Vertex Weights

“…e edge-dependent vertex weight γ e ( ) models the contribution of vertex to hyperedge e. Edge-dependent vertex weights have previously been used in several applications including: image segmentation, where the weights represent the probability of an image pixel (vertex) belonging to a segment (hyperedge) [11]; e-commerce, where the weights model the quantity of a product (hyperedge) in a user's shopping basket (vertex) [26]; and text ranking, where the weights represent the importance of a keyword (vertex) to a document (hyperedge) [5]. Hypergraphs with edge-dependent vertex weights have also been used in image search [20,40] and 3D object classi cation [42], where the weights represent contributions of vertices in a k-nearest-neighbors hypergraph.…”

Image Retrieval using Hypergraph of Visual Concepts

“…Hypergraphs are more useful to represent complex relationship between objects [2]. In a hypergraph each edge can be attached to any (one or more than one) [3]. In fig.2, V 1 to V 12 are the vertices in a hypergraph and e 1 to e 6 are the hyperedges.…”