Deep Compositional Cross-modal Learning to Rank via Local-Global Alignment

52 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Image Captioning with Deep Bidirectional LSTMs (2016, background): “This is an instance of cross-modal retrieval [6, 30, 41] which has been a hot research subject in multimedia field.”
A Comprehensive Survey on Cross-modal Retrieval (2016, methodology): “…[35], PAMIR [36], LSCMR [37], bi-LSCMR [38], Wsabie [39], RCCA [40] Deep learning methods DeViSE [41], DT-RNNs [42], Deep Fragment [43], C 2 MLR [44] Supervised methods Subspace learning methods CDFE [45], GMA [15], I 2 SCA [46], PFAR [47], JRL [48], SliM 2 [49], cluster-CCA [50], CCA-3V [51],…”
An Overview of Cross-Media Retrieval: Concepts, Methodologies, Benchmarks, and Challenges (2017, background): “[58] first project visual objects and text words into the local common space, and then project them into the global common space in a compositional way with ranking information.”
A Survey of Multi-View Representation Learning (2016, unknown): “[184] also introduce a deep cross-modal retrieval method, called deep compositional cross-modal learning to rank, which considers learning a multi-modal embedding from the perspective of optimizing a pairwise ranking problem while enhancing both local alignment and global alignment.”
Predicting Visual Features From Text for Image and Video Caption Retrieval (2017, background): “For image retrieval by caption, recent evidence [12] shows that a one-way mapping from the visual to the textual modality outperforms the state-of-the-art subspace based solutions.”