Triplet Hierarchical Metric Network for Sketch-Based 3D Shape Retrieval
A triplet hierarchical metric network for 3D model sketch retrieval is proposed to address the problem that sketches are treated as ordinary images and their unique sparsity is ignored,and the intra-class differences between sketches and 3D models are not given enough attention,which affects the retrieval per-formance.Then,the network is fully constrained by multi-level joint loss across domains,so that the net-work learns to represent both single-domain intra-class differences and inter-domain relationships,which effectively improves the retrieval performance of the network.The experimental results show that the aver-age retrieval accuracy of the proposed network on two publicly available datasets SHREC2013 and SHREC2014 is 87.7％and 83.3％,respectively,which is more than 0.5 percentage points and 1.5 percentage points better than the advanced work(the same base-net).
sketch-based 3D shape retrievaltriplet network structuremulti-level joint loss functionsemantic embeddingcross-modality retrieval
万方数据
维普
