Y^2Seq2Seq: Cross-Modal Representation Learning for 3D Shape and Text by Joint Reconstruction and Prediction of View and Word Sequences
This addresses the issue of detailed geometry in 3D shape representation for computer vision and AI applications, but it is incremental as it builds on existing view-based and sequence-to-sequence methods.
The paper tackles the problem of representing 3D shapes at low resolutions due to computational costs by proposing Y^2Seq2Seq, a view-based model that learns cross-modal representations through joint reconstruction and prediction of view and word sequences, achieving state-of-the-art results in cross-modal retrieval and 3D shape captioning.
A recent method employs 3D voxels to represent 3D shapes, but this limits the approach to low resolutions due to the computational cost caused by the cubic complexity of 3D voxels. Hence the method suffers from a lack of detailed geometry. To resolve this issue, we propose Y^2Seq2Seq, a view-based model, to learn cross-modal representations by joint reconstruction and prediction of view and word sequences. Specifically, the network architecture of Y^2Seq2Seq bridges the semantic meaning embedded in the two modalities by two coupled `Y' like sequence-to-sequence (Seq2Seq) structures. In addition, our novel hierarchical constraints further increase the discriminability of the cross-modal representations by employing more detailed discriminative information. Experimental results on cross-modal retrieval and 3D shape captioning show that Y^2Seq2Seq outperforms the state-of-the-art methods.