AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Y2Seq2Seq: Cross-Modal Representation Learning for 3D Shape and Text by Joint Reconstruction and Prediction of View and Word Sequences

Zhizhong Han, Mingyang Shang, Xiyang Wang, Yu-Shen Liu, Matthias Zwicker

AAAI 2019 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval · 56 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use coupled branches with joint within-modality reconstruction and cross-modal prediction (ablation)Y²Seq2Seq · Primitive S2TRR@1: 69.87 -> 80.13Improved
Use coupled branches with joint within-modality reconstruction and cross-modal prediction (ablation)Y²Seq2Seq · ShapeNet S2TRR@1: 1.74 -> 1.88Improved
Add the class-level classification constraint (ablation)Y²Seq2Seq · Primitive S2TRR@1: 80.13 -> 83.07Improved
Add the triplet constraint after classification (ablation)Y²Seq2Seq · Primitive S2TRR@1: 83.07 -> 88.53Improved
Add the joint embedding constraint after classification and triplet constraints (ablation)Y²Seq2Seq · Primitive S2TRR@1: 88.53 -> 94.13Improved
Add all hierarchical constraints (ablation)Y²Seq2Seq · ShapeNet S2TRR@1: 1.88 -> 6.77Improved
Increase voxel resolution from 32³ to 128³ (ablation)Y²Seq2Seq · ShapeNet S2TRR@1: 6.77 -> 7.64Improved
Increase voxel resolution from 32³ to 64³ (ablation)Y²Seq2Seq · ShapeNet T2SRR@1: 2.93 -> 2.37Hurt
Increase voxel resolution from 32³ to 128³ (ablation)Y²Seq2Seq · ShapeNet T2SRR@5: 9.23 -> 9.82Improved
Generate captions rather than retrieve the nearest description (ablation)Y²Seq2Seq · Primitive shape captioningMETEOR: 0.70 -> 0.54Hurt
Generate captions rather than retrieve the nearest description (ablation)Y²Seq2Seq · ShapeNet shape captioningMETEOR: 0.22 -> 0.29Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy