MLVCNN: Multi-Loop-View Convolutional Neural Network for 3D Shape Retrieval
Authors: Jianwen Jiang, Di Bao, Ziqiang Chen, Xibin Zhao, Yue Gao8513-8520
AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our proposed method has been evaluated on the public 3D shape benchmark, i.e., Model Net40. Experiments and comparisons with the state-of-the-art methods show that the proposed MLVCNN method can achieve significant performance improvement on 3D shape retrieval tasks. Our MLVCNN outperforms the state-of-the-art methods by the m AP of 4.84% in 3D shape retrieval task. We have also evaluated the performance of the proposed method on the 3D shape classification task where MLVCNN also achieves superior performance compared with recent methods. |
| Researcher Affiliation | Academia | Jianwen Jiang, Di Bao, Ziqiang Chen, Xibin Zhao, Yue Gao BNRist, KLISS, School of Software, Tsinghua University, China. {jjw17, bd17, czq18}@mails.tsinghua.edu.cn, {zxb, gaoyue}@tsinghua.edu.cn |
| Pseudocode | No | The paper does not contain any pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any concrete statement or link regarding the availability of its source code. |
| Open Datasets | Yes | Our proposed method has been evaluated on the public 3D shape benchmark, i.e., Model Net40. Model Net dataset contains 127,915 3D CAD models from 622 object categories. A subset of 40-common classes (Model Net40) including 12311 3D shapes is used in our experiments. We follow the same training and testing split setting in (Su et al. 2015). |
| Dataset Splits | Yes | We follow the same training and testing split setting in (Su et al. 2015). |
| Hardware Specification | No | The paper mentions 'limitation of GPU memory' but does not specify any particular GPU model, CPU, or other hardware component used for experiments. |
| Software Dependencies | No | The paper mentions using 'Res Net18' and 'LSTM' as parts of its model architecture, but does not specify any software dependencies (e.g., libraries, frameworks) with version numbers. |
| Experiment Setup | No | The paper mentions using 'softmax loss' and 'Center Loss' but does not provide specific hyperparameters such as learning rate, batch size, number of epochs, or optimizer settings for the experimental setup. |