Semantic Graph Construction for Weakly-Supervised Image Parsing
Authors: Wenxuan Xie, Yuxin Peng, Jianguo Xiao
AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results demonstrate that the proposed semantic graphs not only capture more semantic relevance, but also perform significantly better than conventional graphs in image parsing. |
| Researcher Affiliation | Academia | Wenxuan Xie and Yuxin Peng and Jianguo Xiao Institute of Computer Science and Technology, Peking University, Beijing 100871, China {xiewenxuan, pengyuxin, xiaojianguo}@pku.edu.cn |
| Pseudocode | No | The paper describes methods through mathematical formulations and text, but does not include structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any statement or link regarding the availability of open-source code for the described methodology. |
| Open Datasets | Yes | We conduct experiments on two standard datasets: PASCAL VOC 07 (PASCAL for short) (Everingham et al. 2010) and MSRC-21 (Shotton et al. 2009). |
| Dataset Splits | No | The paper states "In the weakly-supervised image parsing task, we assume all the image-level labels are known for both training and test set", but does not specify any explicit training/validation/test dataset splits (e.g., percentages, sample counts, or cross-validation setup). |
| Hardware Specification | No | The paper does not provide specific details about the hardware used to run the experiments. |
| Software Dependencies | No | The paper mentions using 'SLIC algorithm' and 'SIFT' but does not specify version numbers for any software dependencies. |
| Experiment Setup | Yes | In the experiments, we discover that the parameter k in all k-NN-based graphs are relatively insensitive to the performance, and we set k = 20 empirically. |