Saliency Detection with a Deeper Investigation of Light Field
Authors: Jun Zhang, Meng Wang, Jun Gao, Yi Wang, Xudong Zhang, Xindong Wu
IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive evaluations on the recently introduced Light Field Saliency Dataset (LFSD) [Li et al., 2014], including studies of different light field cues and comparisons with Li et al. s method (the only reported light field saliency detection approach to our knowledge) and the 2D/3D state-of-the-art approaches extended with light field depth/focusness information, show that the investigated light field properties are complementary with each other and lead to improvements on 2D/3D models, and our approach produces superior results in comparison with the state-of-the-art. We conduct extensive experiments to demonstrate the effectiveness and superiority of our proposed approach. |
| Researcher Affiliation | Academia | School of Computer Science and Information Engineering, Hefei University of Technology, China Department of Computer Science, University of Vermont, USA zhangjun@hfut.edu.cn, eric.mengwang@gmail.com, gaojun@hfut.edu.cn wangyi916@mail.hfut.edu.cn, xudong@hfut.edu.cn, xwu@uvm.edu |
| Pseudocode | No | The paper presents a pipeline diagram (Figure 2) and describes the approach using natural language and mathematical equations, but it does not include a formal pseudocode block or an algorithm section. |
| Open Source Code | No | The paper does not provide any explicit statements or links indicating that the source code for the described methodology is publicly available. |
| Open Datasets | Yes | Dataset Light Field Saliency Dataset (LFSD)1 is the only reported dataset captured by Lytro camera for saliency analysis, which contains 100 light fields acquired in 60 indoor and 40 outdoor scenes. ... 1http://www.eecis.udel.edu/ nianyi/LFSD.htm |
| Dataset Splits | No | The paper mentions evaluating on the 'whole dataset' but does not specify any particular training, validation, or testing splits (e.g., percentages or counts) for model development or hyperparameter tuning. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used to run the experiments. |
| Software Dependencies | No | The paper mentions using the 'Simple Linear Iterative Clustering (SLIC) algorithm' and working in 'CIE LAB color space', but it does not specify any software names with version numbers required for reproduction. |
| Experiment Setup | Yes | We found that 300 super-pixels are enough to obtain high performance for saliency detection. σw is specified as 0.67 throughout our experiments. ...we empirically set them as α = 0.3 and β = 0.7. ...here, η = 28 controls the bandwidth. ...where σbg = 1. ...and set β2 = 0.3 to highlight precision [Achanta et al., 2009]. |