k-SDPP: Fixed-Size Video Summarization via Sequential Determinantal Point Processes
Authors: Jiping Zheng, Ganfeng Lu
IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results show that our proposed BB method outperforms not only k-DPP and sequential DPP (seq DPP) but also the partition and Markovian assumption based methods. ... We evaluate our approach along with related DPP methods in the literature for video summarization. ... Datasets. ... Evaluation metrics. ... Results. |
| Researcher Affiliation | Academia | Jiping Zheng1,2 and Ganfeng Lu1 1College of Computer Science & Technology, Nanjing University of Aeronautics & Astronautics 2Collaborative Innovation Center of Novel Software Technology and Industrialization {jzh, luganf}@nuaa.edu.cn |
| Pseudocode | No | The paper describes the branch and bound method in detail but does not provide pseudocode or a clearly labeled algorithm block. |
| Open Source Code | No | The paper does not provide any links or statements indicating the availability of open-source code for the described methodology. |
| Open Datasets | Yes | We validate our method on two video datasets: the Open Video Project (OVP) dataset, and the You Tube dataset [de Avila et al., 2011]. ...[de Avila et al., 2011] Sandra Eliza Fontes de Avila, Ana Paula Brand ao Lopes, Antonio da Luz, Jr., and Arnaldo de Albuquerque Ara ujo. Vsumm: A mechanism designed to produce static video summaries and a novel evaluation method. Pattern Recognition Letters, 32(1):56 68, 2011. |
| Dataset Splits | No | The paper mentions training and testing splits: 'for You Tube dataset, we randomly choose 31 videos of them for training and the rest 8 videos for testing. For OVP dataset, we randomly choose 40 videos of them for training and the rest 10 videos for testing.' However, it does not explicitly mention a 'validation' set or its specific split. |
| Hardware Specification | No | The paper does not provide any specific hardware specifications (e.g., CPU/GPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper mentions 'L2-normalized 8192-dimensional Fisher vector [Perronnin and Dance, 2007], using SIFT features to compute it [Lowe, 2004]' and 'linear embedding which is introduced in [Gong et al., 2014]', but does not specify any software names with version numbers. |
| Experiment Setup | Yes | We set different k to show the performance of the 4 methods. ... Table 1 and 2 show F-score, Recall and Precision values over OVP and You Tube datasets with different summary sizes. ...Table 3 shows the performance of all the 5 methods when the segment size equals 10. ... For other 4 methods, we set their summary sizes in the range [T 5, T + 5]. |