Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
GIF Thumbnails: Attract More Clicks to Your Videos
Authors: Yi Xu, Fan Bai, Yingxuan Shi, Qiuyu Chen, Longwen Gao, Kai Tian, Shuigeng Zhou, Huyang Sun3074-3082
AAAI 2021 | Venue PDF | LLM Run Details | Input Tokens: 18,192 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,030 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on our built dataset show that GEVADEN significantly outperforms several baselines, including video-summarization and highlight-detection based ones. Furthermore, we develop a pilot application of the proposed model on an online video platform with 9814 videos covering 1231 hours, which shows that our model achieves a 37.5% CTR improvement over traditional image thumbnails. |
| Researcher Affiliation | Collaboration | 1Shanghai Key Lab of Intelligent Information Processing, and School of Computer Science, Fudan University, China 2Bilibili, China 3Department of Computer Science, UNC Charlotte |
| Pseudocode | No | The paper describes the model architecture and components but does not provide pseudocode or algorithm blocks. |
| Open Source Code | Yes | Codes and Appendix are available at https://github.com/xyiyy/GIF-Thumbnails |
| Open Datasets | No | While the paper describes building a new dataset ('we build the ο¬rst GIF thumbnails benchmark dataset'), it does not provide concrete access information (e.g., a specific link, DOI, or repository) for this dataset to be publicly accessed. |
| Dataset Splits | Yes | We randomly split the annotated videos from the benchmark dataset into three parts: 857 for training, 106 for validation, and 107 for testing. |
| Hardware Specification | Yes | experiments are conducted on eight NVIDIA Tesla P40s. |
| Software Dependencies | Yes | Networks are implemented in Pytorch v1.3 |
| Experiment Setup | Yes | We train networks via Aadm (Kingma and Ba 2014) optimizer with an initial learning rate of 3 10 4 and a mini-batch size of 16. |