Prediction of Head Saliency for Videos
| Model Name | Reference | NSS | CC | SIM | KLD | AUC_Judd |
|---|---|---|---|---|---|---|
| Multi-Viewing Bias Spherical U-Net | Peng-Wen Chen, Tsung-Shan Yang, Pei-Yuan Wu, Chien-Hung Lu | 2.087 | 0.471 | 0.432 | 3.044 | 0.817 |
| SJTU (*) | Yucheng Zhu, Xiongkuo Min, Zhaohui Che, Guangtao Zhai | 1.694 | 0.408 | 0.370 | 4.274 | 0.836 |
| DAIICT (*) | Smit Thakkar, Neelanshi Varia, Manish Narwaria Website: https://sites.google.com/site/narwariam/visual-attention-in-360-degree-content | 1.617 | 0.396 | 0.368 | 4.202 | 0.854 |
| Zhejiang University and TU Ilmenau (*) | Pierre Lebreton, Stephan Fremerey, Alexander Raake, "V-BMS360: A video extention to the BMS360 image saliency model", ICME2018. | 1.614 | 0.383 | 0.350 | 4.995 | 0.815 |
| Wuhan University (*) | Kao Zhang, Yingxue Zhang, Zhenzhong Chen | 1.603 | 0.400 | 0.362 | 4.543 | 0.827 |
Prediction of Head+Eye Saliency for Videos
| Model Name | Reference | NSS | CC | SIM | KLD | AUC_Judd |
|---|---|---|---|---|---|---|
| VAADER/IETR - INSA Rennes | Fangyi Chao, Lu Zhang, Wassim Hamidouche, Olivier Déforges | 2.246 | 0.337 | 0.232 | 7.052 | 0.857 |
| Wuhan University (*) | Kao Zhang, Yingxue Zhang, Zhenzhong Chen | 1.987 | 0.315 | 0.212 | 7.556 | 0.830 |
| SJTU (*) | Yucheng Zhu, Xiongkuo Min, Zhaohui Che, Guangtao Zhai | 1.712 | 0.246 | 0.201 | 7.733 | 0.838 |
Prediction of Eye-gaze Scan-paths for Videos
| Model Name | Reference | VectorSimilarity (Hungarian) |
|---|---|---|
| SJTU (*) | Yucheng Zhu, Xiongkuo Min, Zhaohui Che, Guangtao Zhai | 0.282 |
Prediction of Head-gaze Scan-paths for Videos
| Model Name | Reference | VectorSimilarity (Hungarian) |
|---|---|---|
| SJTU (*) | Yucheng Zhu, Xiongkuo Min, Zhaohui Che, Guangtao Zhai | 0.277 |
(*) Model submitted during the ICME’18 Grand Challenge, thus under different conditions (e.g. limited time, etc.).