Research Article

Research on Video Captioning Based on Multifeature Fusion

Table 2

Comparing the experimental results with the top five model structures in the second MSR-VTT challenge.

RankOrganizationBLEU4METEORROUGELCIDEr

1RUC&CMU0.3900.2550.5420.315
2TJU0.3590.2260.5150.249
3NII0.3590.2340.5140.231
4Tongji University0.3510.2260.5090.236
5IIT Delhi0.3040.2130.4940.206
 Ours0.4430.3270.6190.521