Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval

Benchmark Model Rank Results
ad-hoc-video-search-on-trecvid-avs16-iacc-3LAFF#1infAP: 0.222
ad-hoc-video-search-on-trecvid-avs17-iacc-3LAFF#1infAP: 0.290
ad-hoc-video-search-on-trecvid-avs18-iacc-3LAFF#1infAP: 0.147
video-retrieval-on-msr-vttLAFF#19text-to-video R@1: 29.1text-to-video R@5: 54.9
video-retrieval-on-msr-vtt-1kaLAFF#29text-to-video R@1: 45.8text-to-video R@5: 71.5text-to-video R@10: 82
video-retrieval-on-msvdLAFF#16text-to-video R@1: 45.4text-to-video R@5: 76.0
video-retrieval-on-vatexLAFF#10text-to-video R@1: 59.1text-to-video R@10: 91.7