Associating Neural Word Embeddings With Deep Image Representations Using Fisher Vectors
Open paper
Benchmark
Model
Rank
Results
video-retrieval-on-youcook2
HGLMM FV CCA
–
text-to-video R@1: 4.6
text-to-video R@5: 14.3
text-to-video R@10: 21.6
…
Rank counts only results with a code link.