FDDB: A benchmark for face detection in unconstrained settings
Citations
3,980 citations
3,097 citations
2,340 citations
Cites background from "FDDB: A benchmark for face detectio..."
...Our dataset differs from similar “in-the-wild” collections [20, 3, 23, 5] in its annotation of multiple, non-frontal faces in a single image....
[...]
1,458 citations
1,325 citations
Cites background from "FDDB: A benchmark for face detectio..."
...…and obtain high quality localization; • we present a multi-resolution CNN architecture that can be more discriminative than the single resolution CNN with only a fractional overhead; • we further improve the state-of-the-art performance on the Face Detection Data Set and Benchmark (FDDB) [7]....
[...]
References
13,037 citations
11,096 citations
"FDDB: A benchmark for face detectio..." refers methods in this paper
...This dual formulation is exploited by the Hungarian algorithm [11] to obtain the solution for the former problem....
[...]
9,043 citations
"FDDB: A benchmark for face detectio..." refers methods in this paper
...Following the spectral graph-clustering approach [15], we compute the (unnormalized) Laplacian LG of graph G as...
[...]
...We cluster (steps 3-5 of Algorithm 1) using a spectral graph-clustering approach [15]....
[...]
4,105 citations
3,894 citations
"FDDB: A benchmark for face detectio..." refers background in this paper
...[28], the reported performance measures depend on the definition of a “correct” detection result....
[...]
...Moving forward from previous comparisons [28] of approaches that focus on limited head orientations, we intend to evaluate different approaches for the most general, i....
[...]