There are some great videolectures online from CVPR this year.
Two I find particularly intresting are
Layered Object Detection for Multiclass Segmentation
Cascade Object Detection with Deformable Part Models.
The former basically uses sliding window classifiers for detection and shape priors to generate segmentations from detections.
The second is an interesting continuation on Felzenszwalb's part based models.
The talk explains how to use a cascade to speed up detection.