Standard deep learning based object detectors suffer from catastrophic forgetting, which results in performance degradation on old classes as new classes are incrementally added. There has been a few recent methods that attempt to address this …
Our ActEV (Activities in Extended Video) experiments from TRECVID 2018 [5] utilized a feature pyramid network (FPN) combined with a deformable convolutional network (DCN) to perform very accurate and fine-grain object detection. This approach …