30Hz Object Detection with DPM V5

114 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

You Only Look Once: Unified, Real-Time Object Detection (2015, methodology): “Real-Time Detectors Train mAP FPS 100Hz DPM [30] 2007 16.”
Scalable, High-Quality Object Detection (2014, methodology): “Sadeghi and Forsyth [17] developed a framework with several conﬁgurable runtime-quality trade-offs and demonstrate real-time detection using DPMs on the PASCAL 2007 detection data.”
Object Detection in 20 Years: A Survey (2019, unknown): “v5 [37], RCNN [16], SPPNet [17], Fast RCNN [18], Faster RCNN [19],”
Adaptive Feeding: Achieving Fast and Accurate Detections by Adaptively Combining Object Detectors (2017, methodology): “After DPM was invented, many DPM-based detectors [24, 30, 6] focused on optimizing different parts in the pipeline.”
Leaving Some Stones Unturned: Dynamic Feature Prioritization for Activity Detection in Streaming Video (2016, background): “Various ways to accelerate object detection have been explored [37]–[40].”
All Weather Perception: Joint Data Association, Tracking, and Classification for Autonomous Ground Vehicles (2016, background): “Recent developments such as (Sadeghi and Forsyth, 2014), (Angelova et al., 2015), and (Cai et al., 2015) have demonstrated real-time implementation by intelligently selecting regions of interest for processing and by utilizing GPU acceleration for DPM implementation.”