Fast Training of Pose Detectors in the Fourier Domain

Authors: João F. Henriques, Pedro Martins, Rui F Caseiro, Jorge Batista

NeurIPS 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental To demonstrate the generality of the proposed model, we conducted object detection and pose estimation experiments on 3 widely different settings, which will be described shortly. ... For the performance evaluation, ground truth objects are assigned to hypothesis by the widely used Pascal criterion of bounding box overlap [7]. We then measure average precision (AP) and pose error...
Researcher Affiliation Academia Jo ao F. Henriques Pedro Martins Rui Caseiro Jorge Batista Institute of Systems and Robotics University of Coimbra {henriques,pedromartins,ruicaseiro,batista}@isr.uc.pt
Pseudocode Yes We give a Matlab implementation in Appendix B, which can use any off-the-shelf SVR solver without modification.
Open Source Code Yes The supplemental material is available at: www.isr.uc.pt/ henriques/transformations/
Open Datasets Yes Our first test will be on a car detection task on satellite imagery [12]... We used TUD-Campus for training and TUD-Crossing for testing (see Fig. 2)... We chose the very recent KITTI benchmark [9]...
Dataset Splits Yes The first 7 annotated images were used for training, and the remaining 8 for validation.
Hardware Specification No The paper states "we report timings for single-core implementations" but does not specify any particular hardware components like CPU or GPU models, or memory details.
Software Dependencies No The paper mentions "Matlab implementation" and "off-the-shelf SVR solver" but does not provide specific version numbers for these software components.
Experiment Setup No The paper mentions implementing a detector based on HOG templates and training with RR and SVR, but it does not specify concrete experimental setup details such as hyperparameters (e.g., learning rate, batch size, number of epochs) or specific optimizer settings.