CliqueCNN: Deep Unsupervised Exemplar Learning

Authors: Miguel A. Bautista, Artsiom Sanakoyeu, Ekaterina Tikhoncheva, Bjorn Ommer

NeurIPS 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In the experimental evaluation the proposed approach significantly improves over state-of-the-art approaches for posture analysis and retrieval by learning a general feature representation for human pose that can be transferred across datasets.
Researcher Affiliation Academia Miguel A. Bautista , Artsiom Sanakoyeu , Ekaterina Sutter, Björn Ommer Heidelberg Collaboratory for Image Processing IWR, Heidelberg University, Germany firstname.lastname@iwr.uni-heidelberg.de
Pseudocode No The paper describes its algorithm and optimization steps using equations and textual explanations, but it does not provide a formal pseudocode block or algorithm listing.
Open Source Code Yes Project on Git Hub: https://github.com/asanakoy/cliquecnn
Open Datasets Yes The Olympic Sports dataset [16] is a video compilation of different sports competitions. The Leeds Sports Dataset [12] is the most widely used benchmark for pose estimation. ... PASCAL VOC 2007 dataset.
Dataset Splits No The paper mentions training data and test data but does not explicitly specify a separate validation set or its split/size for any of the datasets used.
Hardware Specification Yes We are grateful to the NVIDIA corporation for donating a Titan X GPU.
Software Dependencies No The paper mentions 'caffe implementation' but does not specify its version number or any other software dependencies with version numbers.
Experiment Setup Yes Batches for training the network are obtained by solving the optimization problem in Eq. (1) with B = 100, K = 100, and r = 20 and fine-tuning the model for 105 iterations.