Preserving Modes and Messages via Diverse Particle Selection

Authors: Jason Pacheco, Silvia Zuffi, Michael Black, Erik Sudderth

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

Reproducibility Variable Result LLM Response
Research Type Experimental Section 4 provides an extensive validation on the challenging problem of articulated human pose estimation from single images, demonstrating state-of-the-art performance and significant improvements over other particle max-product algorithms.
Researcher Affiliation Academia Jason Pacheco* PACHECOJ@CS.BROWN.EDU Department of Computer Science, Brown University, Providence, RI 02912, USA Silvia Zuffi* SILVIA.ZUFFI@TUE.MPG.DE Max Planck Institute for Intelligent Systems, 72076 T ubingen, Germany; ITC-CNR, 20133 Milan, Italy Michael J. Black BLACK@TUE.MPG.DE Max Planck Institute for Intelligent Systems, 72076 T ubingen, Germany Erik B. Sudderth SUDDERTH@CS.BROWN.EDU Department of Computer Science, Brown University, Providence, RI 02912, USA
Pseudocode No The paper includes flowcharts in Figure 1 illustrating the algorithms but does not provide structured pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any statement about releasing source code or provide a link to a code repository for the described methodology.
Open Datasets Yes We demonstrate the robustness of our proposed algorithm on the Buffy the Vampire Slayer dataset (Ferrari et al., 2008), a widely used benchmark for evaluating pose estimation methods based on part-based models.
Dataset Splits Yes The dataset consists of a standard partition of 276 test images and about 500 training images.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used to run the experiments.
Software Dependencies No The paper mentions general software components like 'SVM classifier' and 'logistic regression', but does not list any specific software dependencies or libraries with version numbers.
Experiment Setup Yes For all methods we use 200 particles and run for 300 iterations.