Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
A Self Validation Network for Object-Level Human Attention Estimation
Authors: Zehua Zhang, Chen Yu, David Crandall
NeurIPS 2019 | Venue PDF | LLM Run Details | Input Tokens: 18,935 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 5,062 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate on two public datasets, demonstrating that the Self Validation Module significantly benefits both training and testing and that our model outperforms the state-of-the-art. |
| Researcher Affiliation | Academia | Zehua Zhang,1 Chen Yu,2 David Crandall1 1Luddy School of Informatics, Computing, and Engineering 2Department of Psychological and Brain Sciences Indiana University Bloomington EMAIL |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | More information is available at http://vision.soic.indiana.edu/mindreader/. This link points to a project page, not an explicit code repository or a statement of code release for the methodology. |
| Open Datasets | Yes | We evaluate on two public datasets, ATT [68] (Adult-Toddler Toy play) and Epic-Kitchen Dataset [13]. |
| Dataset Splits | Yes | We randomly select 90% of the samples in each object class for training and use the remaining 10% for testing, resulting in about 17, 000 training and 1, 900 testing samples, each with 15 continuous frames. ... We randomly select 90% of samples for training, yielding about 120, 000 training and 13, 000 testing samples. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU models, CPU types, or memory) used for running its experiments. |
| Software Dependencies | No | We implemented our model with Keras [12] and Tensorflow [1]. No specific version numbers are provided for these software dependencies. |
| Experiment Setup | Yes | We use stochastic gradient descent with learning rate 0.03, momentum 0.9, decay 0.0001, and L2 regularizer 5e 5. The loss function consists of four parts: global classification Lglobalclass, attention Lattn, anchor box classification Lboxclass, and box regression Lbox, Ltotal = αLglobalclass + βLattn + 1 Npos (γLboxclass + Lbox), where we empirically set α = β = γ = 1. |