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.
Adaptive Pattern-Parameter Matching for Robust Pedestrian Detection
Authors: Mengyin Liu, Chao Zhu, Jun Wang, Xu-Cheng Yin2154-2162
AAAI 2021 | Venue PDF | LLM Run Details | Input Tokens: 16,688 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,836 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 | Extensive experiments on two popular benchmarks, Caltech and City Persons, show that our proposed method achieves superior performance compared to other state-of-the-art methods on subsets of different scales and occlusion types. |
| Researcher Affiliation | Academia | Mengyin Liu, Chao Zhu*, Jun Wang, Xu-Cheng Yin* School of Computer and Communication Engineering University of Science and Technology Beijing, Beijing, China EMAIL, EMAIL, wj EMAIL, EMAIL |
| Pseudocode | No | The paper describes modules and their functions but does not include any pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any links to open-source code or explicit statements about code availability. |
| Open Datasets | Yes | The Caltech pedestrian dataset (Doll ar et al. 2009) contains 2.5 hours of video data... City Persons (Zhang, Benenson, and Schiele 2017) is a recently published large-scale pedestrian detection dataset. |
| Dataset Splits | Yes | The standard test set includes 4024 images. We train the model on an ofο¬cial training set with 2975 images and test it on validation set with 500 images. |
| Hardware Specification | Yes | For Caltech dataset, one Nvidia P100 GPU is utilized for training. For City Persons, two P40 GPUs are applied to training. All the tests are conducted on a single 1080Ti GPU. |
| Software Dependencies | No | The paper mentions 'Keras framework' and 'Adam' but does not specify version numbers for these software dependencies. |
| Experiment Setup | Yes | For Caltech dataset, ... with 1 Γ 10β4 learning rate. For City Persons, ... with 2 Γ 10β4 learning rate. The size of training images is 336 Γ 448 for Caltech and 640 Γ 1280 for City Persons. For the best ensemble, IoU threshold of NMS after fusing detection results of two policies are 0.54 for Caltech and 0.59 for City Persons. |