3D Crowd Counting via Multi-View Fusion with 3D Gaussian Kernels
Authors: Qi Zhang, Antoni B. Chan12837-12844
AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The proposed method is tested on 3 multi-view counting datasets and achieves better or comparable counting performance to the state-of-the-art. |
| Researcher Affiliation | Academia | Qi Zhang, Antoni B. Chan Department of Computer Science, City University of Hong Kong Tat Chee 83, Kowloon Tong, Hong Kong SAR, China qzhang364-c@my.cityu.edu.hk, abchan@cityu.edu.hk |
| Pseudocode | No | The paper describes the system architecture and process flow but does not include structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide an explicit statement about releasing code or a direct link to a code repository for the described methodology. |
| Open Datasets | Yes | The proposed method is evaluated and compared on the 3 multi-view counting datasets, PETS2009 (Ferryman and Shahrokni 2009), Duke MTMC (Ristani, Solera, and et al. 2016) and City Street (Zhang and Chan 2019). |
| Dataset Splits | No | The paper specifies training and testing splits for datasets but does not explicitly define a separate validation dataset split. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running its experiments, such as GPU/CPU models or memory amounts. |
| Software Dependencies | No | The paper does not provide specific details about ancillary software dependencies, such as library names with version numbers. |
| Experiment Setup | Yes | In the first stage, β = 1 means that the single-view 2D supervision is dominant to benefit the feature extraction training; In the second stage, β = 0.01 means the 3D supervision is dominant to accelerate the 3D fusion training; In the third stage, β = 0.01 and γ is variable according to ground-truth setting, which increases the influence of the projection consistency measure (PCM) to further enhance the performance. In all stages, the learning rate is set as 10 4 and the batch size is 1. |