DVANet: Disentangling View and Action Features for Multi-View Action Recognition
Authors: Nyle Siddiqui, Praveen Tirupattur, Mubarak Shah
AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We show that our model and method of training significantly outperforms all other uni-modal models on four multi-view action recognition datasets: NTU RGB+D, NTU RGB+D 120, PKUMMD, and N-UCLA. Compared to previous RGB works, we see maximal improvements of 1.5%, 4.8%, 2.2%, and 4.8% on each dataset, respectively. Our code can be found here: https://github.com/Nyle Siddiqui/Multi View Actions |
| Researcher Affiliation | Academia | Nyle Siddiqui, Praveen Tirupattur, Mubarak Shah Center for Research in Computer Vision, University of Central Florida nyle.siddiqui@ucf.edu, praveen.tirupattur@ucf.edu, shah@crcv.ucf.edu |
| Pseudocode | No | The paper describes the proposed method but does not include any pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our code can be found here: https://github.com/Nyle Siddiqui/Multi View Actions |
| Open Datasets | Yes | We show that our model and method of training significantly outperforms all other uni-modal models on four multi-view action recognition datasets: NTU RGB+D, NTU RGB+D 120, PKUMMD, and N-UCLA. |
| Dataset Splits | Yes | We show results on three large-scale, multi-view action recognition datasets (NTU RGB+D, NTU RGB+D 120, PKU-MMD) and one smaller scale dataset (N-UCLA) to exhibit the effectiveness of our approach with varying amounts of data. We show results on the standard cross-subject and cross-view evaluation protocols provided for each dataset. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used to run the experiments, such as GPU or CPU models. |
| Software Dependencies | No | The paper does not list specific software dependencies with version numbers. |
| Experiment Setup | No | While the paper describes the general approach and loss formulation, it does not explicitly provide concrete hyperparameter values (e.g., learning rate, batch size, number of epochs, optimizer settings) in the main text. |