Skating-Mixer: Long-Term Sport Audio-Visual Modeling with MLPs
Authors: Jingfei Xia, Mingchen Zhuge, Tiantian Geng, Shun Fan, Yuantai Wei, Zhenyu He, Feng Zheng
AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments show the proposed method achieves SOTAs over all major metrics on the public Fis-V and our FS1000 dataset. |
| Researcher Affiliation | Academia | Jingfei Xia*1,2, Mingchen Zhuge*1,3, Tiantian Geng1, Shun Fan1, Yuantai Wei1, Zhenyu He4, Feng Zheng 1 1Southern University of Science and Technology 2The Chinese University of Hong Kong 3AI Initiative, King Abdullah University of Science and Technology (KAUST) 4Harbin Institute of Technology (Shenzhen) |
| Pseudocode | No | The paper describes the model architecture and its components (Memory Recurrent Unit, Bi-Direction Mixer) in detail with text and figures (Figure 1, Figure 3), but it does not include any explicitly labeled 'Pseudocode' or 'Algorithm' blocks. |
| Open Source Code | No | The paper does not contain an explicit statement about releasing the source code for the described methodology, nor does it provide a link to a code repository. |
| Open Datasets | Yes | Aside from the model, we collected a high-quality audio-visual FS1000 dataset, which contains over 1000 videos on 8 types of programs with 7 different rating metrics, overtaking other datasets in both quantity and diversity. |
| Dataset Splits | Yes | Fis-V dataset (Xu et al. 2019) contains 400 ladies short program videos for training and 100 videos for validation. Our proposed FS1000 dataset contains a training set of 1000 videos and a validation set of 247 videos. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., GPU model, CPU model, memory) used to run the experiments. |
| Software Dependencies | No | The paper mentions using AST and Time Sformer as feature extractors, but it does not specify version numbers for these tools or any other software dependencies like Python, PyTorch, or TensorFlow. |
| Experiment Setup | No | The paper describes the model architecture and experimental results, but it does not provide specific details regarding hyperparameter values such as learning rate, batch size, number of epochs, or optimizer settings, which are crucial for reproducing the experimental setup. |