Uncertainty-Aware Representation Learning for Action Segmentation
Authors: Lei Chen, Muheng Li, Yueqi Duan, Jie Zhou, Jiwen Lu
IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate our method on three popular action prediction datasets: Breakfast, Georgia Tech Egocentric Activities (GTEA), and 50Salads. The experimental results demonstrate that our method achieves the performance with state-of-the-art. |
| Researcher Affiliation | Academia | 1Beijing National Research Center for Information Science and Technology (BNRist), and the Department of Automation, Tsinghua University 2Department of Electronic Engineering, Tsinghua University chenlei2020@mail.tsinghua.edu.cn, li-mh20@mails.tsinghua.edu.cn, duanyueqi@tsinghua.edu.cn, jzhou@mail.tsinghua.edu.cn, lujiwen@tsinghua.edu.cn |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks (e.g., clearly labeled algorithm sections or code-like formatted procedures). |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described (no specific repository link, explicit code release statement, or mention of code in supplementary materials). |
| Open Datasets | Yes | We evaluate our proposed method on three challenging action segmentation datasets: 50Salads [Stein and Mc Kenna, 2013], Georgia Tech Egocentric Activities (GTEA) [Fathi et al., 2011], and the Breakfast dataset [Hilde et al., 2014]. |
| Dataset Splits | Yes | The 50Salads dataset contains 50 top-view videos of salad preparation with 17 different action classes. The 5-fold cross-validation is performed for evaluation. ... The GTEA dataset ... We use the 4-fold cross-validation to evaluate the performances. ... The Breakfast dataset ... the standard 4-fold cross-validation is used to evaluate the performances. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types with speeds, or memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper mentions using I3D features and backbone models like MS-TCN++, ASRF, and ASFormer, and using Adam optimizer, but it does not specify version numbers for any software libraries, frameworks, or environments used (e.g., Python, PyTorch/TensorFlow, CUDA versions). |
| Experiment Setup | Yes | The extracted feature size is set to 64 for each video frame. ... For the loss function, we set the weight as 0.01 for Lrec (λ1), the weight of the regularization term is set to 1e 4 (λ4), and the weights of all smoothing terms are set to 0.15 (λ2 and λ3). We trained the models for 200 epochs. For optimization, we used Adam optimizer with the learning rate of 0.0005 and the batch size of 1 for all experiments in this paper. |