Timestamp-Supervised Action Segmentation from the Perspective of Clustering

Authors: Dazhao Du, Enhan Li, Lingyu Si, Fanjiang Xu, Fuchun Sun

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments show the effectiveness of our method.
Researcher Affiliation Academia 1Institute of Software, Chinese Academy of Science 2University of Chinese Academy of Sciences 3Institute of Computing Technology, Chinese Academy of Sciences 4Department of Computer Science and Technology, Tsinghua University
Pseudocode Yes Algorithm 1 The iterative clustering algorithm
Open Source Code No The paper does not contain an explicit statement about releasing source code or a link to a code repository.
Open Datasets Yes The 50Salads dataset [Stein and Mc Kenna, 2013]
Dataset Splits Yes We perform fourfold cross-validation on the GTEA and Breakfast datasets, and five-fold cross-validation on the 50Salads dataset. For evaluation, we report the average of all the splits.
Hardware Specification No The paper does not provide specific hardware details such as GPU/CPU models, processor types, or memory amounts used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers, such as programming language versions or library versions (e.g., PyTorch, TensorFlow, scikit-learn).
Experiment Setup Yes We train the model for 70 epochs with Adam optimizer [Kingma and Ba, 2014]. Similar to [Li et al., 2021], in the first 50 epochs, we only use the annotated timestamps to train to find a good initialization. Subsequently, we apply the IC algorithm to train for 20 epochs. We use the learning rate 0.0001 for Breakfast and 0.0005 for GTEA and 50Salads. We set λ, β, γ to 0.15, 0.075 and 0.15 respectively.