HOI-aware Adaptive Network for Weakly-supervised Action Segmentation
Authors: Runzhong Zhang, Suchen Wang, Yueqi Duan, Yansong Tang, Yue Zhang, Yap-Peng Tan
IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on two widely-used datasets including Breakfast and 50Salads demonstrate the effectiveness of our method under different evaluation metrics. |
| Researcher Affiliation | Academia | 1Nanyang Technological University 2Tsinghua University 3Beijing Jiaotong University |
| Pseudocode | No | The paper describes algorithms in prose but does not provide structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described. |
| Open Datasets | Yes | We conduct our experiments on two real-world instructional video datasets: Breakfast [Kuehne et al., 2014] and 50Salads [Stein and Mc Kenna, 2013]. |
| Dataset Splits | No | The paper mentions the datasets used (Breakfast and 50Salads) but does not provide explicit details about the training, validation, and test splits (e.g., percentages, sample counts, or specific predefined split citations). |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments. |
| Software Dependencies | No | The paper mentions using components like a pre-trained HOI detector (from 100 Days of Hands), ResNet50, ViT, GRU, and a Hyper Network, but it does not specify version numbers for any software libraries, frameworks, or dependencies. |
| Experiment Setup | Yes | We set 0.5 as the HOI detection threshold and pick K = 10 bounding boxes after the selection process. ... We use D = 128 for the dimension of both HOI-dependent and HOI-independent knowledge, and set the multi-head number as 8. For the adaptive temporal encoder, we use the 64-hidden unit GRU. We maintain the learning rate of 0.01 with 12500 epochs through the training process. |