Detect or Track: Towards Cost-Effective Video Object Detection/Tracking
Authors: Hao Luo, Wenxuan Xie, Xinggang Wang, Wenjun Zeng8803-8810
AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Although being light-weight and simple in structure, the scheduler network is more effective than the frame skipping baselines and flow-based approaches, as validated on Image Net VID dataset in video object detection/tracking. |
| Researcher Affiliation | Collaboration | Hao Luo,1 Wenxuan Xie,2 Xinggang Wang,1 Wenjun Zeng2 1School of Electronic Information and Communications, Huazhong University of Science and Technology 2Microsoft Research Asia {luohao, xgwang}@hust.edu.cn, {wenxie, wezeng}@microsoft.com |
| Pseudocode | Yes | Algorithm 1 The Detect or Track (Dor T) Framework |
| Open Source Code | No | The paper does not provide an unambiguous statement or link for the open-source code of the described methodology. |
| Open Datasets | Yes | All experiments are conducted on the Image Net VID dataset (Russakovsky et al. 2015). |
| Dataset Splits | No | The paper mentions 'Image Net VID is split into a training set of 3862 videos and a test set of 555 videos.' but does not provide specific details for a separate validation split. Although it refers to 'validation set' when reporting results, the split details are not provided. |
| Hardware Specification | Yes | All experiments are conducted on a workstation with an Intel Core i7-4790k CPU and a Titan X GPU. |
| Software Dependencies | No | The paper mentions software components like R-FCN, ResNet101, Siam FC, AlexNet, and SGD optimizer, but does not provide specific version numbers for these or other software dependencies required for reproduction. |
| Experiment Setup | Yes | The SGD optimizer is adopted with a learning rate 1e-2, momentum 0.9 and weight decay 5e4. The batch size is set to 32. During testing, we raise the decision threshold of track to δ = 0.97. |