SPSTracker: Sub-Peak Suppression of Response Map for Robust Object Tracking
Authors: Qintao Hu, Lijun Zhou, Xiaoxiao Wang, Yao Mao, Jianlin Zhang, Qixiang Ye10989-10996
AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on the OTB, NFS and VOT2018 benchmarks demonstrate that SPSTrack outperforms the state-of-the-art real-time trackers with significant margins1 |
| Researcher Affiliation | Academia | Qintao Hu,1,2,3 Lijun Zhou,2,3,4 Xiaoxiao Wang,5 Yao Mao,1,2 Jianlin Zhang,1,2 Qixiang Ye3 1Key Laboratory of Optical Engineering, Chinese Academy of Sciences, Chengdu , China 2 Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu , China 3University of Chinese Academy of Sciences, Beijing , China 4TU Kaiserslautern, Kaiserslautern, Germany 5University of California, Davis, USA |
| Pseudocode | No | The paper does not contain any clearly labeled 'Pseudocode' or 'Algorithm' blocks. |
| Open Source Code | Yes | 1The code is available at. github.com/Tracker LB/SPSTracker |
| Open Datasets | Yes | Experiments on the OTB, NFS and VOT2018 benchmarks demonstrate that SPSTrack outperforms the state-of-the-art real-time trackers with significant margins1 |
| Dataset Splits | No | The paper mentions 'training samples' and performs an 'ablation study' on VOT2018, but it does not provide specific train/validation/test dataset splits (e.g., percentages or counts) or a detailed splitting methodology required for reproduction. |
| Hardware Specification | Yes | All the experiments are carried out with Pytorch on a Intel i5-8600k 3.4GHz CPU and a single Nvidia GTX 1080ti GPU with 24GB memory. |
| Software Dependencies | No | The paper mentions 'Pytorch' but does not specify a version number or list other key software components with their respective versions. |
| Experiment Setup | Yes | SPSTracker is implemented upon the ATOM architecture (Danelljan et al. 2019), by using Res Net-18 (He et al. 2016) pre-trained on Image Net as the backbone network. The Block3 and Block4 features extracted from the test image are first passed through two Conv layers. Regions defined by the input bounding boxes are then pooled to a fixed size using pooling layers. The pooled features are modulated by channel-wise multiplication with the coefficient vector returned by the reference branch. The features are then passed through fully-connected layers to predict the Intersection over Union (Io U). All Conv and FC layers are followed by Batch Norm and Re LU. |