Visual Tracking with Reliable Memories
Authors: Shu Wang, Shaoting Zhang, Wei Liu, Dimitris N. Metaxas
IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results show that our tracker performs favorably against other stateof-the-art methods on benchmark datasets. |
| Researcher Affiliation | Collaboration | 1CBIM Center, Rutgers University, Piscataway, NJ, USA 2Department of Computer Science, UNC Charlotte, Charlotte, NC, USA 3Didi Research, Beijing, China |
| Pseudocode | Yes | Algorithm 1 Temporal Constrained Clustering Algorithm |
| Open Source Code | No | The paper does not contain any explicit statements or links indicating that the source code for the described methodology is publicly available. It only provides a link to a video clip: 'A video clip with more detailed illustration can be found at https://youtu.be/wtZAGzFDjnM.' |
| Open Datasets | Yes | We first evaluate our method on 50 challenging sequences from OTB-2013 [Wu et al., 2013] against 12 state-of-theart methods |
| Dataset Splits | No | The paper mentions using OTB-2013 and long sequences from Kalal et al. for evaluation, but does not specify explicit training, validation, or test dataset splits (e.g., percentages or sample counts for each split) within these datasets. |
| Hardware Specification | Yes | Our framework is implemented in Matlab with running speed ranges from 12fps to 20fps, on a desktop with an Intel Xeon(R) 3.5GHz CPU, a Tesla K40c video card and 32GB RAM. |
| Software Dependencies | No | The paper mentions 'Matlab', 'HOG [Dalal and Triggs, 2005]', and 'Faster-RCNN (ZF-Net)' but does not provide specific version numbers for these software components. |
| Experiment Setup | Yes | The adaptiveness ratio γ is empirically set as 0.15 through all experiments. Stoping factor is decided adaptively as 1.2 times the average covariance of the samples at the first 40 frames on each video. HOG [Dalal and Triggs, 2005] is chosen as the feature φ( ). The maximum number of memories |U| is set as 10 and max(N u) is set to 100. |