Learning Target-aware Representation for Visual Tracking via Informative Interactions
Authors: Mingzhe Guo, Zhipeng Zhang, Heng Fan, Liping Jing, Yilin Lyu, Bing Li, Weiming Hu
IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | A series of experiments are conducted to prove the generality and effectiveness of the proposed Li BN and GIM. |
| Researcher Affiliation | Academia | 1Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University 2National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 3Department of Computer Science and Engineering, University of North Texas, Denton, TX USA |
| Pseudocode | No | The paper does not contain any pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | No | The paper does not include an unambiguous statement about releasing source code for the described methodology or a direct link to a code repository. |
| Open Datasets | Yes | In particular, the training splits of La SOT [Fan et al., 2019], Tracking Net [Muller et al., 2018] and GOT-10k [Huang et al., 2019] and COCO [Lin et al., 2014] are used during learning. |
| Dataset Splits | No | The paper states: 'the training splits of La SOT [Fan et al., 2019], Tracking Net [Muller et al., 2018] and GOT-10k [Huang et al., 2019] and COCO [Lin et al., 2014] are used during learning.' However, it does not explicitly provide the specific percentages or sample counts for validation splits or refer to a standard validation split. It defers detailed training settings to external papers. |
| Hardware Specification | Yes | Notably, CNNIn Mo runs at 47 fps on GTX2080Ti GPU, while Trans In Mo/Trans In Mo* run at 67/34 fps respectively. |
| Software Dependencies | No | The paper mentions using baseline trackers like Siam CAR and Trans T and refers to external papers for training details, but it does not specify any software dependencies with version numbers (e.g., PyTorch 1.x, CUDA 11.x). |
| Experiment Setup | Yes | We employ n = 4, C = 256, and d = 256 to achieve real-time tracking speed without other specified. |