Research map / Detection and segmentation / Tracking
Object Tracking using Spatio-Temporal Networks for Future Prediction Location
Yuan Liu, Ruoteng Li, Yu Cheng, Robby T. Tan, Xiubao Sui
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add trajectory prediction to DiMP tracker | DiMP · VOT2019 | robustness (failure rate): 0.361 -> 0.311 | Improved |
| add trajectory prediction to DiMP tracker | DiMP · OTB-100 | AUC: 67.7 -> 69.3 | Improved |
| add trajectory prediction to DiMP tracker | DiMP · UAV123 | AUC: 64.3 -> 64.9 | Improved |
| add trajectory prediction to DiMP tracker | DiMP · OTB-100 occlusion attribute | AUC: 63.5 -> 67.0 | Improved |
| add trajectory prediction to DiMP tracker | DiMP · UAV123 in-plane rotation attribute | AUC: 47.8 -> 47.1 | Hurt |
| add trajectory prediction to DiMP tracker | DiMP · OTB-100 fast motion attribute | AUC: 68.5 -> 69.0 | No clear effect |
| add trajectory prediction to SiamMask | SiamMask · VOT2018 | EAO: 0.380 -> 0.398 | Improved |
| add trajectory prediction to SiamMask-LD | SiamMask-LD · VOT2018 | robustness (failure rate): 0.234 -> 0.201 | Improved |
| add trajectory prediction to SiamMask-LD | SiamMask-LD · VOT2018 | speed (FPS): 43 -> 13 | Hurt |
| add background motion cue (ablation) | trajectory prediction network · VOT2018 | EAO: 0.394 -> 0.436 | Improved |
| add image cue (ablation) | trajectory prediction network · VOT2018 | EAO: 0.434 -> 0.436 | Improved |
| use location map instead of raw location value (ablation) | trajectory prediction network · VOT2018 | EAO: 0.429 -> 0.436 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ATOM — ATOM: Accurate Tracking by Overlap Maximization (CVPR 2019) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Robust Object Tracking Based on Temporal and Spatial Deep Networks (ICCV 2017 · similarity 0.89)
- Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking (CVPR 2023 · similarity 0.89)
- SpOT: Spatiotemporal Modeling for 3D Object Tracking (ECCV 2022 · similarity 0.89)
- Learning Spatio-Temporal Transformer for Visual Tracking (ICCV 2021 · similarity 0.89)
- Track-On: Transformer-based Online Point Tracking with Memory (ICLR 2025 · similarity 0.88)
- Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
