Central South University researcher in 3D LiDAR point cloud tracking for autonomous driving perception.
2
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
1
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-09-19) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.
Research profile
Output—
Not yet computable: the bibliometric snapshot lacks sufficient data for a productivity score. This axis would measure total and per-year publication output. Only fragments exist so far — six indexed records, an h-index of 1, and an i10-index of 0.
Impact—
Not yet computable: citation-based influence could not be assessed from the snapshot. This axis would measure citations per paper and citation trajectories over time. With two 2026 arXiv preprints and an i10-index of 0, citation evidence is essentially absent.
Focus0/100
Scores 0/100. The platform's field distribution splits indexed output evenly — 0.5 and 0.5 — across two nearly identical labels: 3D point cloud tracking for autonomous driving perception, and LiDAR-based 3D tracking. Topic counts reinforce this: "Video Surveillance and Tracking Methods" accounts for 2 of the topic-assigned records. The recorded footprint is therefore extremely narrow, though the six-record base means concentration partly reflects a small sample.
Collaboration39/100
Scores 39/100. The OpenAlex snapshot lists six distinct coauthors; recurring names include Sifan Zhou, Ziyu Zhao, Xiaobo Lu, Qiwei Wang, and Ziyu Liu. Both Evolve-reviewed papers place Tan in a middle authorship position without corresponding-author status, consistent with a contributing member of a small, stable team rather than an independent group lead. The compact coauthor pool supports the moderate score; it should rise if independent or senior-author roles accumulate.
Activity47/100
Scores 47/100. The snapshot records 4 works in the last three years, all concentrated in 2026, against isolated earlier entries in 2006 and 2023. This gives a short, recent burst of output rather than a sustained multi-year record — the four 2026 items, including both Evolve-reviewed arXiv preprints, mark an active current phase, while the thin prior history keeps the score moderate.
Reproducibility55/100
Scores 55/100 — the mean repro-readiness across the 2 papers Evolve has reviewed, both rated "medium". SAVTrack reports consistent roughly 2-3 point KITTI/nuScenes gains at 82 FPS on top of a P2P baseline, though the gains are incremental; MAETrack shows strong ablations, but single-run statistics and a pretraining-data confound persist. Together they suggest published pipelines are followable, with statistical-rigor caveats.
Research summary
Linyue Tan is a computer vision researcher at Central South University (China) whose recorded work concentrates on 3D single object tracking in LiDAR point clouds for autonomous driving perception. Evolve's catalog includes two 2026 arXiv preprints with Tan in a middle authorship position: SAVTrack, which adds motion-conditioned vote gating on top of a P2P baseline for reliability-aware tracking, reporting roughly 2-3 point gains on KITTI/nuScenes at 82 FPS; and MAETrack, which uses shallow-layer masked-autoencoder initialization and search-area gating to exploit pretrained geometric priors. Evolve assesses both as technically sound but incremental, with medium reproducibility readiness; MAETrack's statistics come from single runs and inherit a pretraining-data confound. The bibliometric footprint is early-stage: an OpenAlex-derived snapshot lists six works (one each in 2006 and 2023, four in 2026), an h-index of 1, an i10-index of 0, and six distinct coauthors, including recurring collaborators Sifan Zhou, Ziyu Zhao, Xiaobo Lu, Qiwei Wang, and Ziyu Liu. The field distribution places all indexed output within two overlapping 3D point cloud tracking labels, indicating narrow, deepening specialization. The isolated 2006 record and several off-topic topics, such as diabetes management, likely reflect name-matching noise rather than Tan's research.
Collaboration pattern
Tan's recorded collaboration footprint is a small, stable pool: six distinct coauthors, with Sifan Zhou, Ziyu Zhao, Xiaobo Lu, Qiwei Wang, and Ziyu Liu recurring across records. On both Evolve-reviewed papers Tan appears in a middle authorship position and is not the corresponding author, suggesting a contributing researcher within a team led by others. No independent or cross-institution collaborations are visible in the available data.
Research keywords
Highlights
SAVTrack: selective vote aggregation for reliability-aware point cloud tracking
MAETrack: pretrained geometric priors for 3D single object tracking
Timeline
- 2006Earliest record in the OpenAlex-derived profile: one indexed work, predating the current 3D tracking focus and possibly reflecting name-matching noise.
- 2023One indexed work appears in the snapshot — an isolated entry between the 2006 record and the 2026 output cluster.
- 2026Most active year: four indexed works, including both Evolve-reviewed arXiv preprints — SAVTrack and MAETrack on 3D LiDAR single object tracking.
Papers in the Evolve catalog
Frequent co-authors
About this profile
This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.
- Bibliometric figures come from an OpenAlex-derived snapshot only; no ORCID is linked, so the isolated 2006 entry and off-topic topics (e.g., diabetes management, memory mechanisms) may reflect name-matching noise.
- Output and impact dimensions are not computed; the only available fragments are an h-index of 1, an i10-index of 0, and six indexed works.
- Both reviewed papers are 2026 arXiv preprints; peer-reviewed venue status is not recorded in this data.
- The reproducibility score covers only the 2 papers Evolve has reviewed and may not generalize to all of this researcher's work.