Research map / Label-efficient and robust learning / Semi-supervised learning
Semi-supervised Visual Tracking of Marine Animals Using Autonomous Underwater Vehicles
Levi Cai, Nathan McGuire, Roger T. Hanlon, T. Aran Mooney, Yogesh Girdhar
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 |
|---|---|---|---|
| use KeepTrack (distractor-aware, built on SuperDiMP) instead of SuperDiMP | SuperDiMP · VMAT | success AUC: 48.5 -> 53.6 | Improved |
| use KeepTrackFast parameters instead of KeepTrack | KeepTrack · VMAT | success AUC: 52.7 -> 53.6 | No clear effect |
| use KeepTrackFast parameters instead of KeepTrack (speed) | KeepTrack · Jetson Xavier | frame rate: 2-4fps -> 7-9fps | Improved |
| add transformer layers to SuperDiMP-style trackers (TrDiMP, TrSiam, TransT) | SuperDiMP · VMAT | success AUC | No clear effect |
| use transformer-based trackers in midwater and active lighting scenes | transformer trackers · VMAT midwater / active lighting | success AUC | Improved |
| use online discriminator-based trackers instead of Siamese-based ones | semi-supervised trackers · VMAT | success AUC | Improved |
| move from simple midwater scenes to coral reef and seagrass habitats | all trackers · VMAT CR and SG subsets | success AUC | Hurt |
Closest papers by meaning
- When Trackers Date Fish: A Benchmark and Framework for Underwater Multiple Fish Tracking (AAAI 2026 · similarity 0.88)
- Context-Driven Detection of Invertebrate Species in Deep-Sea Video (IJCV 2023 · similarity 0.86)
- WebUOT-1M: Advancing Deep Underwater Object Tracking with A Million-Scale Benchmark (NeurIPS 2024 · similarity 0.86)
- Fantastic Animals and Where to Find Them: Segment Any Marine Animal with Dual SAM (CVPR 2024 · similarity 0.85)
- ReefNet: A Large-Scale Dataset and Benchmark for Fine-Grained Coral Reef Recognition (NeurIPS 2026 · similarity 0.82)
- BuckTales: A multi-UAV dataset for multi-object tracking and re-identification of wild antelopes (NeurIPS 2024 · similarity 0.82)
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.
