Research map / Learning theory and algorithms / Clustering
Multi-view Tracking, Re-ID, and Social Network Analysis of a Flock of Visually Similar Birds in an Outdoor Aviary
Shiting Xiao, Yufu Wang, Ammon D. Perkes, Bernd Pfrommer, Marc F. Schmidt, Kostas Daniilidis, Marc A. Badger
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 |
|---|---|---|---|
| replace Stereo Matching single-point reconstruction with dense Pointcloud Reconstruction (ablation) | multi-view bird tracker · WILD (<=100 frames) | AC0.1: 0.17 -> 0.44 | Improved |
| replace Stereo Matching with Pointcloud Reconstruction (ablation) | multi-view bird tracker · WILD (100-300 frames) | AC1.0: 0.47 -> 0.61 | Improved |
| replace Stereo Matching with Pointcloud Reconstruction (ablation) | multi-view bird tracker · WILD (>300 frames) | AC0.1: 0.04 -> 0.16 | Improved |
| use oracle matching through ambiguities in re-tracking (ablation) | Pointcloud tracker · WILD (<=100 frames) | AC1.0: 0.75 -> 0.87 | Improved |
| use oracle matching through ambiguities in re-tracking (ablation) | Pointcloud tracker · WILD (>300 frames) | AC0.1: 0.16 -> 0.36 | Improved |
| increase sequence length from short to long segments | Pointcloud tracker · WILD | AC0.1: 0.44 -> 0.30 -> 0.16 | Hurt |
| set a detection confidence threshold of 0.8 for re-ID (ablation) | ResNet50 re-ID · Bird15 test | accuracy: 68% -> 0.97 accuracy while correctly predicting 52% of samples | Mixed |
| combine Mask R-CNN with Gaussian-mixture background subtraction detections | bird detector · aviary videos | detection of flying birds | Improved |
Closest papers by meaning
- 3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View (ECCV 2020 · similarity 0.90)
- BirdCollect: A Comprehensive Benchmark for Analyzing Dense Bird Flock Attributes (AAAI 2024 · similarity 0.86)
- BuckTales: A multi-UAV dataset for multi-object tracking and re-identification of wild antelopes (NeurIPS 2024 · similarity 0.83)
- SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Prediction (CVPR 2024 · similarity 0.83)
- BEAST3D: animal behavioral analysis and neural encoding from multi-view video via Gaussian splatting (NeurIPS 2026 · similarity 0.83)
- CleverBirds: A Multiple-Choice Benchmark for Fine-grained Human Knowledge Tracing (NeurIPS 2025 · similarity 0.83)
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.
