Research map / 3D vision / Human pose estimation
LoTE-Animal: A Long Time-span Dataset for Endangered Animal Behavior Understanding
Dan Liu, Jin Hou, Shaoli Huang, Jing Liu, Yuxin He, Bochuan Zheng, Jifeng Ning, Jingdong Zhang
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 |
|---|---|---|---|
| move from earlier to newer detectors (Faster R-CNN to DiffusionDet) on the web subset | object detection on LoTE-Animal · LoTE-Animal web subset | AP (r50): 55.45 -> 70.65 | Improved |
| move from earlier to newer detectors on the wild subset | object detection on LoTE-Animal · LoTE-Animal wild subset | AP (r50): 69.75 -> 76.13 | Improved |
| newer instance segmentation model (QueryInst vs Mask R-CNN) on web subset | instance segmentation · LoTE-Animal web subset | AP (r50): 57.16 -> 64.98 | Improved |
| newer instance segmentation model (QueryInst vs Mask R-CNN) on wild subset | instance segmentation · LoTE-Animal wild subset | AP (r50): 68.47 -> 67.00 | Hurt |
| test web-trained or wild-trained models on the opposite domain (cross-domain) | detection models · LoTE-Animal cross-domain | AP: decrease of 52.49% to 60.18% | Hurt |
| test web-trained or wild-trained models on the opposite domain | instance segmentation models · LoTE-Animal cross-domain | AP: decrease of 51.95% to 57.96% | Hurt |
| test pose models cross-domain | pose estimation models · LoTE-Animal cross-domain | AP: decrease of 49.54% to 54.83% | Hurt |
| use human-pose-oriented newer networks (SCNet, LiteHRNet, PVTv2) instead of HRNet-style animal pose networks | pose estimation · LoTE-Animal | AP | Hurt |
Closest papers by meaning
- Animal-Bench: Benchmarking Multimodal Video Models for Animal-centric Video Understanding (NeurIPS 2024 · similarity 0.88)
- MammAlps: A Multi-view Video Behavior Monitoring Dataset of Wild Mammals in the Swiss Alps (CVPR 2025 · similarity 0.87)
- The PanAf-FGBG Dataset: Understanding the Impact of Backgrounds in Wildlife Behaviour Recognition (CVPR 2025 · similarity 0.87)
- UniAP: Towards Universal Animal Perception in Vision via Few-Shot Learning (AAAI 2024 · similarity 0.86)
- BuckTales: A multi-UAV dataset for multi-object tracking and re-identification of wild antelopes (NeurIPS 2024 · similarity 0.86)
- Web-Scale Collection of Video Data for 4D Animal Reconstruction (NeurIPS 2025 · similarity 0.85)
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.
