Research map / Video / Video segmentation and tracking
Spatiotemporal Modeling for Crowd Counting in Videos
Feng Xiong, Xingjian Shi, Dit-Yan Yeung
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 temporal connections between ConvLSTM cells (ablation) | ConvLSTM-nt · UCSD | MAE: 1.73 -> 1.30 | Improved |
| add temporal connections between ConvLSTM cells (ablation) | ConvLSTM-nt · UCSD | MSE: 3.52 -> 1.79 | Improved |
| make ConvLSTM bidirectional (ablation) | ConvLSTM · UCSD | MAE: 1.30 -> 1.13 | Improved |
| make ConvLSTM bidirectional (ablation) | ConvLSTM · UCSD | MSE: 1.79 -> 1.43 | Improved |
| add temporal connections between ConvLSTM cells (ablation) | ConvLSTM-nt · Mall | MAE: 2.53 -> 2.24 | Improved |
| add temporal connections between ConvLSTM cells (ablation) | ConvLSTM-nt · Mall | MSE: 11.2 -> 8.5 | Improved |
| make ConvLSTM bidirectional (ablation) | ConvLSTM · Mall | MAE: 2.24 -> 2.10 | Improved |
| make ConvLSTM bidirectional (ablation) | ConvLSTM · Mall | MSE: 8.5 -> 7.6 | Improved |
| add temporal connections between ConvLSTM cells (ablation) | ConvLSTM-nt · WorldExpo (average over 5 test scenes) | MAE: 11.9 -> 10.9 | Improved |
| make ConvLSTM bidirectional (ablation) | ConvLSTM · WorldExpo (average over 5 test scenes) | MAE: 10.9 -> 10.6 | Improved |
| add temporal modeling (bidirectional ConvLSTM over ConvLSTM-nt) (ablation) | ConvLSTM-nt · WorldExpo (scene 3) | MAE: 14.6 -> 14.9 | Hurt |
| train on one dataset and adapt with 50 frames of the other | Bidirectional ConvLSTM · Transfer UCSD to Mall | MAE: 3.55 -> 2.63 | Improved |
Closest papers by meaning
- Adapting Lightweight Image-based Counting Models for Video Crowd Counting (CVPR 2026 · similarity 0.92)
- Switching Convolutional Neural Network for Crowd Counting (CVPR 2017 · similarity 0.91)
- Single-Image Crowd Counting via Multi-Column Convolutional Neural Network (CVPR 2016 · similarity 0.90)
- Iterative Crowd Counting (ECCV 2018 · similarity 0.90)
- Context-Aware Crowd Counting (CVPR 2019 · similarity 0.90)
- Wide-Area Crowd Counting via Ground-Plane Density Maps and Multi-View Fusion CNNs (CVPR 2019 · similarity 0.89)
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.
