Research map / Video / Video segmentation and tracking
Slicing Convolutional Neural Network for Crowd Video Understanding
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 semantic rather than raw temporal slices for the xy branch (ablation) | S-CNN-xy · WWW Crowd test | mean AP: 49.56 -> 54.97 (τ=20); 52.05 -> 55.31 (τ=50) | Helped |
| Extend semantic temporal slices from 20 to 100 frames (ablation) | S-CNN-xy · WWW Crowd test | mean AP: 54.97 -> 55.67 | Helped |
| Combine xy, xt, and yt branches instead of using a single branch (ablation) | S-CNN · WWW Crowd test | mean AP: 59.25 -> 62.55 | Helped |
| Prune feature cuboids using the proposed relevance criteria, retaining 256 (ablation) | S-CNN · WWW Crowd test | mean AP: 62.55 -> 60.13 | Hurt |
| Randomly prune feature cuboids to 256 instead of selecting relevant cuboids (ablation) | S-CNN · WWW Crowd test | mean AP: 60.13 -> 57.03 | Hurt |
Closest papers by meaning
- Switching Convolutional Neural Network for Crowd Counting (CVPR 2017 · similarity 0.87)
- Single-Image Crowd Counting via Multi-Column Convolutional Neural Network (CVPR 2016 · similarity 0.87)
- Divide and Grow: Capturing Huge Diversity in Crowd Images With Incrementally Growing CNN (CVPR 2018 · similarity 0.87)
- Top-Down Feedback for Crowd Counting Convolutional Neural Network (AAAI 2018 · similarity 0.85)
- Context-Aware Crowd Counting (CVPR 2019 · similarity 0.85)
- Gramformer: Learning Crowd Counting via Graph-Modulated Transformer (AAAI 2024 · similarity 0.84)
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.