Research map / Video / Video segmentation and tracking
Highway Vehicle Counting in Compressed Domain
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 |
|---|---|---|---|
| add all proposed compressed-domain features instead of using size features only (ablation) | HCR · UCSD highway traffic dataset, first splitting strategy | MAE: 2.935 -> 2.593 | Helped |
| add all proposed compressed-domain features instead of using size features only (ablation) | HCR · UCSD highway traffic dataset, second splitting strategy | MAE: 3.332 -> 2.938 | Helped |
| add shape features to size features (ablation) | HCR · UCSD highway traffic dataset, first splitting strategy | MAE: 2.935 -> 2.808 | Helped |
| add shape features to size features (ablation) | HCR · UCSD highway traffic dataset, second splitting strategy | MAE: 3.332 -> 3.173 | Helped |
| add HOMV features to size and shape features (ablation) | HCR · UCSD highway traffic dataset, first splitting strategy | MAE: 2.808 -> 2.702 | Helped |
| add HOMV features to size and shape features (ablation) | HCR · UCSD highway traffic dataset, second splitting strategy | MAE: 3.173 -> 3.111 | Helped |
| add the LBP texture feature to size, shape, and HOMV features (ablation) | HCR · UCSD highway traffic dataset, first splitting strategy | MAE: 2.702 -> 2.593 | Helped |
| add the LBP texture feature to size, shape, and HOMV features (ablation) | HCR · UCSD highway traffic dataset, second splitting strategy | MAE: 3.111 -> 2.938 | Helped |
| replace HCR with a single Gaussian Process regression model (ablation) | compressed-domain vehicle counting · UCSD highway traffic dataset | MAE | Hurt |
| remove the second-layer boundary classifiers from HCR (ablation) | compressed-domain vehicle counting · UCSD highway traffic dataset | MAE | Hurt |
Closest papers by meaning
- On-Road Object Importance Estimation: A New Dataset and A Model with Multi-Fold Top-Down Guidance (NeurIPS 2024 · similarity 0.82)
- Traffic Scene Parsing through the TSP6K Dataset (CVPR 2024 · similarity 0.81)
- Unveiling the Hidden: Online Vectorized HD Map Construction with Clip-Level Token Interaction and Propagation (NeurIPS 2024 · similarity 0.80)
- Referring Expression Counting (CVPR 2024 · similarity 0.80)
- Efficient Masked AutoEncoder for Video Object Counting and A Large-Scale Benchmark (ICLR 2025 · similarity 0.80)
- Point Segment and Count: A Generalized Framework for Object Counting (CVPR 2024 · similarity 0.80)
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.