Research map / Video / Action recognition
Recognizing Car Fluents From Video
Bo Li, Tianfu Wu, Caiming Xiong, Song-Chun Zhu
Check 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 |
|---|---|---|---|
| Combine TPS with iDT | Car fluent recognition · Car-Fluent | MP: 34.4 -> 45.0 | Improved |
| Add C3D features to TPS+iDT | Car fluent recognition · Car-Fluent | MP: 45.0 -> 50.8 | Improved |
| Use ST-AOG with HOG instead of CNN features | ST-AOG part localization · Car-Fluent | mean part detection rate: 29.0 -> 48.3 | Improved |
| Use cascade car detection | ST-AOG part localization · Car-Fluent | mean part detection rate: 48.3 -> 44.6 | Hurt |
| Add view penalty (ablation) | ST-AOG part status estimation · Car-Fluent | part status detection rate | Improved |
| Add part status penalty (ablation) | ST-AOG part status estimation · Car-Fluent | part status detection rate | Improved |
| Add motion flow (ablation) | ST-AOG part status estimation · Car-Fluent | part status detection rate | Mixed |
| Add view and part status penalties (ablation) | ST-AOG part status estimation · Car-Fluent | part status detection rate | Mixed |
Closest papers by meaning
- Learning And-Or Model to Represent Context and Occlusion for Car Detection and Viewpoint Estimation (TPAMI 2016 · similarity 0.87)
- Structural Information Guided Multimodal Pre-training for Vehicle-Centric Perception (AAAI 2024 · similarity 0.82)
- Infer the Whole from a Glimpse of a Part: Keypoint-Based Knowledge Graph for Vehicle Re-Identification (AAAI 2025 · similarity 0.82)
- On-Road Object Importance Estimation: A New Dataset and A Model with Multi-Fold Top-Down Guidance (NeurIPS 2024 · similarity 0.81)
- Weakly Supervised Semantic Segmentation for Driving Scenes (AAAI 2024 · similarity 0.81)
- Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models (NeurIPS 2025 · similarity 0.81)
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.
