Research map / Video / Video generation
Early Anticipation of Driving Maneuvers
Abdul Wasi Lone, Shankar Gangisetty, Shyam Nandan Rai, C. V. Jawahar
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 gaze modality to multi-view input (ablation) | M2MVT · DAAD | accuracy: 63.28 -> 65.59 | Improved |
| add front view (ablation) | M2MVT · DAAD | accuracy: 60.53 -> 65.59 | Improved |
| add in-cabin driver view (ablation) | M2MVT · DAAD | accuracy: 63.82 -> 65.59 | Improved |
| increase episodic memory tokens from 0 to 12 (ablation) | M2MVT · DAAD | accuracy: 63.46 -> 65.59 | Improved |
| increase memory tokens from 12 to 16 (ablation) | M2MVT · DAAD | accuracy: 65.59 -> 65.35 | Hurt |
| replace ViT encoder with M2MVT hybrid-fusion multiscale encoder | CEMFormer · DAAD (all views + gaze) | accuracy: 60.74 -> 65.59 | Improved |
| replace MViTv2 encoder with M2MVT fusion design | MViTv2 · DAAD (all views + gaze) | accuracy: 62.78 -> 65.59 | Improved |
| train and test on longer videos including before-maneuver (BM) context rather than only maneuver (DM) clips | M2MVT · DAAD | anticipation accuracy before onset | Improved |
| move from short DIP datasets to longer DAAD videos | existing DIP baselines · DAAD vs Brain4Cars | accuracy: 83.37 -> 58.33 (CEMFormer, in and out-cabin) | Hurt |
Closest papers by meaning
- Progressive Risk Estimation for Accident Anticipation (NeurIPS 2026 · similarity 0.87)
- Leveraging Driver Field-of-View for Multimodal Ego-Trajectory Prediction (ICLR 2025 · similarity 0.86)
- Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving (CVPR 2024 · similarity 0.85)
- Dual-View Interaction-Aware Lane Change Prediction for Autonomous Driving (AAAI 2025 · similarity 0.85)
- BAT: Behavior-Aware Human-Like Trajectory Prediction for Autonomous Driving (AAAI 2024 · similarity 0.85)
- Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving (NeurIPS 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.
