Claude Code-Driving Scenario Mining for the Argoverse 2 Challenge
Not on the map. Why?
Abstract (arXiv)
We present our submission to the CVPR 2026 Argoverse 2 Scenario Mining Challenge. Our system uses a four-stage pipeline: (1) autonomous code generation via a Claude Code agent powered by GLM~5.1, (2) iterative training set screening with Timestamp Balanced Accuracy threshold 0.8 to curate few-shot examples, (3) semantic code review by a separate Claude Code session, and (4) Qwen3-VL scene-level verification to filter false positives. We report results on the Argoverse 2 test set.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 10 of its 15 references that are in the map. First posted on arXiv 8 Jun 2026.
Builds on
10 of 15 references.
References · 10
- 2024T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Drivingcited by 35
- 2023Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Featurecited by 21
- 2025Action Quality Assessment via Hierarchical Pose-guided Multi-stage Contrastive Regressioncited by 21
- 2025Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoningcited by 20
- 2025DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistencycited by 15
- 2025SafeDriveRAG: Towards Safe Autonomous Driving with Knowledge Graph-based Retrieval-Augmented Generationcited by 14
- 2025RefAV: Towards Planning-Centric Scenario Miningcited by 13
- 2025Explainable Action Form Assessment by Exploiting Multimodal Chain-of-Thoughts Reasoningcited by 13
- 2025Towards Balanced Multi-Modal Learning in 3D Human Pose Estimationcited by 11
- 2023Technical Report for Argoverse Challenges on Unified Sensor-based Detection, Tracking, and Forecastingcited by 8
Built on by
Not cited yet.