- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper introduces a benchmark of approximately 4,650 real-world dashcam videos covering 20 fine-grained behaviors grouped into six California Vehicle Code violation families. Its case-file annotations include behavior labels, responsible actors, decisive timestamps, statute references and human-reviewed rationales/evidence.
It also proposes iCluedo, a training-free pipeline combining frozen perception tools, persistent spatio-temporal memory, competing hypotheses and a READ–ASK–INSPECT–DECIDE investigation loop. Additional evidence is acquired to resolve missing or unreliable clues, followed by consistency verification and deterministic mapping to a statute. On the reported evaluation subset, classification accuracy improves from 30.6% to 50.6%, while macro F1 improves from 0.382 to 0.423. Further experiments characterize actor/time grounding and top-two hypothesis recovery.
Critical strengths
- the formulation sounds useful, instead of just a label-only traffic-video analysis. The case-file representation not only asks what happened, but also who acted, where the decisive event occurred and what evidence supports the conclusion.
- the paper proposes a task-aligned investigation architecture with promising initial results.
Critical weaknesses
- evaluation coverage and alignment with the case-level claims are not very clear. Section 3 describes six violation families plus no-violation as closed-set categories, but Table 2 reports only five families, with supports totaling 3,264 clips. The manuscript does not clearly reconcile these supports with the approximately 4,650-video dataset or account for Special Stops, no-violation, Unknown and invalid predictions. Section 5.1 evaluates only clips for which every method returns a valid prediction. This provides matched coverage within the selected subset, but exclusion counts, class composition and per-model validity rates are necessary to interpret the headline score. This is not evidence of deliberate selection bias; it is an unresolved protocol question. These gaps affect what the benchmark and reported gains actually establish.
- The claimed benefit of clue-directed investigation is not isolated, and some of the reproduction details are missing. The method combines structured perception, tracking, scene memory, multiple model calls and adaptive video inspection, while the main baselines use fixed-context raw-video prompting. This can demonstrate a system-level improvement, but it does not identify the contribution of clue-conditioned investigation rather than better inputs, different models, additional observations or greater inference expenditure.
Questions for authors
- how does iCluedo compare with a similar computation budget, similar architecture system with non-clue-directed inspection policy? It would help isolate the proposed investigation mechanisum
- Could you clarify the temporal-evaluation population and provide corresponding baseline actor/time results? What systematic evaluation supports the evidence-grounding claim beyond the qualitative examples?
3 comments
W2/Q1: Isolating clue-directed investigation and clarifying implementation details
Reviewer’s question: How does iCluedo compare with a similarly structured system using non-clue-directed inspection under a comparable computation budget?
Response:
We agree that comparisons with fixed-context, raw-video VLMs alone cannot isolate the contribution of clue-directed investigation. To strengthen the comparison, we added iFinder [1], a training-free structured-perception pipeline that does not employ the scene graph and clue-driven investigation used by iCluedo. The iFinder use perception toolchain. The perception models are pretrained and frozen, with no fine-tuning on CVCV.
We have already presented the comparison across the seven CVCV violation categories in our response to the first reviewer concern. We further expanded the evaluation beyond the original family-level setting by conducting additional experiments covering fine-grained recognition across 19 primary violation labels, reporting MRR, Top-1, Top-3, and Top-10 accuracy, precision, recall, and F1-score.
Table 1. Fine-grained primary violation recognition (%). Best results in each column are highlighted in bold.
| Model | MRR↑ | Top-1 Acc. | P@1 | R@1 | F1@1 | Top-3 Acc. | P@3 | R@3 | F1@3 | Top-10 Acc. | P@10 | R@10 | F1@10 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Cosmos-Reason2-8B | 23.9 | 19.1 | 25.5 | 18.6 | 15.2 | 25.7 | 39.9 | 25.0 | 22.2 | 38.2 | 72.2 | 37.1 | 38.6 |
| Qwen3-VL-8B | 37.2 | 19.9 | 25.9 | 19.3 | 15.5 | 47.8 | 55.5 | 48.3 | 44.2 | 80.1 | 86.1 | 80.7 | 79.4 |
| iFinder | 39.4 | 23.8 | 15.9 | 13.1 | 10.9 | 45.2 | 47.3 | 36.9 | 37.2 | 81.0 | 92.8 | 81.0 | 82.3 |
| iCluedo (Ours) | 42.2 | 25.7 | 50.4 | 26.0 | 26.1 | 53.7 | 69.6 | 54.0 | 52.8 | 82.4 | 87.1 | 82.4 | 81.6 |
At the primary-label level, iCluedo improves over iFinder from 23.8% to 25.7% Top-1 accuracy, from 45.2% to 53.7% Top-3 accuracy, and from 39.4% to 42.2% MRR. F1@1 also improves from 10.9% to 26.1%. These results extend the comparison to fine-grained behavior recognition and support the benefit of the complete iCluedo framework over the structured-perception baseline.
Implementation details. The clue-driven investigation operates through four actions: READ, ASK, INSPECT, and DECIDE. The implementation settings are summarized below.
Table 2. iCluedo implementation settings.
| Component | Setting |
|---|---|
| Reasoning models | GLM-5.2, Qwen3.6-35B |
| Inspection VLM | Cosmos-Reason2-8B |
| Inspection sampling rate | 16 FPS |
| Maximum expert actions | 6 |
| Maximum pixel inspections | 4 |
| Expert votes | 2 |
| Scout / uncertainty token limit | 10,000 |
| Expert / revision / voting token limit | 20,000 |
| Primary-audit token limit | 12,000 |
The table summarizes the reasoning models, visual inspection settings, and computational limits used in iCluedo. The reported iFinder and iCluedo results correspond to their GLM configurations.
Reference
[1] Yao et al. iFinder: Structured Zero-Shot Vision-Based LLM Grounding for Dash-Cam Video Reasoning.
Q2 / W1: Temporal-evaluation population, actor attribution, and evidence grounding
Reviewer’s question: Could you clarify the temporal-evaluation population and provide corresponding baseline actor/time results? What systematic evaluation supports evidence grounding beyond qualitative examples?
Response: We agree that the case-level claims require evaluation beyond behavior recognition. To address this concern, we conducted additional experiments comparing iCluedo with direct VLM baselines on temporal localization, actor attribution, reasoning quality, and evidence grounding.
Temporal Localization
We clarify that this evaluation focuses on violation timestamps rather than accident timestamps. We measure temporal localization performance as the percentage of predicted violation timestamps falling within two and three seconds of the human-annotated violation time.
Table 2. Temporal localization performance (%). Higher values indicate better performance. Bold values indicate the best result in each column, including ties.
| Model | Within 3s ↑ | Within 2s ↑ |
|---|---|---|
| Cosmos-Reason2-2B | 44.4 | 26.0 |
| Cosmos-Reason2-8B | 52.7 | 39.6 |
| Qwen3-VL-8B | 33.7 | 24.3 |
| iFinder | 11.2 | 8.9 |
| iCluedo (Ours) | 53.8 | 39.6 |
iCluedo achieves the highest temporal localization performance within three seconds (53.8%) and ties Cosmos-Reason2-8B within two seconds (39.6%). Compared with iFinder, iCluedo improves localization within three seconds by 42.6 percentage points and within two seconds by 30.7 percentage points. These results demonstrate improved temporal localization, although precise identification of violation timestamps remains challenging.
Actor Attribution
The task distinguishes whether the responsible road user is the ego vehicle or another road user, rather than identifying an exact tracked vehicle among multiple surrounding actors. We additionally evaluated the models on this task, as shown in Table 3.
Table 3. Actor attribution performance (%). Higher values indicate better performance.
| Model | Acc. ↑ | Other Car ↑ | Ego Car ↑ |
|---|---|---|---|
| Qwen3-VL-8B | 8.4 | 6.2 | 4.5 |
| Cosmos-Reason2-8B | 5.0 | 1.4 | 4.5 |
| iCluedo (Ours) | 45.3 | 44.1 | 77.3 |
iCluedo achieves the highest overall actor attribution accuracy (45.3%), compared with 8.4% for Qwen3-VL-8B and 5.0% for Cosmos-Reason2-8B. It also achieves the highest performance for identifying other road users (44.1%), while iCluedo–Qwen achieves the highest ego-vehicle attribution score (86.4%). These results demonstrate substantial improvements over direct VLM baselines, although identifying the responsible actor remains challenging.
Reasoning and Evidence Grounding
We additionally evaluate the quality of the generated reasoning and supporting visual evidence.
Table 4. Reasoning and evidence-grounding performance (%). Higher values indicate better performance.
| Model | Reason ↑ | Evidence ↑ |
|---|---|---|
| Cosmos-Reason2-8B | 39.6 | 50.3 |
| Qwen3-VL-8B | 37.6 | 49.3 |
| iCluedo (Ours) | 39.1 | 52.2 |
iCluedo achieves the highest evidence-grounding score (52.2%), compared with 50.3% for Cosmos-Reason2-8B and 49.3% for Qwen3-VL-8B. For reasoning quality, iCluedo–GLM achieves 39.1%, close to the highest score of 39.6% obtained by Cosmos-Reason2-8B. These results show that iCluedo improves evidence grounding while maintaining reasoning performance comparable to the strongest direct VLM baseline.
W1: Evaluation coverage, exclusions, and interpretation of the reported results
Reviewer’s concern: The five-family evaluation does not clearly account for the full dataset, omitted categories, or invalid predictions.
Response:
We would like to clarify that the CVCV dataset contains 4,636 videos, while the original evaluation reported results on 3,264 clips. The original table presents the overall performance and the results for each evaluated violation family. Videos labeled as unknown didn't use in the evaluation. It will be used to support future research on ambiguous and long-tail driving scenarios, which we also plan to investigate in future work.
We understand the reviewer's concern regarding evaluation coverage. To provide a broader evaluation, we conducted additional experiments covering the violation categories beyond the original family labels with no violation. Specifically, we evaluated the methods on a 421-video subset of CVCV, reporting MRR, Top-1 and Top-3 accuracy, precision, recall, and F1-score. The iFinder and iCluedo results in Table 1 correspond to their GLM-based configurations.
Table 1. Violation-family recognition performance (%). Best results in each column are highlighted in bold.
Compared with iFinder, iCluedo improves MRR by 13.3 percentage points, Top-1 accuracy by 19.4 points, and Top-3 accuracy by 5.3 points. F1@1 also improves from 16.8% to 35.2%, although F1@3 is lower (64.9% versus 69.5%). These results support the benefit of the complete iCluedo framework over a structured-perception baseline.
We additionally report the per-category performance across all seven CVCV categories, including No Violation, to provide a more detailed comparison between iCluedo, iFinder–GLM, and direct VLM baselines.
Table 2. Chapter-level F1@1 (%) comparison across seven CVCV categories. Best results in each row are highlighted in bold.
iCluedo achieves the highest macro-F1 of 35.2%, outperforming iFinder–GLM by 20.5 percentage points, Qwen3-VL-8B by 6.8 points, and Cosmos-2B by 24.1 points. It achieves the best performance in five of the seven categories, with particularly notable improvements in Driving/Overtaking, Right-of-Way, and Pedestrian violations. However, Qwen3-VL-8B performs better on Special Stops, while iFinder–GLM achieves the highest F1@1 for No Violation. These results further support the benefit of iCluedo over the structured-perception baseline while highlighting the remaining challenges in certain violation categories. Reference
[1] Yao et al. iFinder: Structured Zero-Shot Vision-Based LLM Grounding for Dash-Cam Video Reasoning.