{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.31875", "kind": "paper", "url": "https://arxiv.org/abs/2606.31875"}], "authors": ["Nghia T. Nguyen", "Lokman Bekit", "Yasin Yilmaz"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.31875", "source_url": "https://arxiv.org/abs/2606.31875"}, "categories": ["Autonomous Driving", "Vision & 3D", "cs.CV"], "description": {"en": "SENSE-VAD is a synthetic video anomaly detection dataset for autonomous driving, generated with CARLA and Unreal Engine. It includes socially complex anomalies across five categories with per-frame binary labels, plus real-world videos for sim-to-real transfer."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.31875", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.31875", "title": "SENSE-VAD"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of South Florida"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.31875", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.31875", "source_url": "https://openalex.org/W7166874027"}, "key": "claire-radar:2606.31875", "modality": null, "name": "SENSE-VAD", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_sense-vad_052128b1", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "0ad095312051614ca6740a30ae6d4e7432c84801c0d32934b9150e2f5e57d11e", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.31875"}, "publisher": null, "released": "2026-06-30", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.31875", "source_url": "https://arxiv.org/abs/2606.31875"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-31875", "source": "claire_radar", "source_benchmark_id": "2606.31875", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Autonomous Driving"], "area": "Vision & 3D", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.31875", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": [], "confidence": "High", "construction": "Interactive Environment", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "558112397f630815a69a6b85c4bfbbdd057e1e2c89c0dcf69cd808cd9ee19940", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "SENSE-VAD is a synthetic video anomaly detection dataset for autonomous driving, generated with CARLA and Unreal Engine. It includes socially complex anomalies across five categories with per-frame binary labels, plus real-world videos for sim-to-real transfer.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce SENSE-VAD, the first synthetic video anomaly detection benchmark for autonomous driving explicitly designed around socially complex anomalies."}, "familyId": "bmf_a69f1f20096d", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_sense-vad_052128b1", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Automotive"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.31875", "paper": "https://arxiv.org/abs/2606.31875", "pdf": "https://arxiv.org/pdf/2606.31875", "project": null, "report": "https://arxiv.org/abs/2606.31875"}, "metrics": [], "motivation": "Autonomous vehicles (AVs) must navigate not only motion-based hazards but also socially complex situations whose danger is constituted by inter-agent relationships rather than movement statistics alone.", "name": "SENSE-VAD", "oneLine": "SENSE-VAD is a synthetic video anomaly detection dataset for autonomous driving, generated with CARLA and Unreal Engine. It includes socially complex anomalies across five categories with per-frame binary labels, plus real-world videos for sim-to-real transfer.", "paperTitle": "SENSE-VAD: Sentient and Semantic Video Anomaly Detection for Autonomous Driving", "primaryDomain": "Autonomous Driving", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.31875", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-30", "source": {"authors": ["Nghia T. Nguyen", "Lokman Bekit", "Yasin Yilmaz"], "categories": ["cs.CV"], "id": "2606.31875", "title": "SENSE-VAD: Sentient and Semantic Video Anomaly Detection for Autonomous Driving", "type": "arxiv", "url": "https://arxiv.org/abs/2606.31875"}, "sourceUpdatedAt": "2026-06-30T15:57:50Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Addresses the evaluation gap for socially complex anomalies in autonomous driving, which are not captured by motion-based detectors. Provides a controlled benchmark to test current video anomaly detection models."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
