{"record": {"aliases": ["MariSat: A Maritime Dataset for Instance Segmentation of Objects in Satellite and Aerial Images"], "artifacts": [{"id": "arxiv:2608.29852", "kind": "paper", "url": "https://arxiv.org/abs/2608.29852"}, {"id": "gh:amirabbes/p2m-maritime-segmentation", "kind": "repo", "url": "https://github.com/amirabbes/P2M-Maritime-Segmentation"}], "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "MariSat provides 1260 satellite and aerial images with pixel-level instance segmentation annotations for eight maritime object classes."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.29852", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.29852", "title": "MariSat"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.29852", "modality": null, "name": "MariSat", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "true", "origin_record_id": "bm_marisat-a-maritime-dataset-for-instance-se_9e44e60c", "origin_source": "arxiv", "recognition_confidence": "0.55", "record_sha256": "7addd0a3938f6132b6d73cd97188c1555f955f2c1ecd6066bf3e3e25131695a2", "relation": "evaluates_only", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-02T05:23:11.715633Z", "source_url": "https://arxiv.org/abs/2608.29852"}, "publisher": null, "released": "2026-08-30", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.29852", "source_url": "https://arxiv.org/abs/2608.29852"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-29852", "source": "claire_radar", "source_benchmark_id": "2608.29852", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["MariSat: A Maritime Dataset for Instance Segmentation of Objects in Satellite and Aerial Images"], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Vision & 3D", "attention": {"asOf": "2026-09-02", "attemptedAt": "2026-09-02T05:12:51.621571Z", "githubRepo": "https://github.com/amirabbes/P2M-Maritime-Segmentation", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.29852", "observedAt": "2026-09-02T05:12:51.621571Z", "signalStatus": {"githubStars": {"observedAt": "2026-09-02T05:12:51.621571Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-02T05:12:51.621571Z", "state": "unavailable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Maritime surveillance datasets have niche but steady interest, and the public dataset link supports adoption.", "score": 55}, "capabilities": [], "confidence": "Medium", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-02T05:23:11.715633Z", "inputHash": "f75d526203a1d878d754346b65cded44419f271b573b74ffb0114b1c82aff46b", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We present MariSat, a new benchmark dataset of 1260 aerial and satellite images covering diverse port and coastal scenes, annotated at the pixel level for eight maritime object classes", "canonicalNameSource": "abstract", "decisionReason": "The paper releases the dataset with a public download link and reports benchmark results for segmentation and detection models.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-02T05:23:11.715633Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MariSat provides 1260 satellite and aerial images with pixel-level instance segmentation annotations for eight maritime object classes.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL", "named entity is a model, method, framework, or dataset used in evaluation"], "snippet": "We present MariSat, a new benchmark dataset of 1260 aerial and satellite images covering diverse port and coastal scenes, annotated at the pixel level for eight maritime object classes (sailboat, yacht, jet-ski, fishing boat, cruise ship, military vessel, tugboat and cargo ship)."}, "familyId": "bmf_66cf3438cb7f", "firstSeenAt": "2026-09-01", "heat": null, "id": "bm_marisat-a-maritime-dataset-for-instance-se_9e44e60c", "indexedAt": "2026-09-01T06:28:29.895112Z", "industrySectors": [], "links": {"code": "https://github.com/amirabbes/P2M-Maritime-Segmentation", "data": null, "paper": "https://arxiv.org/abs/2608.29852", "pdf": "https://arxiv.org/pdf/2608.29852", "project": null, "report": "https://arxiv.org/abs/2608.29852"}, "metrics": [], "motivation": "Automated maritime surveillance from satellite and aerial imagery requires large, precisely annotated datasets, which remain scarce for the instance-segmentation task, particularly for small vessels in cluttered port environments.", "name": "MariSat", "oneLine": "MariSat provides 1260 satellite and aerial images with pixel-level instance segmentation annotations for eight maritime object classes.", "paperTitle": "MariSat: A Maritime Dataset for Instance Segmentation of Objects in Satellite and Aerial Images", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.29852", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-01T06:28:29.895112Z"}, "publications": [], "publishers": [{"name": "SUP’COM", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/amirabbes/P2M-Maritime-Segmentation"}], "ranking": {"30d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 124, "score": 23}, "method": "attention-ranking-v13", "rank": 124, "score": 23}, "90d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 317, "score": 23}, "method": "attention-ranking-v13", "rank": 317, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 0.55, "relation": "evaluates_only", "releasedAt": "2026-08-30", "source": {"authors": ["Amir Abbes", "Ines Harrabi", "Lucas Justin Yirepoa Kinda", "Rim Trabelsi", "Adnane Cabani", "Fatma Abdelkefi"], "categories": ["cs.CV"], "id": "2608.29852", "title": "MariSat: A Maritime Dataset for Instance Segmentation of Objects in Satellite and Aerial Images", "type": "arxiv", "url": "https://arxiv.org/abs/2608.29852"}, "sourceUpdatedAt": "2026-08-30T15:31:39Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "It fills a gap in precisely annotated maritime instance segmentation datasets, particularly for small vessels in cluttered port environments."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
