{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.01948", "kind": "paper", "url": "https://arxiv.org/abs/2608.01948"}], "authors": ["Cheng-Yao Hong", "Ting-Wei Lin", "Yun-Chung Lai", "Hua-Wei Lee", "Hwann-Tzong Chen", "Tyng-Luh Liu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.01948", "source_url": "https://arxiv.org/abs/2608.01948"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "Event ActivityNet is a large-scale simulated-event benchmark for untrimmed action understanding, derived from ActivityNet videos. It includes 3,263 videos, 200 action classes, event-voxel representations, temporal annotations, and supports recognition, event-language alignment, and online temporal localization."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.01948", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.01948", "title": "Event ActivityNet"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Institute of Information Science, Academia Sinica", "Academia Sinica", "National Tsing Hua University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.01948", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.01948", "source_url": "https://openalex.org/W7172377703"}, "key": "claire-radar:2608.01948", "modality": null, "name": "Event ActivityNet", "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_event-activitynet_532df77c", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "184316f34ab9a1832237c63abf6354b8807427798b310a66680280b38c6537a3", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.01948"}, "publisher": null, "released": "2026-08-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.01948", "source_url": "https://arxiv.org/abs/2608.01948"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-01948", "source": "claire_radar", "source_benchmark_id": "2608.01948", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "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/2608.01948", "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": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "07dbd75f826bdb9f61f3bc2b6b6b25b3f322c60be70ce8e799bd18c9ccfb5e47", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Event ActivityNet is a large-scale simulated-event benchmark for untrimmed action understanding, derived from ActivityNet videos. It includes 3,263 videos, 200 action classes, event-voxel representations, temporal annotations, and supports recognition, event-language alignment, and online temporal localization.", "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 Event ActivityNet, a large-scale simulated-event benchmark derived from human-annotated, untrimmed ActivityNet videos."}, "familyId": "bmf_f0108426e128", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_event-activitynet_532df77c", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.01948", "paper": "https://arxiv.org/abs/2608.01948", "pdf": "https://arxiv.org/pdf/2608.01948", "project": null, "report": "https://arxiv.org/abs/2608.01948"}, "metrics": [], "motivation": "Long-horizon event-based action understanding remains underexplored because existing datasets largely comprise short, trimmed clips, while collecting native event streams with dense temporal annotations is costly.", "name": "Event ActivityNet", "oneLine": "Event ActivityNet is a large-scale simulated-event benchmark for untrimmed action understanding, derived from ActivityNet videos. It includes 3,263 videos, 200 action classes, event-voxel representations, temporal annotations, and supports recognition, event-language alignment, and online temporal localization.", "paperTitle": "Event ActivityNet: A Large-Scale Simulated-Event Benchmark for Untrimmed Action Understanding", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.01948", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-03", "source": {"authors": ["Cheng-Yao Hong", "Ting-Wei Lin", "Yun-Chung Lai", "Hua-Wei Lee", "Hwann-Tzong Chen", "Tyng-Luh Liu"], "categories": ["cs.CV"], "id": "2608.01948", "title": "Event ActivityNet: A Large-Scale Simulated-Event Benchmark for Untrimmed Action Understanding", "type": "arxiv", "url": "https://arxiv.org/abs/2608.01948"}, "sourceUpdatedAt": "2026-08-03T09:20:46Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Existing datasets lack long-horizon event-based understanding. Event ActivityNet provides a scalable benchmark for long-horizon event modeling with multiple tasks, enabling evaluation of models on untrimmed action understanding."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
