{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.02096", "kind": "paper", "url": "https://arxiv.org/abs/2607.02096"}, {"id": "gh:shunya-kato/longegorefer", "kind": "repo", "url": "https://github.com/shunya-kato/LongEgoRefer"}], "authors": ["Shunya Kato", "Taiki Miyanishi", "Shuhei Kurita", "Mahiro Ukai", "Nakamasa Inoue", "Chenhui Chu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.02096", "source_url": "https://arxiv.org/abs/2607.02096"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "LongEgoRefer is a benchmark for Video Referring Expression Comprehension in long-form egocentric videos, built from Ego4D. It contains 1,498 referring expressions over videos averaging 45 minutes, requiring temporal grounding of when an occurrence happens and spatial grounding of where the object appears. The benchmark uses evaluation metrics for temporal and spatial grounding."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.02096", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.02096", "title": "LongEgoRefer"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.02096", "modality": null, "name": "LongEgoRefer", "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_longegorefer_d5a8d99b", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "77c308b971169bad1e073b1b6ce5391a71939910b836cfb31d4f20a293417a6e", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.02096"}, "publisher": null, "released": "2026-07-02", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.02096", "source_url": "https://arxiv.org/abs/2607.02096"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-02096", "source": "claire_radar", "source_benchmark_id": "2607.02096", "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": "https://github.com/shunya-kato/LongEgoRefer", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2607.02096", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "32c32a2217c1b77e91a22a4a2fe81eee443752aa63cc9fea7294a3cef7677b50", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "LongEgoRefer is a benchmark for Video Referring Expression Comprehension in long-form egocentric videos, built from Ego4D. It contains 1,498 referring expressions over videos averaging 45 minutes, requiring temporal grounding of when an occurrence happens and spatial grounding of where the object appears. The benchmark uses evaluation metrics for temporal and spatial grounding.", "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", "public artifact URL"], "snippet": "To address this limitation, we introduce LongEgoRefer, a novel and challenging benchmark constructed from long-form videos in the Ego4D dataset."}, "familyId": "bmf_b9bf12a8afb9", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/shunya-kato/LongEgoRefer", "url": "https://github.com/shunya-kato/LongEgoRefer"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/shunya-kato/LongEgoRefer", "url": "https://huggingface.co/papers/2607.02096"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/shunya-kato/LongEgoRefer", "url": "https://arxiv.org/abs/2607.02096"}], "scope": "benchmark_repo", "url": "https://github.com/shunya-kato/LongEgoRefer", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_longegorefer_d5a8d99b", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/shunya-kato/LongEgoRefer", "data": null, "hfPaper": "https://huggingface.co/papers/2607.02096", "paper": "https://arxiv.org/abs/2607.02096", "pdf": "https://arxiv.org/pdf/2607.02096", "project": null, "report": "https://arxiv.org/abs/2607.02096"}, "metrics": [], "motivation": "Egocentric videos capture rich and diverse human-object interactions and have emerged as a fundamental resource for understanding human activities related to objects.", "name": "LongEgoRefer", "oneLine": "LongEgoRefer is a benchmark for Video Referring Expression Comprehension in long-form egocentric videos, built from Ego4D. It contains 1,498 referring expressions over videos averaging 45 minutes, requiring temporal grounding of when an occurrence happens and spatial grounding of where the object appears. The benchmark uses evaluation metrics for temporal and spatial grounding.", "paperTitle": "LongEgoRefer: A Benchmark for Long-Form Egocentric Video Referring Expression Comprehension", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.02096", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-02", "source": {"authors": ["Shunya Kato", "Taiki Miyanishi", "Shuhei Kurita", "Mahiro Ukai", "Nakamasa Inoue", "Chenhui Chu"], "categories": ["cs.CV"], "id": "2607.02096", "title": "LongEgoRefer: A Benchmark for Long-Form Egocentric Video Referring Expression Comprehension", "type": "arxiv", "url": "https://arxiv.org/abs/2607.02096"}, "sourceUpdatedAt": "2026-07-02T12:32:53Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Existing egocentric Video REC benchmarks focus on short clips, not reflecting real-world long-form recordings. This benchmark defines a demanding spatio-temporal grounding problem that tests models on sparse object occurrences and complex interactions over extended sequences."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
