{"record": {"aliases": ["Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation"], "artifacts": [{"id": "arxiv:2608.10932", "kind": "paper", "url": "https://arxiv.org/abs/2608.10932"}, {"kind": "website", "url": "https://ddz16.github.io/cammotion.github.io/"}], "authors": ["Dazhao Du", "Shiyan Du", "Jian Liu", "Yongjian Yu", "Bohai Gu", "Tao Han", "Hualuo Liu", "Eric Liu", "Yujia Zhang", "Xi Chen", "Song Guo"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.10932", "source_url": "https://arxiv.org/abs/2608.10932"}, "categories": ["Factuality", "General AI", "Vision & 3D", "cs.CV"], "description": {"en": "Evaluates temporally grounded compositional camera motion understanding using 4,229 single-shot clips with expert-annotated segments and 20 direction-aware labels."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.10932", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.10932", "title": "CamChoreo"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.10932", "modality": null, "name": "CamChoreo", "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_temporally-grounded-compositional-camera-m_d9aa8053", "origin_source": "arxiv", "recognition_confidence": "0.7", "record_sha256": "a4b3cec5886a8f3ffca4c4d494ab2ba4127e9a45dbc1d880e2ab95920e971605", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-27T04:14:52.836173Z", "source_url": "https://arxiv.org/abs/2608.10932"}, "publisher": null, "released": "2026-08-11", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.10932", "source_url": "https://arxiv.org/abs/2608.10932"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-10932", "source": "claire_radar", "source_benchmark_id": "2608.10932", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation"], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Vision & 3D", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/ddz16/CamDistill", "githubScope": "benchmark_repo", "githubStars": 3, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2608.10932", "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": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The benchmark addresses multimodal video understanding with a clear public project page and detailed methodology, likely to draw moderate attention from researchers in video and MLLM evaluation.", "score": 52}, "capabilities": ["Factuality"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:14:52.836173Z", "inputHash": "85160b322deec9893e14396466a4c728662b7194e488688841f96bbf38147ff0", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We introduce CamChoreo, a benchmark of 4,229 real single-shot clips with expert-annotated temporal segments", "canonicalNameSource": "abstract", "decisionReason": "The paper defines a formal benchmark with expert annotations and a project page, providing a reusable dataset and evaluation task.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-27T04:14:52.836173Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates temporally grounded compositional camera motion understanding using 4,229 single-shot clips with expert-annotated segments and 20 direction-aware labels.", "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"], "snippet": "We introduce CamChoreo, a benchmark of 4,229 real single-shot clips with expert-annotated temporal segments."}, "familyId": "bmf_57f7e4349ad6", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_temporally-grounded-compositional-camera-m_d9aa8053", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.10932", "pdf": "https://arxiv.org/pdf/2608.10932", "project": "https://ddz16.github.io/cammotion.github.io/", "report": "https://arxiv.org/abs/2608.10932"}, "metrics": [], "motivation": "Understanding camera motion is fundamental to video perception, with applications in spatial intelligence and controllable video generation.", "name": "CamChoreo", "oneLine": "Evaluates temporally grounded compositional camera motion understanding using 4,229 single-shot clips with expert-annotated segments and 20 direction-aware labels.", "paperTitle": "Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.10932", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "publications": [], "publishers": [{"name": "CamChoreo Benchmark Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://ddz16.github.io/cammotion.github.io/"}], "ranking": {"90d": {"confidence": "Medium", "coverage": 0.7, "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": 0.18504537701418716, "value": 3}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.0, "value": 0}}, "confidence": "Medium", "coverage": 0.7, "rank": 364, "score": 25}, "method": "attention-ranking-v13", "rank": 364, "score": 25}}, "readiness": "Paper only", "recognitionConfidence": 0.7, "relation": "introduces", "releasedAt": "2026-08-11", "source": {"authors": ["Dazhao Du", "Shiyan Du", "Jian Liu", "Yongjian Yu", "Bohai Gu", "Tao Han", "Hualuo Liu", "Eric Liu", "Yujia Zhang", "Xi Chen", "Song Guo"], "categories": ["cs.CV", "cs.AI"], "id": "2608.10932", "title": "Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation", "type": "arxiv", "url": "https://arxiv.org/abs/2608.10932"}, "sourceUpdatedAt": "2026-08-11T14:00:02Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Advances camera motion evaluation beyond clip-level labels to compositional and temporal localization, exposing limitations in current multimodal models."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
