{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.09876", "kind": "paper", "url": "https://arxiv.org/abs/2607.09876"}, {"kind": "website", "url": "https://cnai.epfl.ch/prompting-mammalps"}], "authors": ["Valentin Gabeff", "Baptiste Maquignaz", "Jennifer Shan", "Sepideh Mamooler", "Gencer Sumbul", "Blair Costelloe", "Devis Tuia", "Alexander Mathis"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.09876", "source_url": "https://arxiv.org/abs/2607.09876"}, "categories": ["General AI", "Information retrieval", "Vision & 3D", "cs.CV"], "description": {"en": "Prompting-MammAlps is a camera-trap text-to-video retrieval benchmark, evaluating video-language models on fine-grained retrieval of ecological events. It includes a test set of 135 queries and 775 candidate videos, with a proposed method that combines action localization with LLM-based parsing."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.09876", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.09876", "title": "Prompting-MammAlps"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.09876", "modality": null, "name": "Prompting-MammAlps", "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_prompting-mammalps_0a70a842", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "c3cffb7df493deadc046c773e72897178de04f92183445cc7f778dd200f4e3e2", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.09876"}, "publisher": null, "released": "2026-07-10", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.09876", "source_url": "https://arxiv.org/abs/2607.09876"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-09876", "source": "claire_radar", "source_benchmark_id": "2607.09876", "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/2607.09876", "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": ["Information retrieval"], "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": "b3dfdf6acd5bc7b3d4c219c330c950e703448df60f9ede43f16918f2edc71528", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Prompting-MammAlps is a camera-trap text-to-video retrieval benchmark, evaluating video-language models on fine-grained retrieval of ecological events. It includes a test set of 135 queries and 775 candidate videos, with a proposed method that combines action localization with LLM-based parsing.", "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": "In this work, we introduce Prompting-MammAlps, the first camera-trap TVR benchmark, and propose a fine-grained and interpretable TVR method."}, "familyId": "bmf_1eff7b878620", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 2, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "candidates"}, "heat": null, "id": "bm_prompting-mammalps_0a70a842", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.09876", "paper": "https://arxiv.org/abs/2607.09876", "pdf": "https://arxiv.org/pdf/2607.09876", "project": "https://cnai.epfl.ch/prompting-mammalps", "report": "https://arxiv.org/abs/2607.09876"}, "metrics": [], "motivation": "Automatically retrieving videos from large camera-trap datasets remains challenging.", "name": "Prompting-MammAlps", "oneLine": "Prompting-MammAlps is a camera-trap text-to-video retrieval benchmark, evaluating video-language models on fine-grained retrieval of ecological events. It includes a test set of 135 queries and 775 candidate videos, with a proposed method that combines action localization with LLM-based parsing.", "paperTitle": "Prompting-MammAlps: Fine-Grained Text-to-Video Retrieval for Camera-Trap Data", "primaryDomain": "General AI", "publication": {"evidence": "Accepted at ECCV 2026; Project page: https://cnai.epfl.ch/prompting-mammalps", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2607.09876", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "ECCV 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "EPFL CNAI", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://cnai.epfl.ch/prompting-mammalps"}], "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": "Inspectable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-10", "source": {"authors": ["Valentin Gabeff and Baptiste Maquignaz and Jennifer Shan and Sepideh Mamooler and Gencer Sumbul and Blair Costelloe and Devis Tuia and Alexander Mathis"], "categories": ["cs.CV", "cs.AI", "q-bio.NC", "q-bio.QM"], "id": "2607.09876", "title": "Prompting-MammAlps: Fine-Grained Text-to-Video Retrieval for Camera-Trap Data", "type": "arxiv", "url": "https://arxiv.org/abs/2607.09876"}, "sourceUpdatedAt": "2026-07-10T18:09:41Z", "topics": ["cs.CV"], "venueAttempts": [{"decisionRaw": "Accepted at ECCV 2026; Project page: https://cnai.epfl.ch/prompting-mammalps", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted at ECCV 2026; Project page: https://cnai.epfl.ch/prompting-mammalps", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2607.09876"}], "reviewStatus": "accepted", "venueName": "ECCV 2026"}], "whyItMatters": "Text-to-video retrieval in ecological domains requires spatiotemporal understanding that current VLMs lack. This benchmark provides a standardized evaluation for fine-grained and interpretable retrieval, highlighting the limitations of zero-shot VLMs."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
