{"record": {"aliases": ["I Seek You in Videos: Identity-Conditioned Queries for Person-Centric Video Reasoning"], "artifacts": [{"id": "arxiv:2608.07417", "kind": "paper", "url": "https://arxiv.org/abs/2608.07417"}], "authors": ["Shibo Gao", "Chongxiao Wang", "Chenglong Huang", "Jie Ma", "Haolin Shi", "Fei Ding", "Jing Li", "Qiang Lyu", "Yangyang Liu", "Yang Liu", "Jun Liu", "Linlin Huang", "Peipei Yang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.07417", "source_url": "https://arxiv.org/abs/2608.07417"}, "categories": ["General AI", "Reasoning", "Vision & 3D"], "description": {"en": "Evaluates person-centric video reasoning using identity-conditioned queries, with 1,377 real-world videos and QA pairs across six difficulty levels covering identity recognition to causal reasoning."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.07417", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.07417", "title": "ISYV-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.07417", "modality": null, "name": "ISYV-Bench", "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_i-seek-you-in-videos-identity-conditioned-_7f9c3140", "origin_source": "arxiv", "recognition_confidence": "0.6", "record_sha256": "1b7ac973a4a4c85999596cdc893c748bb26c086ff8ab73bb3a267cea1a494519", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-05T08:27:33.339760Z", "source_url": "https://arxiv.org/abs/2608.07417"}, "publisher": null, "released": "2026-08-07", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.07417", "source_url": "https://arxiv.org/abs/2608.07417"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-07417", "source": "claire_radar", "source_benchmark_id": "2608.07417", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["I Seek You in Videos: Identity-Conditioned Queries for Person-Centric Video Reasoning"], "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/2608.07417", "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"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Acceptance at a top venue and the release of both benchmark and training data, combined with a task that extends beyond typical video QA, should attract strong early interest.", "score": 74}, "capabilities": ["Reasoning"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-05T08:27:33.339760Z", "inputHash": "fcb46e3a094a43f3d45a7f129357bc8c4d36e736bf6cea1b8fb2465e879f63b7", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "ISYV-Bench, a challenging evaluation benchmark with 1,377 real-world complex videos and 1,377 question-answer pairs", "canonicalNameSource": "abstract", "decisionReason": "The paper introduces a named benchmark with a clear evaluation setup and reports extensive results; it is accepted to ACM Multimedia and provides an official repository, indicating a public path for reuse.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-05T08:27:33.339760Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates person-centric video reasoning using identity-conditioned queries, with 1,377 real-world videos and QA pairs across six difficulty levels covering identity recognition to causal reasoning.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "Building on ICQ, we present ISYV (I Seek You in Videos), a systematic solution comprising three components: (1) ISYV-Bench, a challenging evaluation benchmark with 1,377 real-world complex videos and 1,377 question-answer pairs, organized into six difficulty levels spanning capabilities from identity recognition to causal reasoning; (2) ISYV-75K, a large-scale training set of 75K high-quality samples constructed via automated annotation, multi-stage verification, and manual review; and (3) ISYV-"}, "familyId": "bmf_21847e9e8742", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_i-seek-you-in-videos-identity-conditioned-_7f9c3140", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.07417", "pdf": "https://arxiv.org/pdf/2608.07417", "project": null, "report": "https://arxiv.org/abs/2608.07417"}, "metrics": [], "motivation": "Real-world video reasoning often involves multimodal, multi-source inputs, whereas existing video reasoning tasks typically assume a simplified video-text setting, limiting identity matching and person-centric reasoning.", "name": "ISYV-Bench", "oneLine": "Evaluates person-centric video reasoning using identity-conditioned queries, with 1,377 real-world videos and QA pairs across six difficulty levels covering identity recognition to causal reasoning.", "paperTitle": "I Seek You in Videos: Identity-Conditioned Queries for Person-Centric Video Reasoning", "primaryDomain": "General AI", "publication": {"evidence": "Accepted to ACM Multimedia 2026 (MM '26). 6 figures, 5 tables", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.07417", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "ACM Multimedia 2026 (MM '26)", "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "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": 0.6, "relation": "introduces", "releasedAt": "2026-08-07", "source": {"authors": ["Shibo Gao", "Chongxiao Wang", "Chenglong Huang", "Jie Ma", "Haolin Shi", "Fei Ding", "Jing Li", "Qiang Lyu", "Yangyang Liu", "Yang Liu", "Jun Liu", "Linlin Huang", "Peipei Yang"], "categories": ["cs.CV", "cs.AI"], "id": "2608.07417", "title": "I Seek You in Videos: Identity-Conditioned Queries for Person-Centric Video Reasoning", "type": "arxiv", "url": "https://arxiv.org/abs/2608.07417"}, "sourceUpdatedAt": "2026-08-07T17:02:02Z", "topics": ["Reasoning"], "venueAttempts": [{"decisionRaw": "Accepted to ACM Multimedia 2026 (MM '26). 6 figures, 5 tables", "evidence": [{"level": "author-claim", "observedAt": "2026-08-19T11:05:13.395391Z", "rawValue": "Accepted to ACM Multimedia 2026 (MM '26). 6 figures, 5 tables", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.07417"}], "reviewStatus": "accepted", "venueName": "ACM Multimedia 2026 (MM '26)"}], "whyItMatters": "Provides a first standardized benchmark for multimodal identity-conditioned video understanding, testing models on grounding, behavior understanding, and temporal reasoning in realistic scenarios."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
