{"adoption": {"forks": 159, "observed_at": "2026-08-28T04:06:41.668440+00:00", "stars": 2368}, "canonical_url": "https://ross.abutalabs.com/products/internvideo", "card": {"archived": false, "artifact_type": "library", "description": "[ECCV2024] Video Foundation Models & Data for Multimodal Understanding", "domain": ["artificial-intelligence", "deep-learning", "computer-vision", "large-language-models"], "enriched": true, "function": ["machine-learning", "deep-learning", "video-processing", "nlp", "rag", "agent-framework"], "health_score": 74, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["OpenGVLab/InternVideo"], "name": "OpenGVLab/InternVideo", "platform": ["python", "cross-platform"], "pushed_at": "2026-07-02T03:20:41+00:00", "repo": "OpenGVLab/InternVideo", "stars": 2368, "tags": ["video-foundation-models", "multimodal", "video-text-dataset", "video-retrieval", "video-question-answering", "action-recognition", "zero-shot-classification", "contrastive-learning", "self-supervised-learning", "instruction-tuning", "vision-transformer", "eccv2024", "video", "ai-agents", "gpu", "linux"], "topics": ["foundation-models", "video-understanding", "vision-transformer", "action-recognition", "masked-autoencoder", "multimodal", "open-set-recognition", "spatio-temporal-action-localization", "temporal-action-localization", "video-question-answering", "video-retrieval", "zero-shot-classification", "zero-shot-retrieval", "benchmark", "contrastive-learning", "self-supervised", "instruction-tuning", "video-data", "video-dataset", "video-clip"], "urls": [], "use_cases": ["understand and answer questions about videos with a multimodal LLM", "retrieve videos using text queries", "classify human actions in video clips", "localize actions temporally in long videos", "train a video-text model on a large video dataset", "run zero-shot video classification benchmarks", "build an agent that reasons over long video content"], "what_it_is": "InternVideo is a series of open-source video foundation models for multimodal video understanding, spanning generative and discriminative learning, long-context video MLLMs, and video agents. It also releases InternVid, a large-scale video-text dataset with hundreds of millions of pairs for training and evaluation.", "when_to_avoid": ["you only need lightweight real-time video processing without deep models", "you lack GPU resources, as the flagship models are 1B-8B parameters", "you need production video streaming or transcoding rather than understanding", "you need a plug-and-play app rather than research code"], "when_to_choose": ["you need state-of-the-art pretrained video understanding models with released checkpoints", "you want a large-scale video-text dataset for pretraining or fine-tuning", "you need video retrieval, QA, or action recognition in one model family", "you are researching multimodal video-language models"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/internvideo", "repo": "OpenGVLab/InternVideo", "role": "main", "score": 72}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:41.668440+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:35:28.185807+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3981414a9e0bad5dcdfabb9ed1673d287e72131d87797c6e038680edbfec5845", "fetched_at": "2026-08-28T04:06:41.668440+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenGVLab/InternVideo"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:41.668440+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:35:28.185807+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3981414a9e0bad5dcdfabb9ed1673d287e72131d87797c6e038680edbfec5845", "fetched_at": "2026-08-28T04:06:41.668440+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenGVLab/InternVideo"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:35:28.185807+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3981414a9e0bad5dcdfabb9ed1673d287e72131d87797c6e038680edbfec5845", "fetched_at": "2026-08-28T04:06:41.668440+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenGVLab/InternVideo"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:41.668440+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:41.668440+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:41.668440+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:35:28.185807+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3981414a9e0bad5dcdfabb9ed1673d287e72131d87797c6e038680edbfec5845", "fetched_at": "2026-08-28T04:06:41.668440+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenGVLab/InternVideo"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:41.668440+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:41.668440+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:35:28.185807+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3981414a9e0bad5dcdfabb9ed1673d287e72131d87797c6e038680edbfec5845", "fetched_at": "2026-08-28T04:06:41.668440+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenGVLab/InternVideo"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:41.668440+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:41.668440+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:41.668440+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:35:28.185807+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3981414a9e0bad5dcdfabb9ed1673d287e72131d87797c6e038680edbfec5845", "fetched_at": "2026-08-28T04:06:41.668440+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenGVLab/InternVideo"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:41.668440+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:41.668440+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:35:28.185807+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3981414a9e0bad5dcdfabb9ed1673d287e72131d87797c6e038680edbfec5845", "fetched_at": "2026-08-28T04:06:41.668440+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenGVLab/InternVideo"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:35:28.185807+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3981414a9e0bad5dcdfabb9ed1673d287e72131d87797c6e038680edbfec5845", "fetched_at": "2026-08-28T04:06:41.668440+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenGVLab/InternVideo"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:35:28.185807+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3981414a9e0bad5dcdfabb9ed1673d287e72131d87797c6e038680edbfec5845", "fetched_at": "2026-08-28T04:06:41.668440+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenGVLab/InternVideo"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:35:28.185807+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3981414a9e0bad5dcdfabb9ed1673d287e72131d87797c6e038680edbfec5845", "fetched_at": "2026-08-28T04:06:41.668440+00:00", "kind": "readme", "missing": false, "url": "https://github.com/OpenGVLab/InternVideo"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 90, "longevity": 98, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1379, "days_push": 62, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 72, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}