{"id":"6c06cec4-c7ce-46ba-b625-ee73fa54a0bc","slug":"hf-model-alibaba-velldepth-ctvg-4b-1qeieby-p","name":"CTVG-4B","description":"Hugging Face model Alibaba-VELLDEPTH/CTVG-4B. Task: video text to text. Library: transformers. 23 downloads. 3 likes.","capabilities":["transformers","safetensors","qwen3_vl","image-text-to-text","video-temporal-grounding","temporal-localization","confidence-estimation","arxiv:2609.39883","video-text-to-text","en","dataset:MCG-NJU/TimeLens2-93K","dataset:insomnia7/omtg56k","base_model:MCG-NJU/TimeLens2-4B","base_model:finetune:MCG-NJU/TimeLens2-4B","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:24.300Z"}