zwcolin/clevr-multichange download history
zwcolin/clevr-multichange is an image to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 6,239 times (176 in the last 7 days), and 6,570 times in total. It ranks #4,701 among datasets by monthly downloads.
CLEVR-Multi-Change (30–40 objects) Two-image change-captioning data used in "Stateful Visual Encoders for Vision-Language Models" (the Multi-object Visual Differencing task). Each example is a before/after pair of a CLEVR scene with 30–40 objects and 4 simultaneous changes (add / dele
Spaces using clevr-multichange
- Model Pulse 8 likes