FlexCap: Generating Rich, Localized, and Flexible Captions in Images

arXiv:2403.12026v1 Announce Type: cross
Abstract: We introduce a versatile $\textit{flexible-captioning}$ vision-language model (VLM) capable of generating region-specific descriptions of varying lengths. The model, FlexCap, is trained to produce length-conditioned captions for input bounding boxes, and this allows control over the information density of its output, with descriptions ranging from concise object labels to detailed captions. To achieve this we create large-scale training datasets of image region descriptions of varying length, starting from captioned images. This flexible-captioning capability has several valuable …

abstract arxiv captioning captions control cs.ai cs.cl cs.cv cs.lg images information language language model object the information type vision vlm