2 citations · 3 across the 4 of their papers we have counts for
4 papers · 1 filter
World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering
Jiacong Wang, Bohong Wu, Haiyong Jiang +4
Recent advances in Vision-Language Models (VLMs) and the scarcity of high-quality multi-modal alignment data have inspired numerous researches on synthetic VLM data generation. The…
Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment
Xin Xiao, Bohong Wu, Jiacong Wang +3
Existing image-text modality alignment in Vision Language Models (VLMs) treats each text token equally in an autoregressive manner. Despite being simple and effective, this method…
Shifted Autoencoders for Point Annotation Restoration in Object Counting
Yuda Zou, Xin Xiao, Peilin Zhou +3
Object counting typically uses 2D point annotations. The complexity of object shapes and the subjectivity of annotators may lead to annotation inconsistency, potentially confusing…
Not All Pixels Are Equal: Learning Pixel Hardness for Semantic Segmentation
Xin Xiao, Daiguo Zhou, Jiagao Hu +2
Semantic segmentation has recently witnessed great progress. Despite the impressive overall results, the segmentation performance in some hard areas (e.g., small objects or thin pa…