activity
20192026
most citedDetecting Colorized Images via Convolutional Neural Networks: Toward High Accuracy and Good Generalization

4 citations · 11 across the 22 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

COMPASS: Grounding Composition-Intent Guidance in Unified Multimodal Models

Ziqi Zhou, Weize Quan, Mining Tan +6

Composition is a high-level visual intent that governs where subjects are placed and how a scene is organized, yet current unified multimodal models remain unreliable at fine-grain…