You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Multi-context visual grounding is a new task that aims at localizing instances based on open-ended text prompts in multi-image scenarios. A new dataset MC-Bench is constructed to benchmark the MLLMs and foundation models with potential multi-context visual grounding capabilities.
0 commit comments