conftrace_

object-level information

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

motion boundaries (1) hallucinations (1) lvlms (1) gpt-4v (1) image-grounded guidance (1) open-source vision models (1) segment anything model (1) optical flow estimation (1) unsupervised learning (1)

Papers

Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance ICML 2025 UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model CVPR 2024