EPIC-Bench is a new fine-grained benchmark that shows leading VLMs struggle with multi-target counting, part-whole relations, and affordance detection in real-world embodied visual grounding tasks.
Based on the first and second images, you need to locate and count the targets in image 3 matching references in images 1-2
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
EPIC-Bench: A Perception-Centric Benchmark for Fine-Grained Embodied Visual Grounding in Vision-Language Models
EPIC-Bench is a new fine-grained benchmark that shows leading VLMs struggle with multi-target counting, part-whole relations, and affordance detection in real-world embodied visual grounding tasks.