fine-grained perception
The ability of AI systems to distinguish between subtle variations in input data, crucial for complex tasks such as image recognition or natural language understanding.
- From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes
- NeedleInATable: Exploring Long-Context Capability of Large Language Models towards Long-Structured Tables
- OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning
- ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models
- UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface
- UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning
- VITRIX-CLIPIN: Enhancing Fine-Grained Visual Understanding in CLIP via Instruction-Editing Data and Long Captions