COCOTree: A Dataset and Benchmark for Open Tree-Structured Visual Decomposition
cs.CV
Submitted: 2026-05-21
Updated: 2026-11-03
Code: https://github.com/melonkick3090/COCOTree
Terminology
Sources
- SAM 3: Segment Anything with Concepts
- SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation
- Semantic-SAM: Segment and Recognize Anything at Any Granularity
- Visual Instruction Tuning
- Cityscapes-Panoptic-Parts and PASCAL-Panoptic-Parts datasets for Scene Understanding
- LLM-Seg: Bridging Image Segmentation and Large Language Model Reasoning
- SegLLM: Multi-round Reasoning Segmentation
- Bridging Semantics and Geometry: A Decoupled LVLM-SAM Framework for Reasoning Segmentation in Optical Remote Sensing
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs