SOTAVerified

Visual Grounding

Visual Grounding (VG) aims to locate the most relevant object or region in an image, based on a natural language query. The query can be a phrase, a sentence, or even a multi-round dialogue. There are three main challenges in VG:

  • What is the main focus in a query?
  • How to understand an image?
  • How to locate an object?

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 571 papers

TitleStatusHype
Visual Intention Grounding for Egocentric Assistants—0
COUNTS: Benchmarking Object Detectors and Multimodal Large Language Models under Distribution Shifts—0
Ges3ViG: Incorporating Pointing Gestures into Language-Based 3D Visual Grounding for Embodied Reference UnderstandingCode0
DSM: Building A Diverse Semantic Map for 3D Visual Grounding—0
AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations—0
VLM-R1: A Stable and Generalizable R1-style Large Vision-Language ModelCode9
Towards Visual Text Grounding of Multimodal Large Language Model—0
STING-BEE: Towards Vision-Language Model for Real-World X-ray Baggage Security InspectionCode1
Multimodal Reference Visual Grounding—0
Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target GranularitiesCode0
Image Difference Grounding with Natural Language—0
MB-ORES: A Multi-Branch Object Reasoner for Visual Grounding in Remote SensingCode0
ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning—0
Efficient Adaptation For Remote Sensing Visual Grounding—0
RefChartQA: Grounding Visual Answer on Chart Images through Instruction TuningCode1
NuGrounding: A Multi-View 3D Visual Grounding Framework in Autonomous Driving—0
Beyond Object Categories: Multi-Attribute Reference Understanding for Visual Grounding—0
Seeing Speech and Sound: Distinguishing and Locating Audios in Visual Scenes—0
A Vision Centric Remote Sensing Benchmark—0
Visual Position Prompt for MLLM based Visual GroundingCode1
LED: LLM Enhanced Open-Vocabulary Object Detection without Human Curated Data GenerationCode0
HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal ModelCode2
DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual GroundingCode2
How Do Multimodal Large Language Models Handle Complex Multimodal Reasoning? Placing Them in An Extensible Escape GameCode1
SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator TrajectoriesCode2
SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator TrajectoriesCode2
Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding—0
Enhancing Abnormality Grounding for Vision Language Models with Knowledge Descriptions—0
Teaching Metric Distance to Autoregressive Multimodal Foundational Models—0
Structured Preference Optimization for Vision-Language Long-Horizon Task Planning—0
ProxyTransformation: Preshaping Point Cloud Manifold With Proxy Attention For 3D Visual Grounding—0
Programming with Pixels: Computer-Use Meets Software Engineering—0
SwimVG: Step-wise Multimodal Fusion and Adaption for Visual GroundingCode1
GroundCap: A Visually Grounded Image Captioning Dataset—0
Leveraging Multimodal-LLMs Assisted by Instance Segmentation for Intelligent Traffic Monitoring—0
Text-guided Sparse Voxel Pruning for Efficient 3D Visual GroundingCode3
TRAVEL: Training-Free Retrieval and Alignment for Vision-and-Language Navigation—0
Evolving Symbolic 3D Visual Grounder with Weakly Supervised ReflectionCode1
NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic ReasoningCode1
RLS3: RL-Based Synthetic Sample Selection to Enhance Spatial Reasoning in Vision-Language Models for Indoor Autonomous Perception—0
ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations—0
PAINT: Paying Attention to INformed Tokens to Mitigate Hallucination in Large Vision-Language ModelCode1
When language and vision meet road safety: leveraging multimodal large language models for video-based traffic accident analysisCode1
FLORA: Formal Language Model Enables Robust Training-free Zero-shot Object Referring Analysis—0
AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring—0
A Simple Aerial Detection Baseline of Multimodal Language ModelsCode2
Multi-task Visual Grounding with Coarse-to-Fine Consistency ConstraintsCode1
GeoPix: Multi-Modal Large Language Model for Pixel-level Image Understanding in Remote Sensing—0
Open Eyes, Then Reason: Fine-grained Visual Mathematical Understanding in MLLMsCode1
URSA: Understanding and Verifying Chain-of-thought Reasoning in Multimodal MathematicsCode2
Show:102550
← PrevPage 2 of 12Next →
All datasetsRefCOCO testARefCOCO+ test BRefCoCo val

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Florence-2-large-ftAccuracy (%)95.3—Unverified
2mPLUG-2Accuracy (%)92.8—Unverified
3X2-VLM (large)Accuracy (%)92.1—Unverified
4XFM (base)Accuracy (%)90.4—Unverified
5X2-VLM (base)Accuracy (%)90.3—Unverified
6X-VLM (base)Accuracy (%)89—Unverified
7HYDRAIoU61.7—Unverified
8HYDRAIoU61.1—Unverified
#ModelMetricClaimedVerifiedStatus
1Florence-2-large-ftAccuracy (%)92—Unverified
2mPLUG-2Accuracy (%)86.05—Unverified
3X2-VLM (large)Accuracy (%)81.8—Unverified
4XFM (base)Accuracy (%)79.8—Unverified
5X2-VLM (base)Accuracy (%)78.4—Unverified
6X-VLM (base)Accuracy (%)76.91—Unverified
#ModelMetricClaimedVerifiedStatus
1Florence-2-large-ftAccuracy (%)93.4—Unverified
2mPLUG-2Accuracy (%)90.33—Unverified
3X2-VLM (large)Accuracy (%)87.6—Unverified
4XFM (base)Accuracy (%)86.1—Unverified
5X2-VLM (base)Accuracy (%)85.2—Unverified
6X-VLM (base)Accuracy (%)84.51—Unverified