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 101–150 of 571 papers

TitleStatusHype
Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric PerspectivesCode5
EAGLE: Enhanced Visual Grounding Minimizes Hallucinations in Instructional Multimodal Models—0
ViGiL3D: A Linguistically Diverse Dataset for 3D Visual Grounding—0
Seeing Speech and Sound: Distinguishing and Locating Audio Sources in Visual Scenes—0
Beyond Human Perception: Understanding Multi-Object World from Monocular ViewCode0
VideoGLaMM : A Large Multimodal Model for Pixel-Level Visual Grounding in Videos—0
Ges3ViG : Incorporating Pointing Gestures into Language-Based 3D Visual Grounding for Embodied Reference UnderstandingCode0
Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local AttentionCode2
Task-aware Cross-modal Feature Refinement Transformer with Large Language Models for Visual Grounding—0
Towards Visual Grounding: A SurveyCode3
Referencing Where to Focus: Improving VisualGrounding with Referential Query—0
Reasoning to Attend: Try to Understand How <SEG> Token WorksCode2
CoF: Coarse to Fine-Grained Image Understanding for Multi-modal Large Language ModelsCode0
Aria-UI: Visual Grounding for GUI InstructionsCode3
FiVL: A Framework for Improved Vision-Language AlignmentCode0
EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues—0
GAGS: Granularity-Aware Feature Distillation for Language Gaussian Splatting—0
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal UnderstandingCode9
Barking Up The Syntactic Tree: Enhancing VLM Training with Syntactic Losses—0
Progressive Multi-granular Alignments for Grounded Reasoning in Large Vision-Language ModelsCode0
3D Spatial Understanding in MLLMs: Disambiguation and Evaluation—0
TACO: Learning Multi-modal Action Models with Synthetic Chains-of-Thought-and-ActionCode2
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time ScalingCode0
M^3D: A Multimodal, Multilingual and Multitask Dataset for Grounded Document-level Information ExtractionCode0
SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding—0
Paint Outside the Box: Synthesizing and Selecting Training Data for Visual Grounding—0
3D Scene Graph Guided Vision-Language Pre-training—0
Interpreting Object-level Foundation Models via Visual Precision SearchCode2
BIP3D: Bridging 2D Images and 3D Perception for Embodied IntelligenceCode3
Solving Zero-Shot 3D Visual Grounding as Constraint Satisfaction ProblemsCode1
Visual Contexts Clarify Ambiguous Expressions: A Benchmark DatasetCode0
GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual GroundingCode2
Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level—0
VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos—0
LidaRefer: Outdoor 3D Visual Grounding for Autonomous Driving with Transformers—0
Fine-Grained Spatial and Verbal Losses for 3D Visual Grounding—0
Phrase Decoupling Cross-Modal Hierarchical Matching and Progressive Position Correction for Visual GroundingCode0
Parameter-Efficient Fine-Tuning Medical Multimodal Large Language Models for Medical Visual Grounding—0
Few-Shot Multimodal Explanation for Visual Question AnsweringCode0
Griffon-G: Bridging Vision-Language and Vision-Centric Tasks via Large Multimodal ModelsCode0
Joint Top-Down and Bottom-Up Frameworks for 3D Visual Grounding—0
VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual GroundingCode2
VividMed: Vision Language Model with Versatile Visual Grounding for MedicineCode1
MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMsCode0
Context-Infused Visual Grounding for ArtCode0
VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AICode2
Learning to Ground VLMs without Forgetting—0
Neural Material Adaptor for Visual Grounding of Intrinsic Dynamics—0
GRAPPA: Generalizing and Adapting Robot Policies via Online Agentic Guidance—0
Context-Aware Command Understanding for Tabletop Scenarios—0
Show:102550
← PrevPage 3 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