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
VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image UnderstandingCode2
The Revolution of Multimodal Large Language Models: A SurveyCode2
InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object RecognitionCode2
Interpreting Object-level Foundation Models via Visual Precision SearchCode2
SegVG: Transferring Object Bounding Box to Segmentation for Visual GroundingCode2
SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator TrajectoriesCode2
Aligning and Prompting Everything All at Once for Universal Visual PerceptionCode2
Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and LanguageCode2
Referring Image MattingCode2
F-LMM: Grounding Frozen Large Multimodal ModelsCode2
List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMsCode2
BuboGPT: Enabling Visual Grounding in Multi-Modal LLMsCode2
RefMask3D: Language-Guided Transformer for 3D Referring SegmentationCode2
NExT-Chat: An LMM for Chat, Detection and SegmentationCode2
One Model to Rule them All: Towards Universal Segmentation for Medical Images with Text PromptsCode2
ChatterBox: Multi-round Multimodal Referring and GroundingCode2
DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real WorldCode2
MedPromptX: Grounded Multimodal Prompting for Chest X-ray DiagnosisCode2
Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local AttentionCode2
Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial TrajectoryCode1
Visual Grounding Methods for VQA are Working for the Wrong Reasons!Code1
Lexicon-Level Contrastive Visual-Grounding Improves Language ModelingCode1
LLMs as Bridges: Reformulating Grounded Multimodal Named Entity RecognitionCode1
Learning Cross-modal Context Graph for Visual GroundingCode1
Beyond Literal Descriptions: Understanding and Locating Open-World Objects Aligned with Human IntentionsCode1
Language-guided Robot Grasping: CLIP-based Referring Grasp Synthesis in ClutterCode1
Learning Cross-modal Context Graph for Visual GroundingCode1
Local-Global Context Aware Transformer for Language-Guided Video SegmentationCode1
Iterative Robust Visual Grounding with Masked Reference based Centerpoint SupervisionCode1
Instruction-Following Agents with Multimodal TransformerCode1
DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and GroundingCode1
Instruction-Guided Visual MaskingCode1
Joint Visual Grounding and Tracking with Natural Language SpecificationCode1
Improving Weakly Supervised Visual Grounding by Contrastive Knowledge DistillationCode1
InfMLLM: A Unified Framework for Visual-Language TasksCode1
Improving Visual Grounding by Encouraging Consistent Gradient-based ExplanationsCode1
Improving One-stage Visual Grounding by Recursive Sub-query ConstructionCode1
Improving Visual Grounding with Visual-Linguistic Verification and Iterative ReasoningCode1
InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual ReferringCode1
Kosmos-2: Grounding Multimodal Large Language Models to the WorldCode1
Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual GroundingCode1
CVLUE: A New Benchmark Dataset for Chinese Vision-Language Understanding EvaluationCode1
UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language ModelingCode1
A Unified Framework for 3D Point Cloud Visual GroundingCode1
Cross3DVG: Cross-Dataset 3D Visual Grounding on Different RGB-D ScansCode1
IAA: Inner-Adaptor Architecture Empowers Frozen Large Language Model with Multimodal CapabilitiesCode1
Cyclic Co-Learning of Sounding Object Visual Grounding and Sound SeparationCode1
An Efficient and Effective Transformer Decoder-Based Framework for Multi-Task Visual GroundingCode1
CPT: Colorful Prompt Tuning for Pre-trained Vision-Language ModelsCode1
A Fast and Accurate One-Stage Approach to Visual GroundingCode1
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