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
Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided DecodingCode1
Beyond Literal Descriptions: Understanding and Locating Open-World Objects Aligned with Human IntentionsCode1
LLMs as Bridges: Reformulating Grounded Multimodal Named Entity RecognitionCode1
Unifying Visual and Vision-Language Tracking via Contrastive LearningCode1
Veagle: Advancements in Multimodal Representation LearningCode1
GroundVLP: Harnessing Zero-shot Visual Grounding from Vision-Language Pre-training and Open-Vocabulary Object DetectionCode1
Mask Grounding for Referring Image SegmentationCode1
Context Disentangling and Prototype Inheriting for Robust Visual GroundingCode1
Unveiling Parts Beyond Objects:Towards Finer-Granularity Referring Expression SegmentationCode1
Mono3DVG: 3D Visual Grounding in Monocular ImagesCode1
GPT-4 Enhanced Multimodal Grounding for Autonomous Driving: Leveraging Cross-Modal Attention with Large Language ModelsCode1
Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and CaptionsCode1
Visual Programming for Zero-shot Open-Vocabulary 3D Visual GroundingCode1
InfMLLM: A Unified Framework for Visual-Language TasksCode1
Florence-2: Advancing a Unified Representation for a Variety of Vision TasksCode1
Language-guided Robot Grasping: CLIP-based Referring Grasp Synthesis in ClutterCode1
GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly DetectionCode1
CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud DataCode1
OV-VG: A Benchmark for Open-Vocabulary Visual GroundingCode1
Visual Grounding Helps Learn Word Meanings in Low-Data RegimesCode1
CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual GroundingCode1
Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language ModelsCode1
PROGrasp: Pragmatic Human-Robot Communication for Object GraspingCode1
Multi3DRefer: Grounding Text Description to Multiple 3D ObjectsCode1
VGDiffZero: Text-to-image Diffusion Models Can Be Zero-shot Visual GroundersCode1
UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and MemoryCode1
A Unified Framework for 3D Point Cloud Visual GroundingCode1
Target-Grounded Graph-Aware Transformer for Aerial Vision-and-Dialog NavigationCode1
Iterative Robust Visual Grounding with Masked Reference based Centerpoint SupervisionCode1
Advancing Visual Grounding with Scene Knowledge: Benchmark and MethodCode1
Distilling Coarse-to-Fine Semantic Matching Knowledge for Weakly Supervised 3D Visual GroundingCode1
What Do Self-Supervised Speech Models Know About Words?Code1
Kosmos-2: Grounding Multimodal Large Language Models to the WorldCode1
Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewardsCode1
Cross3DVG: Cross-Dataset 3D Visual Grounding on Different RGB-D ScansCode1
Syllable Discovery and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech ModelCode1
CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual GroundingCode1
ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype GuidanceCode1
Joint Visual Grounding and Tracking with Natural Language SpecificationCode1
Context-Aware Alignment and Mutual Masking for 3D-Language Pre-TrainingCode1
Confidence-aware Pseudo-label Learning for Weakly Supervised Visual GroundingCode1
Position-guided Text Prompt for Vision-Language Pre-trainingCode1
DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and GroundingCode1
Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual GroundingCode1
YORO -- Lightweight End to End Visual GroundingCode1
Instruction-Following Agents with Multimodal TransformerCode1
Learning Point-Language Hierarchical Alignment for 3D Visual GroundingCode1
GRAVL-BERT: Graphical Visual-Linguistic Representations for Multimodal Coreference ResolutionCode1
EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual GroundingCode1
Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical AlignmentCode1
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