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
CVLUE: A New Benchmark Dataset for Chinese Vision-Language Understanding EvaluationCode1
Improving Visual Grounding with Visual-Linguistic Verification and Iterative ReasoningCode1
Deep Multimodal Neural Architecture SearchCode1
UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language ModelingCode1
A Unified Framework for 3D Point Cloud Visual GroundingCode1
InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual ReferringCode1
Cross3DVG: Cross-Dataset 3D Visual Grounding on Different RGB-D ScansCode1
Instruction-Guided Visual MaskingCode1
CPT: Colorful Prompt Tuning for Pre-trained Vision-Language ModelsCode1
A Fast and Accurate One-Stage Approach to Visual GroundingCode1
Learning Point-Language Hierarchical Alignment for 3D Visual GroundingCode1
CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual GroundingCode1
Beyond Literal Descriptions: Understanding and Locating Open-World Objects Aligned with Human IntentionsCode1
Distilling Coarse-to-Fine Semantic Matching Knowledge for Weakly Supervised 3D Visual GroundingCode1
OCID-Ref: A 3D Robotic Dataset with Embodied Language for Clutter Scene GroundingCode1
Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue GenerationCode1
GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI AgentsCode1
Multi-task Visual Grounding with Coarse-to-Fine Consistency ConstraintsCode1
Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual ConceptsCode1
Visual Grounding Methods for VQA are Working for the Wrong Reasons!Code1
Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial TrajectoryCode1
Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language ModelsCode1
How Do Multimodal Large Language Models Handle Complex Multimodal Reasoning? Placing Them in An Extensible Escape GameCode1
Learning Cross-modal Context Graph for Visual GroundingCode1
Multi-Modal Dynamic Graph Transformer for Visual GroundingCode1
SAT: 2D Semantics Assisted Training for 3D Visual GroundingCode1
Multi-View Transformer for 3D Visual GroundingCode1
Context Disentangling and Prototype Inheriting for Robust Visual GroundingCode1
3D Vision and Language Pretraining with Large-Scale Synthetic DataCode1
Guessing State Tracking for Visual DialogueCode1
Context-Aware Alignment and Mutual Masking for 3D-Language Pre-TrainingCode1
Connecting What to Say With Where to Look by Modeling Human Attention TracesCode1
NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic ReasoningCode1
Visual Grounding for Object-Level Generalization in Reinforcement LearningCode1
Confidence-aware Pseudo-label Learning for Weakly Supervised Visual GroundingCode1
Grounded Situation Recognition with TransformersCode1
Mono3DVG: 3D Visual Grounding in Monocular ImagesCode1
mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connectionsCode1
MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual GroundingCode1
MixGen: A New Multi-Modal Data AugmentationCode1
Extending Large Vision-Language Model for Diverse Interactive Tasks in Autonomous DrivingCode1
Collaborative Transformers for Grounded Situation RecognitionCode1
GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly DetectionCode1
GroundVLP: Harnessing Zero-shot Visual Grounding from Vision-Language Pre-training and Open-Vocabulary Object DetectionCode1
Multi3DRefer: Grounding Text Description to Multiple 3D ObjectsCode1
CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual GroundingCode1
Advancing Visual Grounding with Scene Knowledge: Benchmark and MethodCode1
Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual GroundingCode1
CLIP-Lite: Information Efficient Visual Representation Learning with Language SupervisionCode1
Local-Global Context Aware Transformer for Language-Guided Video SegmentationCode1
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