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 201–250 of 571 papers

TitleStatusHype
NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic ReasoningCode1
Panoptic Narrative GroundingCode1
Visual Grounding in Video for Unsupervised Word TranslationCode1
Visual Grounding of Learned Physical ModelsCode1
EAGLE: Enhanced Visual Grounding Minimizes Hallucinations in Instructional Multimodal Models—0
Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding—0
Dynamic Inference With Grounding Based Vision and Language Models—0
Bridging Modality Gap for Visual Grounding with Effecitve Cross-modal Distillation—0
A Neural Representation Framework with LLM-Driven Spatial Reasoning for Open-Vocabulary 3D Visual Grounding—0
Movie Box Office Prediction With Self-Supervised and Visually Grounded Pretraining—0
LanguageRefer: Spatial-Language Model for 3D Visual Grounding—0
ACTRESS: Active Retraining for Semi-supervised Visual Grounding—0
More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models—0
MNER-QG: An End-to-End MRC framework for Multimodal Named Entity Recognition with Query Grounding—0
BlenderAlchemy: Editing 3D Graphics with Vision-Language Models—0
MoDA: Modulation Adapter for Fine-Grained Visual Grounding in Instructional MLLMs—0
Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level—0
Data-Efficient 3D Visual Grounding via Order-Aware Referring—0
Joint Top-Down and Bottom-Up Frameworks for 3D Visual Grounding—0
Don't Look Only Once: Towards Multimodal Interactive Reasoning with Selective Visual Revisitation—0
I Speak and You Find: Robust 3D Visual Grounding with Noisy and Ambiguous Speech Inputs—0
Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs—0
Beyond Object Categories: Multi-Attribute Reference Understanding for Visual Grounding—0
MMR: Evaluating Reading Ability of Large Multimodal Models—0
A Systematic Evaluation of GPT-4V's Multimodal Capability for Medical Image Analysis—0
3D Spatial Understanding in MLLMs: Disambiguation and Evaluation—0
Interpretable Visual Question Answering via Reasoning Supervision—0
Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration—0
Interpretable Visual Question Answering by Visual Grounding from Attention Supervision Mining—0
Interactive Visual Grounding of Referring Expressions for Human-Robot Interaction—0
Differentiable Parsing and Visual Grounding of Natural Language Instructions for Object Placement—0
INVIGORATE: Interactive Visual Grounding and Grasping in Clutter—0
Interactive Reinforcement Learning for Object Grounding via Self-Talking—0
Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention—0
Differentiable Disentanglement Filter: an Application Agnostic Core Concept Discovery Probe—0
Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignment—0
Differentiable Disentanglement Filter: an Application Agnostic Core Concept Discovery Probe—0
Knowledge Supports Visual Language Grounding: A Case Study on Colour Terms—0
Benchmarking Diverse-Modal Entity Linking with Generative Models—0
AIFit: Automatic 3D Human-Interpretable Feedback Models for Fitness Training—0
Individuation in Neural Models with and without Visual Grounding—0
Language-Guided 3D Object Detection in Point Cloud for Autonomous Driving—0
Detecting Concrete Visual Tokens for Multimodal Machine Translation—0
Being data-driven is not enough: Revisiting interactive instruction giving as a challenge for NLG—0
MedSG-Bench: A Benchmark for Medical Image Sequences Grounding—0
DSM: Building A Diverse Semantic Map for 3D Visual Grounding—0
LCV2: An Efficient Pretraining-Free Framework for Grounded Visual Question Answering—0
Dual Attribute-Spatial Relation Alignment for 3D Visual Grounding—0
Improving Visually Grounded Sentence Representations with Self-Attention—0
DenseGrounding: Improving Dense Language-Vision Semantics for Ego-Centric 3D Visual Grounding—0
Show:102550
← PrevPage 5 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