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
Visually Consistent Hierarchical Image Classification—0
Learning Language Structures through Grounding—0
Dual Attribute-Spatial Relation Alignment for 3D Visual Grounding—0
MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language AnnotationsCode4
Towards Vision-Language Geo-Foundation Model: A SurveyCode2
Advancing Grounded Multimodal Named Entity Recognition via LLM-Based Reformulation and Box-Based SegmentationCode1
Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and LanguageCode2
A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future DirectionsCode3
F-LMM: Grounding Frozen Large Multimodal ModelsCode2
HPE-CogVLM: Advancing Vision Language Models with a Head Pose Grounding Task—0
HENASY: Learning to Assemble Scene-Entities for Egocentric Video-Language Model—0
Instruction-Guided Visual MaskingCode1
Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention—0
LLM-Optic: Unveiling the Capabilities of Large Language Models for Universal Visual Grounding—0
Talk to Parallel LiDARs: A Human-LiDAR Interaction Method Based on 3D Visual Grounding—0
Talk2Radar: Bridging Natural Language with 4D mmWave Radar for 3D Referring Expression ComprehensionCode1
Adversarial Robustness for Visual Grounding of Multimodal Large Language ModelsCode0
DARA: Domain- and Relation-aware Adapters Make Parameter-efficient Tuning for Visual GroundingCode1
Visual grounding for desktop graphical user interfaces—0
Naturally Supervised 3D Visual Grounding with Language-Regularized Concept Learners—0
BlenderAlchemy: Editing 3D Graphics with Vision-Language Models—0
List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMsCode2
HiVG: Hierarchical Multimodal Fine-grained Modulation for Visual GroundingCode2
Groma: Localized Visual Tokenization for Grounding Multimodal Large Language ModelsCode4
Rethinking 3D Dense Caption and Visual Grounding in A Unified Framework through Prompt-based LocalizationCode0
MedRG: Medical Report Grounding with Multi-modal Large Language Model—0
VHM: Versatile and Honest Vision Language Model for Remote Sensing Image AnalysisCode2
AgentStudio: A Toolkit for Building General Virtual AgentsCode3
Data-Efficient 3D Visual Grounding via Order-Aware Referring—0
Surgical-LVLM: Learning to Adapt Large Vision-Language Model for Grounded Visual Question Answering in Robotic Surgery—0
MedPromptX: Grounded Multimodal Prompting for Chest X-ray DiagnosisCode2
VidLA: Video-Language Alignment at Scale—0
Lexicon-Level Contrastive Visual-Grounding Improves Language ModelingCode1
Learning from Synthetic Data for Visual Grounding—0
Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial TrajectoryCode1
HYDRA: A Hyper Agent for Dynamic Compositional Visual ReasoningCode1
WaterVG: Waterway Visual Grounding based on Text-Guided Vision and mmWave Radar—0
Right Place, Right Time! Dynamizing Topological Graphs for Embodied Navigation—0
SeCG: Semantic-Enhanced 3D Visual Grounding via Cross-modal Graph AttentionCode0
Detecting Concrete Visual Tokens for Multimodal Machine Translation—0
MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual GroundingCode1
Adversarial Testing for Visual Grounding via Image-Aware Property Reduction—0
ShapeLLM: Universal 3D Object Understanding for Embodied InteractionCode3
OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web—0
Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided DecodingCode1
The Revolution of Multimodal Large Language Models: A SurveyCode2
Beyond Literal Descriptions: Understanding and Locating Open-World Objects Aligned with Human IntentionsCode1
LLMs as Bridges: Reformulating Grounded Multimodal Named Entity RecognitionCode1
ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward ModelingCode0
Neural Slot Interpreters: Grounding Object Semantics in Emergent Slot Representations—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