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 251–300 of 571 papers

TitleStatusHype
SCO-VIST: Social Interaction Commonsense Knowledge-based Visual Storytelling—0
LCV2: An Efficient Pretraining-Free Framework for Grounded Visual Question Answering—0
ChatterBox: Multi-round Multimodal Referring and GroundingCode2
Unifying Visual and Vision-Language Tracking via Contrastive LearningCode1
Veagle: Advancements in Multimodal Representation LearningCode1
SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language ModelCode2
SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding—0
Uncovering the Full Potential of Visual Grounding Methods in VQACode0
Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMsCode3
Towards Truly Zero-shot Compositional Visual Reasoning with LLMs as Programmers—0
Unveiling Parts Beyond Objects: Towards Finer-Granularity Referring Expression SegmentationCode2
Investigating Compositional Challenges in Vision-Language Models for Visual GroundingCode0
Towards CLIP-driven Language-free 3D Visual Grounding via 2D-3D Relational Enhancement and ConsistencyCode0
LQMFormer: Language-aware Query Mask Transformer for Referring Image Segmentation—0
G^3-LQ: Marrying Hyperbolic Alignment with Explicit Semantic-Geometric Modeling for 3D Visual Grounding—0
When Visual Grounding Meets Gigapixel-level Large-scale Scenes: Benchmark and Approach—0
Multi-Attribute Interactions Matter for 3D Visual GroundingCode0
Omni-Q: Omni-Directional Scene Understanding for Unsupervised Visual Grounding—0
Viewpoint-Aware Visual Grounding in 3D Scenes—0
V?: Guided Visual Search as a Core Mechanism in Multimodal LLMsCode4
Bridging Modality Gap for Visual Grounding with Effecitve Cross-modal Distillation—0
One Model to Rule them All: Towards Universal Segmentation for Medical Images with Text PromptsCode2
Cycle-Consistency Learning for Captioning and Grounding—0
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
Weakly-Supervised 3D Visual Grounding based on Visual Linguistic Alignment—0
Mono3DVG: 3D Visual Grounding in Monocular ImagesCode1
Unveiling Parts Beyond Objects:Towards Finer-Granularity Referring Expression SegmentationCode1
Visual Grounding of Whole Radiology Reports for 3D CT Images—0
Improved Visual Grounding through Self-Consistent Explanations—0
GPT-4 Enhanced Multimodal Grounding for Autonomous Driving: Leveraging Cross-Modal Attention with Large Language ModelsCode1
Mismatch Quest: Visual and Textual Feedback for Image-Text MisalignmentCode0
Uni3DL: Unified Model for 3D and Language Understanding—0
Expand BERT Representation with Visual Information via Grounded Language Learning with Multimodal Partial Alignment—0
Aligning and Prompting Everything All at Once for Universal Visual PerceptionCode2
Behind the Magic, MERLIM: Multi-modal Evaluation Benchmark for Large Image-Language ModelsCode0
G2D: From Global to Dense Radiography Representation Learning via Vision-Language Pre-trainingCode0
Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and CaptionsCode1
Context-Aware Indoor Point Cloud Object Generation through User Instructions—0
Visual Programming for Zero-shot Open-Vocabulary 3D Visual GroundingCode1
Enhancing Visual Grounding and Generalization: A Multi-Task Cycle Training Approach for Vision-Language ModelsCode0
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
NExT-Chat: An LMM for Chat, Detection and SegmentationCode2
GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly DetectionCode1
A Systematic Evaluation of GPT-4V's Multimodal Capability for Medical Image Analysis—0
CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud DataCode1
GROOViST: A Metric for Grounding Objects in Visual StorytellingCode0
Show:102550
← PrevPage 6 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