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 351–400 of 571 papers

TitleStatusHype
TreePrompt: Learning to Compose Tree Prompts for Explainable Visual Grounding—0
Vision-Language Pre-training with Object Contrastive Learning for 3D Scene Understanding—0
CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual GroundingCode1
Sample-Specific Debiasing for Better Image-Text Models—0
Movie Box Office Prediction With Self-Supervised and Visually Grounded Pretraining—0
WildRefer: 3D Object Localization in Large-scale Dynamic Scenes with Multi-modal Visual Data and Natural LanguageCode0
ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype GuidanceCode1
ScanERU: Interactive 3D Visual Grounding based on Embodied Reference UnderstandingCode0
Joint Visual Grounding and Tracking with Natural Language SpecificationCode1
Medical Phrase Grounding with Region-Phrase Context Contrastive Alignment—0
Parallel Vertex Diffusion for Unified Visual Grounding—0
Focusing On Targets For Improving Weakly Supervised Visual Grounding—0
mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and VideoCode4
Champion Solution for the WSDM2023 Toloka VQA ChallengeCode3
Toward Building General Foundation Models for Language, Vision, and Vision-Language Understanding TasksCode0
ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding—0
CoSign: Exploring Co-occurrence Signals in Skeleton-based Continuous Sign Language Recognition—0
Confidence-aware Pseudo-label Learning for Weakly Supervised Visual GroundingCode1
Context-Aware Alignment and Mutual Masking for 3D-Language Pre-TrainingCode1
Dynamic Inference With Grounding Based Vision and Language Models—0
GAFNet: A Global Fourier Self Attention Based Novel Network for multi-modal downstream tasks—0
Position-guided Text Prompt for Vision-Language Pre-trainingCode1
Using Multiple Instance Learning to Build Multimodal Representations—0
UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding—0
DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and GroundingCode1
MNER-QG: An End-to-End MRC framework for Multimodal Named Entity Recognition with Query Grounding—0
Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual GroundingCode1
X^2-VLM: All-In-One Pre-trained Model For Vision-Language TasksCode2
A survey on knowledge-enhanced multimodal learning—0
YORO -- Lightweight End to End Visual GroundingCode1
Visually Grounded VQA by Lattice-based RetrievalCode0
Are Current Decoding Strategies Capable of Facing the Challenges of Visual Dialogue?—0
Instruction-Following Agents with Multimodal TransformerCode1
RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data—0
A Visual Tour Of Current Challenges In Multimodal Language Models—0
Learning Point-Language Hierarchical Alignment for 3D Visual GroundingCode1
Vision-Language Pre-training: Basics, Recent Advances, and Future TrendsCode3
Like a bilingual baby: The advantage of visually grounding a bilingual language model—0
YFACC: A Yorùbá speech-image dataset for cross-lingual keyword localisation through visual grounding—0
MAMO: Masked Multimodal Modeling for Fine-Grained Vision-Language Representation Learning—0
Enhancing Interpretability and Interactivity in Robot Manipulation: A Neurosymbolic ApproachCode0
Cost-Effective Language Driven Image Editing with LX-DRIMCode0
GRAVL-BERT: Graphical Visual-Linguistic Representations for Multimodal Coreference ResolutionCode1
Differentiable Parsing and Visual Grounding of Natural Language Instructions for Object Placement—0
EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual GroundingCode1
Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding—0
Introspective Learning : A Two-Stage Approach for Inference in Neural NetworksCode0
Visual Grounding of Inter-lingual Word-Embeddings—0
Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical AlignmentCode1
VLMAE: Vision-Language Masked Autoencoder—0
Show:102550
← PrevPage 8 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