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 401–450 of 571 papers

TitleStatusHype
Sample-Specific Debiasing for Better Image-Text Models—0
ScanReason: Empowering 3D Visual Grounding with Reasoning Capabilities—0
Adversarial Testing for Visual Grounding via Image-Aware Property Reduction—0
Scene-Intuitive Agent for Remote Embodied Visual Grounding—0
SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding—0
SCO-VIST: Social Interaction Commonsense Knowledge-based Visual Storytelling—0
Adventurer's Treasure Hunt: A Transparent System for Visually Grounded Compositional Visual Question Answering based on Scene Graphs—0
Second Place Solution of WSDM2023 Toloka Visual Question Answering Challenge—0
SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding—0
Emergent Communication with World Models—0
Seeing Speech and Sound: Distinguishing and Locating Audios in Visual Scenes—0
Seeing Speech and Sound: Distinguishing and Locating Audio Sources in Visual Scenes—0
Seeing the advantage: visually grounding word embeddings to better capture human semantic knowledge—0
Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding—0
Efficient Multi-Modal Embeddings from Structured Data—0
Efficient Adaptation For Remote Sensing Visual Grounding—0
EconWebArena: Benchmarking Autonomous Agents on Economic Tasks in Realistic Web Environments—0
EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues—0
VQD: Visual Query Detection in Natural Scenes—0
Semantic Localization Guiding Segment Anything Model For Reference Remote Sensing Image Segmentation—0
ACTRESS: Active Retraining for Semi-supervised Visual Grounding—0
Semantic sentence similarity: size does not always matter—0
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
WALL-E: Embodied Robotic WAiter Load Lifting with Large Language Model—0
Dual Attribute-Spatial Relation Alignment for 3D Visual Grounding—0
DSM: Building A Diverse Semantic Map for 3D Visual Grounding—0
Sim-To-Real Transfer of Visual Grounding for Human-Aided Ambiguity Resolution—0
Data-Efficient 3D Visual Grounding via Order-Aware Referring—0
WaterVG: Waterway Visual Grounding based on Text-Guided Vision and mmWave Radar—0
Don't Look Only Once: Towards Multimodal Interactive Reasoning with Selective Visual Revisitation—0
Weakly-Supervised 3D Visual Grounding based on Visual Linguistic Alignment—0
Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs—0
Weakly-supervised segmentation of referring expressions—0
Differentiable Parsing and Visual Grounding of Natural Language Instructions for Object Placement—0
Spatio-Temporal Graph for Video Captioning with Knowledge Distillation—0
SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding—0
Differentiable Disentanglement Filter: an Application Agnostic Core Concept Discovery Probe—0
Structured Preference Optimization for Vision-Language Long-Horizon Task Planning—0
Surgical-LVLM: Learning to Adapt Large Vision-Language Model for Grounded Visual Question Answering in Robotic Surgery—0
Suspected Object Matters: Rethinking Model's Prediction for One-stage Visual Grounding—0
Differentiable Disentanglement Filter: an Application Agnostic Core Concept Discovery Probe—0
Detecting Concrete Visual Tokens for Multimodal Machine Translation—0
DenseGrounding: Improving Dense Language-Vision Semantics for Ego-Centric 3D Visual Grounding—0
Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded—0
Decoupled Spatial Temporal Graphs for Generic Visual Grounding—0
Talk to Parallel LiDARs: A Human-LiDAR Interaction Method Based on 3D Visual Grounding—0
D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding—0
Task-aware Cross-modal Feature Refinement Transformer with Large Language Models for Visual Grounding—0
Show:102550
← PrevPage 9 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