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
Learning Better Visual Dialog Agents with Pretrained Visual-Linguistic RepresentationCode0
Learning semantic sentence representations from visually grounded language without lexical knowledgeCode0
Learning to ground medical text in a 3D human atlasCode0
Learning Two-Branch Neural Networks for Image-Text Matching TasksCode0
LED: LLM Enhanced Open-Vocabulary Object Detection without Human Curated Data GenerationCode0
Leverage Points in Modality Shifts: Comparing Language-only and Multimodal Word RepresentationsCode0
Leveraging Vision-Language Models for Visual Grounding and Analysis of Automotive UICode0
M^3D: A Multimodal, Multilingual and Multitask Dataset for Grounded Document-level Information ExtractionCode0
MB-ORES: A Multi-Branch Object Reasoner for Visual Grounding in Remote SensingCode0
MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMsCode0
Measuring Faithful and Plausible Visual Grounding in VQACode0
Mismatch Quest: Visual and Textual Feedback for Image-Text MisalignmentCode0
Modularized Textual Grounding for Counterfactual ResilienceCode0
Multi-Attribute Interactions Matter for 3D Visual GroundingCode0
Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual GroundingCode0
Neural Twins TalkCode0
NICE: Improving Panoptic Narrative Detection and Segmentation with Cascading Collaborative LearningCode0
Not (yet) the whole story: Evaluating Visual Storytelling Requires More than Measuring Coherence, Grounding, and RepetitionCode0
Phrase Decoupling Cross-Modal Hierarchical Matching and Progressive Position Correction for Visual GroundingCode0
Progressive Multi-granular Alignments for Grounded Reasoning in Large Vision-Language ModelsCode0
ResVG: Enhancing Relation and Semantic Understanding in Multiple Instances for Visual GroundingCode0
Rethinking 3D Dense Caption and Visual Grounding in A Unified Framework through Prompt-based LocalizationCode0
Rethinking Diversified and Discriminative Proposal Generation for Visual GroundingCode0
Revisiting Visual Question Answering BaselinesCode0
RoViST:Learning Robust Metrics for Visual StorytellingCode0
RoViST: Learning Robust Metrics for Visual StorytellingCode0
ScanERU: Interactive 3D Visual Grounding based on Embodied Reference UnderstandingCode0
SeCG: Semantic-Enhanced 3D Visual Grounding via Cross-modal Graph AttentionCode0
Self-view Grounding Given a Narrated 360° VideoCode0
Semantic query-by-example speech search using visual groundingCode0
Shaking Up VLMs: Comparing Transformers and Structured State Space Models for Vision & Language ModelingCode0
SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual GroundingCode0
Smart Vision-Language ReasonersCode0
SOrT-ing VQA Models : Contrastive Gradient Learning for Improved ConsistencyCode0
To Find Waldo You Need Contextual Cues: Debiasing Who's WaldoCode0
To Find Waldo You Need Contextual Cues: Debiasing Who’s WaldoCode0
Toward Building General Foundation Models for Language, Vision, and Vision-Language Understanding TasksCode0
Towards CLIP-driven Language-free 3D Visual Grounding via 2D-3D Relational Enhancement and ConsistencyCode0
Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target GranularitiesCode0
Uncovering the Full Potential of Visual Grounding Methods in VQACode0
OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning FrameworkCode0
UniMoCo: Unified Modality Completion for Robust Multi-Modal EmbeddingsCode0
Unveiling the Compositional Ability Gap in Vision-Language Reasoning ModelCode0
ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward ModelingCode0
Enhancing Visual Grounding and Generalization: A Multi-Task Cycle Training Approach for Vision-Language ModelsCode0
Visual Contexts Clarify Ambiguous Expressions: A Benchmark DatasetCode0
Visual Coreference Resolution in Visual Dialog using Neural Module NetworksCode0
Visually Grounded VQA by Lattice-based RetrievalCode0
Visual Word2Vec (vis-w2v): Learning Visually Grounded Word Embeddings Using Abstract ScenesCode0
WildRefer: 3D Object Localization in Large-scale Dynamic Scenes with Multi-modal Visual Data and Natural LanguageCode0
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