SOTAVerified

Referring Expression

Referring expressions places a bounding box around the instance corresponding to the provided description and image.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 364 papers

TitleStatusHype
4th PVUW MeViS 3rd Place Report: Sa2VACode5
Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object DetectionCode5
Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4VCode4
RemoteSAM: Towards Segment Anything for Earth ObservationCode3
Towards Visual Grounding: A SurveyCode3
EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything ModelCode3
PSALM: Pixelwise SegmentAtion with Large Multi-Modal ModelCode3
Universal Instance Perception as Object Discovery and RetrievalCode3
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text ModelsCode2
GroundingSuite: Measuring Complex Multi-Granular Pixel GroundingCode2
Text4Seg: Reimagining Image Segmentation as Text GenerationCode2
SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression SegmentationCode2
Revisiting Referring Expression Comprehension Evaluation in the Era of Large Multimodal ModelsCode2
F-LMM: Grounding Frozen Large Multimodal ModelsCode2
Decoupling Static and Hierarchical Motion Perception for Referring Video SegmentationCode2
Elysium: Exploring Object-level Perception in Videos via MLLMCode2
Unveiling Parts Beyond Objects: Towards Finer-Granularity Referring Expression SegmentationCode2
NExT-Chat: An LMM for Chat, Detection and SegmentationCode2
GLaMM: Pixel Grounding Large Multimodal ModelCode2
GREC: Generalized Referring Expression ComprehensionCode2
GRES: Generalized Referring Expression SegmentationCode2
MDETR - Modulated Detection for End-to-End Multi-Modal UnderstandingCode2
Exploring Contextual Attribute Density in Referring Expression CountingCode1
IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word EmphasisCode1
New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM CollaborationCode1
PixFoundation: Are We Heading in the Right Direction with Pixel-level Vision Foundation Models?Code1
RefDrone: A Challenging Benchmark for Referring Expression Comprehension in Drone ScenesCode1
NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic ReasoningCode1
Multi-task Visual Grounding with Coarse-to-Fine Consistency ConstraintsCode1
IPDN: Image-enhanced Prompt Decoding Network for 3D Referring Expression SegmentationCode1
Exploring Contextual Attribute Density in Referring Expression CountingCode1
RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression SegmentationCode1
Cross-Modal Bidirectional Interaction Model for Referring Remote Sensing Image SegmentationCode1
Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoECode1
FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression ComprehensionCode1
Exploring Fine-Grained Image-Text Alignment for Referring Remote Sensing Image SegmentationCode1
MaPPER: Multimodal Prior-guided Parameter Efficient Tuning for Referring Expression ComprehensionCode1
LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for Referring Expression ComprehensionCode1
3D-GRES: Generalized 3D Referring Expression SegmentationCode1
Multi-branch Collaborative Learning Network for 3D Visual GroundingCode1
Referring Atomic Video Action RecognitionCode1
SAM as the Guide: Mastering Pseudo-Label Refinement in Semi-Supervised Referring Expression SegmentationCode1
CoHD: A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression SegmentationCode1
Talk2Radar: Bridging Natural Language with 4D mmWave Radar for 3D Referring Expression ComprehensionCode1
DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLMCode1
Multi-modal Instruction Tuned LLMs with Fine-grained Visual PerceptionCode1
LLMs as Bridges: Reformulating Grounded Multimodal Named Entity RecognitionCode1
An Open and Comprehensive Pipeline for Unified Object Grounding and DetectionCode1
Referring Expression CountingCode1
Tune-An-Ellipse: CLIP Has Potential to Find What You WantCode1
Show:102550
← PrevPage 1 of 8Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RandomAcc@0.5m14.6—Unverified