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 76–100 of 364 papers

TitleStatusHype
Modeling Context in Referring ExpressionsCode1
LAVT: Language-Aware Vision Transformer for Referring Image SegmentationCode1
Multi-modal Instruction Tuned LLMs with Fine-grained Visual PerceptionCode1
DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLMCode1
CoHD: A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression SegmentationCode1
Human-centric Spatio-Temporal Video Grounding With Visual TransformersCode1
NS3D: Neuro-Symbolic Grounding of 3D Objects and RelationsCode1
Described Object Detection: Liberating Object Detection with Flexible ExpressionsCode1
Exploring Contextual Attribute Density in Referring Expression CountingCode1
Exploring Contextual Attribute Density in Referring Expression CountingCode1
Exploring Fine-Grained Image-Text Alignment for Referring Remote Sensing Image SegmentationCode1
3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression SegmentationCode1
Graph-Structured Referring Expression Reasoning in The WildCode1
Image Segmentation Using Text and Image PromptsCode1
GENOME: GenerativE Neuro-symbOlic visual reasoning by growing and reusing ModulEsCode1
RefEgo: Referring Expression Comprehension Dataset from First-Person Perception of Ego4DCode1
FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression ComprehensionCode1
Improving Visual Grounding by Encouraging Consistent Gradient-based ExplanationsCode1
Referring Atomic Video Action RecognitionCode1
Layout-aware Dreamer for Embodied Referring Expression GroundingCode1
GSVA: Generalized Segmentation via Multimodal Large Language ModelsCode1
New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM CollaborationCode1
Room-and-Object Aware Knowledge Reasoning for Remote Embodied Referring ExpressionCode1
A Fast and Accurate One-Stage Approach to Visual GroundingCode1
VL-BERT: Pre-training of Generic Visual-Linguistic RepresentationsCode1
Show:102550
← PrevPage 4 of 15Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RandomAcc@0.5m14.6—Unverified