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 351–360 of 364 papers

TitleStatusHype
Visual Referring Expression Recognition: What Do Systems Actually Learn?Code0
OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning FrameworkCode0
Detecting Referring Expressions in Visually Grounded Dialogue with Autoregressive Language ModelsCode0
Deconfounded Visual GroundingCode0
Bring Adaptive Binding Prototypes to Generalized Referring Expression SegmentationCode0
InstructSeq: Unifying Vision Tasks with Instruction-conditioned Multi-modal Sequence GenerationCode0
Improving Contrastive Learning for Referring Expression CountingCode0
Single-Stream Multi-Level Alignment for Vision-Language PretrainingCode0
Cross-Modal Self-Attention Network for Referring Image SegmentationCode0
Grounding Referring Expressions in Images by Variational ContextCode0
Show:102550
← PrevPage 36 of 37Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RandomAcc@0.5m14.6—Unverified