SOTAVerified

Semantic correspondence

The task of semantic correspondence aims to establish reliable visual correspondence between different instances of the same object category.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 175 papers

TitleStatusHype
RL from Physical Feedback: Aligning Large Motion Models with Humanoid Control—0
Jamais Vu: Exposing the Generalization Gap in Supervised Semantic Correspondence—0
Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels—0
MotionRAG-Diff: A Retrieval-Augmented Diffusion Framework for Long-Term Music-to-Dance Generation—0
Cora: Correspondence-aware image editing using few step diffusionCode1
Semantic Correspondence: Unified Benchmarking and a Strong BaselineCode1
TC-MGC: Text-Conditioned Multi-Grained Contrastive Learning for Text-Video RetrievalCode0
SemAlign3D: Semantic Correspondence between RGB-Images through Aligning 3D Object-Class Representations—0
Semantix: An Energy Guided Sampler for Semantic Style Transfer—0
Evaluating book summaries from internal knowledge in Large Language Models: a cross-model and semantic consistency approach—0
Show:102550
← PrevPage 1 of 18Next →
All datasetsSPair-71kPF-PASCALPF-WILLOWCaltech-101AP-10KCUB-200-2011

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DINOv2PCK95.8—Unverified
2GeoAware-SC (Supervised, AP-10K P.T.)PCK95.7—Unverified
3GeoAware-SC (Supervised)PCK95.1—Unverified
4CATs++PCK93.8—Unverified
5SD+DINO (Supervised)PCK93.6—Unverified
6CATsPCK92.6—Unverified
7VATPCK92.3—Unverified
8VAT (ECCV)PCK92.3—Unverified
9CHMPCK91.6—Unverified
10DHPFPCK90.7—Unverified