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 101–125 of 175 papers

TitleStatusHype
OneSeg: Self-learning and One-shot Learning based Single-slice Annotation for 3D Medical Image Segmentation—0
Order embeddings and character-level convolutions for multimodal alignment—0
PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence—0
Advanced Multimodal Deep Learning Architecture for Image-Text Matching—0
A Framework For Image Synthesis Using Supervised Contrastive Learning—0
Reference Based Color Transfer for Medical Volume Rendering—0
Bidirectional Retrieval Made Simple—0
BiSTNet: Semantic Image Prior Guided Bidirectional Temporal Feature Fusion for Deep Exemplar-based Video Colorization—0
BitSim: An Algebraic Similarity Measure for Description Logics Concepts—0
Bridging Viewpoint Gaps: Geometric Reasoning Boosts Semantic Correspondence—0
Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence—0
Reference-Based Video Colorization with Spatiotemporal Correspondence—0
CL2CM: Improving Cross-Lingual Cross-Modal Retrieval via Cross-Lingual Knowledge Transfer—0
Attentive Semantic Alignment with Offset-Aware Correlation Kernels—0
Towards Affordance-Aware Articulation Synthesis for Rigged Objects—0
RL from Physical Feedback: Aligning Large Motion Models with Humanoid Control—0
CONDA: Condensed Deep Association Learning for Co-Salient Object Detection—0
ContraReg: Contrastive Learning of Multi-modality Unsupervised Deformable Image Registration—0
Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation—0
Seeing Sound: Assembling Sounds from Visuals for Audio-to-Image Generation—0
Self-Supervised Spatial Correspondence Across Modalities—0
SemAlign3D: Semantic Correspondence between RGB-Images through Aligning 3D Object-Class Representations—0
Countering Language Drift via Grounding—0
CPGAN: Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesis—0
Cross-lingual Parse Disambiguation based on Semantic Correspondence—0
Show:102550
← PrevPage 5 of 7Next →
All datasetsSPair-71kPF-PASCALPF-WILLOWCaltech-101AP-10KCUB-200-2011

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1GeoAware-SC (Supervised, AP-10K P.T.)PCK85.6—Unverified
2DINOv2PCK85.2—Unverified
3GeoAware-SC (Supervised)PCK82.9—Unverified
4SD+DINO (Supervised)PCK74.6—Unverified
5GeoAware-SC + CleanDIFT (Zero-Shot)PCK70—Unverified
6GeoAware-SC (Zero-Shot)PCK68.5—Unverified
7SD+DINO + CleanDIFT (Zero-Shot)PCK64.8—Unverified
8IFCATPCK64.4—Unverified
9SD+DINO (Zero-shot)PCK64—Unverified
10DIFT + CleanDIFT (Zero-Shot)PCK61.4—Unverified
#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
#ModelMetricClaimedVerifiedStatus
1LDMCorrespondencesPCK84.3—Unverified
2VAT (ECCV)PCK81.6—Unverified
3VATPCK81—Unverified
4CHMPCK79.4—Unverified
5CATsPCK79.2—Unverified
6SCOTPCK78.1—Unverified
7DHPFPCK77.6—Unverified
8HPFPCK76.3—Unverified
#ModelMetricClaimedVerifiedStatus
1HPFIoU63—Unverified
2DHPFIoU62—Unverified
#ModelMetricClaimedVerifiedStatus
1DINOv2PCK87.4—Unverified
#ModelMetricClaimedVerifiedStatus
1LDM CorrespondencesMean PCK@0.0561.6—Unverified