AlignPose performs generalizable 6D pose estimation by multi-view feature-metric refinement that minimizes feature discrepancy between on-the-fly rendered object features and observed images across calibrated views.
Microsoft coco: Common objects in context
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
ForenAgent lets MLLMs create and iteratively improve low-level Python tools for image forgery detection via a two-stage training pipeline and a new 100k-image benchmark dataset.
FDA differentially subtracts function-word cross-attention from original attention heads to cut attack success rates by 18-90% across models and tasks while dropping performance by at most 0.6%.
FedHarmony harmonizes heterogeneous label correlations in federated multi-label learning via consensus correlations as global teachers and quality-weighted aggregation, with an accelerated optimizer that converges faster while improving accuracy over prior methods.
citing papers explorer
-
AlignPose: Generalizable 6D Pose Estimation via Multi-view Feature-metric Alignment
AlignPose performs generalizable 6D pose estimation by multi-view feature-metric refinement that minimizes feature discrepancy between on-the-fly rendered object features and observed images across calibrated views.
-
Code-in-the-Loop Forensics: Agentic Tool Use for Image Forgery Detection
ForenAgent lets MLLMs create and iteratively improve low-level Python tools for image forgery detection via a two-stage training pipeline and a new 100k-image benchmark dataset.
-
Pay Less Attention to Function Words for Free Robustness of Vision-Language Models
FDA differentially subtracts function-word cross-attention from original attention heads to cut attack success rates by 18-90% across models and tasks while dropping performance by at most 0.6%.
-
FedHarmony: Harmonizing Heterogeneous Label Correlations in Federated Multi-Label Learning
FedHarmony harmonizes heterogeneous label correlations in federated multi-label learning via consensus correlations as global teachers and quality-weighted aggregation, with an accelerated optimizer that converges faster while improving accuracy over prior methods.