Proposes a cyclic 2.5D perceptual loss with manufacturer SUVR standardization for T1w MRI to tau PET synthesis, reporting improved regional agreement on ADNI and SCAN cohorts across U-Net, UNETR, SwinUNETR, CycleGAN, and Pix2Pix.
hub
author Tang, Y
20 Pith papers cite this work. Polarity classification is still indexing.
20
Pith papers citing it
hub tools
citation-role summary
background 3
dataset 1
citation-polarity summary
polarities
background 4representative citing papers
Large vision-language models exhibit severe object hallucination that varies with training instructions, and the proposed POPE polling method evaluates it more stably and flexibly than prior approaches.
AF3AD is a modular synthesis framework using center-conditioned parametric deformations in local PCA frames to create diverse pseudo-anomalies, improving unsupervised 3D anomaly detection on AnomalyShapeNet and Real3D-AD.
Bengal-HP_RU is the first publicly available head pose dataset for Bengali subjects, with 12,894 images collected from Wikimedia Commons and partitioned by uploader identity.
A Diffusion Transformer framework applies coordinate-transformed RoPE and disjoint attention masks to achieve controllable, high-fidelity texture tiling that preserves reference structure and scene lighting.
ST-Merge uses gated cross-attention to adaptively weight source models during merging, outperforming baselines on multilingual reasoning tasks across 21 languages.
MS-DKC is a dataset knowledge card framework that maps image, morphology, supervision, context, and risk descriptors to design priors and failure modes, shown to produce dataset-specific model adaptations with improved metrics on DRIVE, ISIC2018, and ACDC.
AdaCodec introduces a predictive visual code that cuts visual token use in video MLLMs by sending full frames only on high predictive cost and otherwise encoding inter-frame changes as P-tokens, yielding better benchmark scores at lower budgets.
Proposes a psychovisual-inspired deep learning method that encodes images in learned frequency sub-bands for interpretable semantic structures and reduced depth dependence.
A framework trains keypoint detectors on inpainted markerless robot images and uses runtime inpainting plus UKF for robust vision-based control without models or calibration.
RoMAE applies rotary positional embeddings to masked autoencoders to enable representation learning and interpolation on continuous positional data across irregular time-series, images, and audio without modality-specific modifications.
MapDreamer synthesizes lane-level maps from aerial imagery via VAE latent encoding, transformer latent diffusion conditioned on aerial features, a lane cardinality module with ghost latents, and sliding-window graph aggregation, showing improved fidelity on UrbanLaneGraph data.
μFlow trains a normalizing flow on averaged real-image features to detect deepfakes via likelihood in a fully out-of-distribution setting.
A semi-supervised VAE combined with static and residual motion LDMs generates anatomically consistent 4D cardiac MRI, achieving Pearson r > 0.8 controllability and 1.4% Dice improvement in downstream segmentation when used for data augmentation.
LinStereo uses Position-Aware Linear Attention, Hierarchical Semantic Cost Volumes, and Depth Prior Initialization to enable global aggregation in iterative stereo matching at linear complexity, showing improved performance on standard and underwater benchmarks.
Uses TPE-based neural architecture search to tune MW-Net's layers, nodes, and input layer for combined label noise and class imbalance, showing improved results on modified CIFAR-10/100.
This is the first comprehensive survey of OOD generalization methodologies for time series, organized across data distribution, representation learning, and OOD evaluation.
A UAS with YOLO-based swimmer detection and DES simulations reduces drowning rescue response time by a factor of five versus standard operations in tested lake areas.
PaliGemma is an open 3B VLM based on SigLIP and Gemma that achieves strong performance on nearly 40 diverse open-world tasks including benchmarks, remote-sensing, and segmentation.
NTGA is the first clean-label generalization attack under black-box settings but is vulnerable to adversarial training and image transformations, with newer attacks outperforming it.
citing papers explorer
-
Cyclic 2.5D Perceptual Loss for Cross-Modal 3D Medical Image Synthesis: T1w MRI to Tau PET
Proposes a cyclic 2.5D perceptual loss with manufacturer SUVR standardization for T1w MRI to tau PET synthesis, reporting improved regional agreement on ADNI and SCAN cohorts across U-Net, UNETR, SwinUNETR, CycleGAN, and Pix2Pix.
-
Anomaly Factory 3D: A Modular Framework for Diverse Pseudo-Anomaly Synthesis in Unsupervised 3D Anomaly Detection
AF3AD is a modular synthesis framework using center-conditioned parametric deformations in local PCA frames to create diverse pseudo-anomalies, improving unsupervised 3D anomaly detection on AnomalyShapeNet and Real3D-AD.
-
Bengal-HP_RU: A Dataset of Bengal People For Head Pose Estimation
Bengal-HP_RU is the first publicly available head pose dataset for Bengali subjects, with 12,894 images collected from Wikimedia Commons and partitioned by uploader identity.
-
Controllable Texture Tiling with Transformed RoPE-Enhanced Diffusion Models
A Diffusion Transformer framework applies coordinate-transformed RoPE and disjoint attention masks to achieve controllable, high-fidelity texture tiling that preserves reference structure and scene lighting.
-
Enhancing Multilingual Reasoning via Steerable Model Merging
ST-Merge uses gated cross-attention to adaptively weight source models during merging, outperforming baselines on multilingual reasoning tasks across 21 languages.
-
MS-DKC: A Dataset Knowledge Card Framework for Designing and Adapting Medical Image Segmentation Models
MS-DKC is a dataset knowledge card framework that maps image, morphology, supervision, context, and risk descriptors to design priors and failure modes, shown to produce dataset-specific model adaptations with improved metrics on DRIVE, ISIC2018, and ACDC.
-
AdaCodec: A Predictive Visual Code for Video MLLMs
AdaCodec introduces a predictive visual code that cuts visual token use in video MLLMs by sending full frames only on high predictive cost and otherwise encoding inter-frame changes as P-tokens, yielding better benchmark scores at lower budgets.
-
Deep Psychovisual Image Representations
Proposes a psychovisual-inspired deep learning method that encodes images in learned frequency sub-bands for interpretable semantic structures and reduced depth dependence.
-
Utilizing Inpainting for Keypoint Detection for Vision-Based Control of Robotic Manipulators
A framework trains keypoint detectors on inpainted markerless robot images and uses runtime inpainting plus UKF for robust vision-based control without models or calibration.
-
Rotary Masked Autoencoders are Versatile Learners
RoMAE applies rotary positional embeddings to masked autoencoders to enable representation learning and interpolation on continuous positional data across irregular time-series, images, and audio without modality-specific modifications.
-
MapDreamer: Aerial Imagery Conditioned Latent Diffusion for Lane-Level Map Generation
MapDreamer synthesizes lane-level maps from aerial imagery via VAE latent encoding, transformer latent diffusion conditioned on aerial features, a lane cardinality module with ghost latents, and sliding-window graph aggregation, showing improved fidelity on UrbanLaneGraph data.
-
$\mu$Flow: Leveraging Average Images for Improving Generalisation of Deepfake Faces Detectors
μFlow trains a normalizing flow on averaged real-image features to detect deepfakes via likelihood in a fully out-of-distribution setting.
-
Anatomy-Guided Residual Motion Diffusion for Controllable 4D Cardiac MRI Synthesis
A semi-supervised VAE combined with static and residual motion LDMs generates anatomically consistent 4D cardiac MRI, achieving Pearson r > 0.8 controllability and 1.4% Dice improvement in downstream segmentation when used for data augmentation.
-
LinStereo: Linear-Complexity Global Attention for Multi-Scale Iterative Stereo Matching
LinStereo uses Position-Aware Linear Attention, Hierarchical Semantic Cost Volumes, and Depth Prior Initialization to enable global aggregation in iterative stereo matching at linear complexity, showing improved performance on standard and underwater benchmarks.
-
Neural Architecture Search of Sample Reweighting Networks for Complex Distribution Shift
Uses TPE-based neural architecture search to tune MW-Net's layers, nodes, and input layer for combined label noise and class imbalance, showing improved results on modified CIFAR-10/100.
-
Out-of-Distribution Generalization in Time Series: A Survey
This is the first comprehensive survey of OOD generalization methodologies for time series, organized across data distribution, representation learning, and OOD evaluation.
-
Autonomous Unmanned Aircraft Systems for Enhanced Search and Rescue of Drowning Swimmers: Image-Based Localization and Mission Simulation
A UAS with YOLO-based swimmer detection and DES simulations reduces drowning rescue response time by a factor of five versus standard operations in tested lake areas.
-
PaliGemma: A versatile 3B VLM for transfer
PaliGemma is an open 3B VLM based on SigLIP and Gemma that achieves strong performance on nearly 40 diverse open-world tasks including benchmarks, remote-sensing, and segmentation.