GeoFidelity-Bench shows text-to-image models gain city-level plausibility from local names but achieve near-zero improvement in exact segment identity, with GPS coordinates adding no benefit.
hub
360mvsnet: Deep multi-view stereo network with 360° images for indoor scene reconstruction
25 Pith papers cite this work. Polarity classification is still indexing.
25
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
AgroVG is a new multi-source benchmark for agricultural visual grounding formulated as generalized set prediction, with protocols for box and mask grounding across single-target, multi-target, and target-absent queries from six object families.
AIGaitor is the first claimed end-to-end on-device monocular motion-capture and deep-learning gait analysis pipeline demonstrated on consumer smartphones.
Driver-WM is a driver-centric latent world model for causal rollout of in-cabin dynamics conditioned on out-cabin traffic, unifying kinematics forecasting with behavioral and emotional recognition via dual-stream architecture and gated injection.
GEODE uses per-sample cosine-similarity scaling in a norm loss to preserve feature geometry for universal scorer-compatible OOD detection, matching or exceeding OE performance on CIFAR benchmarks.
DHCNet improves ultra-fine-grained visual categorization by progressively building holistic cognition from local discrepancies using self-shuffling and refinement on limited data.
SARR modifies trigonometric rotation encodings with object symmetry orders to produce unique continuous poses, enabling standard CNNs to outperform existing methods on symmetry-aware 6D pose estimation without custom losses or 3D models.
TCG-AR is a real-time multi-view AR system for trading card games using only commodity RGB cameras and synthetic training data.
SENTRY is a plug-and-play module that replaces confidence-based memory writes with neighbor-aware cycle-consistent validation in SAM2 trackers, yielding new zero-shot SOTA results on LaSOT, GOT-10k and other benchmarks.
Uncertainty decomposition via deep ensembles separates annotator disagreement from distribution shift in FER, enabling a routing mechanism that retains 1.8x more ambiguous faces at matched OOD rejection compared to single-uncertainty baselines.
Venice-H1 improves failure-case mIoU by 0.89-1.40 points in referring image segmentation via multi-scale grid signatures and a failure-aware re-ranker, with positive CIs on all tested pairs and low harmful-switch rates.
A multi-contrast self-supervised MRI reconstruction framework with end-to-end learned k-space partitioning produces higher-fidelity images than single-contrast self-supervised baselines on two public datasets.
Introduces SOCK (SOft Competing Kernels), a differentiable random convolutional feature map, to train generative models of financial time series via feature matching and shows outperformance over signature and diffusion baselines on small-sample datasets.
A two-stage framework that decouples generation, selection, and refinement to improve budget use in diffusion-based dataset distillation.
Deep UCSL uses a contrastive EM loss on patient-control labels to isolate disease-driven subgroups in medical imaging by suppressing shared healthy variability.
UJEM-KL improves cross-model transferability of untargeted jailbreaks on VLMs by maximizing entropy at decision tokens rather than enforcing fixed response patterns.
Late fusion of asynchronous vehicle predictions improves trajectory success rate (TSR_0.5) by 1.22-1.69% on real-world V2V4Real data compared to single-vehicle forecasting.
MaMe is a differentiable matrix-only token merging method that doubles ViT-B throughput with a 2% accuracy drop on pre-trained models and enables faster, higher-quality image synthesis when paired with MaRe.
RealLiFe optimizes multi-plane images with HSGD to deliver real-time light field reconstruction from sparse views, claiming 100x speedup over offline methods and 2 dB PSNR gain over online ones.
COPRA introduces conditional parameter adaptation via RL to dynamically tune frozen VLMs for video anomaly detection, outperforming static methods in in-domain and cross-domain settings while generalizing to other video tasks.
DeFakerOne is a unified foundation model for joint image-level fake image detection and pixel-level localization that reports SOTA results on 39 detection and 9 localization benchmarks.
A responsible computing framework substitutes real protest imagery with labeled synthetic reproductions from conditional image synthesis to enable privacy-aware analysis of collective action patterns.
STEP uses dynamic superpatch merging via dCTS and early token exits to cut token count by 2.5x and computational complexity by up to 4x on ViT-Large for high-res segmentation, with at most 2% accuracy drop and 40% tokens halted early.
Foundation models excel at pattern recognition in biomedical imaging but lack causal reasoning, robustness, and safety for real-world use, so they should augment rather than replace clinical expertise according to the proposed REAL-FM assessment framework.
citing papers explorer
-
GeoFidelity-Bench: Evaluating Segment-Level Geographic Fidelity in Text-to-Image Street-View Generation
GeoFidelity-Bench shows text-to-image models gain city-level plausibility from local names but achieve near-zero improvement in exact segment identity, with GPS coordinates adding no benefit.
-
AgroVG: A Large-Scale Multi-Source Benchmark for Agricultural Visual Grounding
AgroVG is a new multi-source benchmark for agricultural visual grounding formulated as generalized set prediction, with protocols for box and mask grounding across single-target, multi-target, and target-absent queries from six object families.
-
AIGaitor: Privacy-preserving and cloud-free motion analysis for everyone, using edge computing
AIGaitor is the first claimed end-to-end on-device monocular motion-capture and deep-learning gait analysis pipeline demonstrated on consumer smartphones.
-
Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout
Driver-WM is a driver-centric latent world model for causal rollout of in-cabin dynamics conditioned on out-cabin traffic, unifying kinematics forecasting with behavioral and emotional recognition via dual-stream architecture and gated injection.
-
GEODE: Angle-Adaptive OOD Detection with Universal Scorer Compatibility
GEODE uses per-sample cosine-similarity scaling in a norm loss to preserve feature geometry for universal scorer-compatible OOD detection, matching or exceeding OE performance on CIFAR benchmarks.
-
Divide-and-Conquer Approach to Holistic Cognition in High-Similarity Contexts with Limited Data
DHCNet improves ultra-fine-grained visual categorization by progressively building holistic cognition from local discrepancies using self-shuffling and refinement on limited data.
-
Towards Symmetry-sensitive Pose Estimation: A Rotation Representation for Symmetric Object Classes
SARR modifies trigonometric rotation encodings with object symmetry orders to produce unique continuous poses, enabling standard CNNs to outperform existing methods on symmetry-aware 6D pose estimation without custom losses or 3D models.
-
TCG-AR: Real-Time Multi-View Augmented Reality for Trading Card Game Streaming
TCG-AR is a real-time multi-view AR system for trading card games using only commodity RGB cameras and synthetic training data.
-
SENTRY: SAM2-Enhanced Neighbor-Aware and Temporally Reasoned Memory for Visual Tracking
SENTRY is a plug-and-play module that replaces confidence-based memory writes with neighbor-aware cycle-consistent validation in SAM2 trackers, yielding new zero-shot SOTA results on LaSOT, GOT-10k and other benchmarks.
-
Interpretable Uncertainty Routing Separating Emotion Ambiguity from Distribution Shift in Facial Expression Recognition
Uncertainty decomposition via deep ensembles separates annotator disagreement from distribution shift in FER, enabling a routing mechanism that retains 1.8x more ambiguous faces at matched OOD rejection compared to single-uncertainty baselines.
-
Venice-H1: Failure-Aware Query Re-Ranking with Multi-Scale Grid Signatures for Referring Image Segmentation
Venice-H1 improves failure-case mIoU by 0.89-1.40 points in referring image segmentation via multi-scale grid signatures and a failure-aware re-ranker, with positive CIs on all tested pairs and low harmful-switch rates.
-
Optimized Multi-Contrast Self-Supervised MRI Reconstruction using Learned k-space Partitioning
A multi-contrast self-supervised MRI reconstruction framework with end-to-end learned k-space partitioning produces higher-fidelity images than single-contrast self-supervised baselines on two public datasets.
-
Generating Financial Time Series by Matching Random Convolutional Features
Introduces SOCK (SOft Competing Kernels), a differentiable random convolutional feature map, to train generative models of financial time series via feature matching and shows outperformance over signature and diffusion baselines on small-sample datasets.
-
Pool-Select-Refine for Allocation-Aware Generative Dataset Distillation
A two-stage framework that decouples generation, selection, and refinement to improve budget use in diffusion-based dataset distillation.
-
Automatic Discovery of Disease Subgroups by Contrasting with Healthy Controls
Deep UCSL uses a contrastive EM loss on patient-control labels to isolate disease-driven subgroups in medical imaging by suppressing shared healthy variability.
-
Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization
UJEM-KL improves cross-model transferability of untargeted jailbreaks on VLMs by maximizing entropy at decision tokens rather than enforcing fixed response patterns.
-
Collaborative Trajectory Prediction via Late Fusion
Late fusion of asynchronous vehicle predictions improves trajectory success rate (TSR_0.5) by 1.22-1.69% on real-world V2V4Real data compared to single-vehicle forecasting.
-
MaMe & MaRe: Matrix-Based Token Merging and Restoration for Efficient Visual Perception and Synthesis
MaMe is a differentiable matrix-only token merging method that doubles ViT-B throughput with a 2% accuracy drop on pre-trained models and enables faster, higher-quality image synthesis when paired with MaRe.
-
RealLiFe: Real-Time Light Field Reconstruction via Hierarchical Sparse Gradient Descent
RealLiFe optimizes multi-plane images with HSGD to deliver real-time light field reconstruction from sparse views, claiming 100x speedup over offline methods and 2 dB PSNR gain over online ones.
-
COPRA: Conditional Parameter Adaptation with Reinforcement Learning for Video Anomaly Detection
COPRA introduces conditional parameter adaptation via RL to dynamically tune frozen VLMs for video anomaly detection, outperforming static methods in in-domain and cross-domain settings while generalizing to other video tasks.
-
Venus-DeFakerOne: Unified Fake Image Detection & Localization
DeFakerOne is a unified foundation model for joint image-level fake image detection and pixel-level localization that reports SOTA results on 39 detection and 9 localization benchmarks.
-
Protecting and Preserving Protest Dynamics for Responsible Analysis
A responsible computing framework substitutes real protest imagery with labeled synthetic reproductions from conditional image synthesis to enable privacy-aware analysis of collective action patterns.
-
Where Do Tokens Go? Understanding Pruning Behaviors in STEP at High Resolutions
STEP uses dynamic superpatch merging via dCTS and early token exits to cut token count by 2.5x and computational complexity by up to 4x on ViT-Large for high-res segmentation, with at most 2% accuracy drop and 40% tokens halted early.
-
Foundation Models in Biomedical Imaging: Turning Hype into Reality
Foundation models excel at pattern recognition in biomedical imaging but lack causal reasoning, robustness, and safety for real-world use, so they should augment rather than replace clinical expertise according to the proposed REAL-FM assessment framework.
-
SoccerNet 2026 Challenges Results
The SoccerNet 2026 Challenges benchmarked 427 teams across five soccer video understanding tasks, with leading submissions improving over baselines on all tasks.