![[2606.01896] Train, Test, Re-evaluate: Schedule-Sensitive Evaluation of Generative Data for Hand Detection](/static/img/curated/desks/afbytes-tech.png)
[2606.01896] Train, Test, Re-evaluate: Schedule-Sensitive Evaluation of Generative Data for Hand Detection
Abstract page for arXiv paper 2606.01896: Train, Test, Re-evaluate: Schedule-Sensitive Evaluation of Generative Data for Hand Detection
America Forever Bytes
computer vision · AFBytes
Other
computer vision
Recent coverage
[2606.01900] Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation
Abstract page for arXiv paper 2606.01900: Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation
[2606.01901] The Image Reconstruction Game: Drawing Common Ground Through Iterative Multimodal Dialogue
Abstract page for arXiv paper 2606.01901: The Image Reconstruction Game: Drawing Common Ground Through Iterative Multimodal Dialogue
[2606.01933] 3rd Place at CVPR 2026 CASTLE Challenge: Agentic Multi-View Long-Context Video Understanding via Hierarchical Knowledge Graph Retrieval
Abstract page for arXiv paper 2606.01933: 3rd Place at CVPR 2026 CASTLE Challenge: Agentic Multi-View Long-Context Video Understanding via Hierarchical Knowledg...
[2606.01939] SAVMap: Structure-Aided Visual Mapping of Large-Scale 2.5D Manhattan Wireframes from Panoramic Video
Abstract page for arXiv paper 2606.01939: SAVMap: Structure-Aided Visual Mapping of Large-Scale 2.5D Manhattan Wireframes from Panoramic Video
[2606.02022] Ranking vs. Assignment: The Metric Mismatch in Multi-View Object Association
Abstract page for arXiv paper 2606.02022: Ranking vs. Assignment: The Metric Mismatch in Multi-View Object Association
[2606.01981] Generalization Limits in Vehicle Re-Identification
Abstract page for arXiv paper 2606.01981: Generalization Limits in Vehicle Re-Identification
[2208.00967] Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification
Abstract page for arXiv paper 2208.00967: Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification
[2307.06647] DeepIPCv2: LiDAR-powered Robust Environmental Perception and Navigational Control for Autonomous Vehicle
Abstract page for arXiv paper 2307.06647: DeepIPCv2: LiDAR-powered Robust Environmental Perception and Navigational Control for Autonomous Vehicle
[2606.02242] Towards Resolving Optimization Conflicts Between Image- and Text-Based Person Re-Identification
Abstract page for arXiv paper 2606.02242: Towards Resolving Optimization Conflicts Between Image- and Text-Based Person Re-Identification
[2606.02342] Detecting Pen-In-Air States from Video: A Proof-of-Concept Toward Complementary Handwriting Analysis
Abstract page for arXiv paper 2606.02342: Detecting Pen-In-Air States from Video: A Proof-of-Concept Toward Complementary Handwriting Analysis
[2606.02350] TROPHIES: Temporal Reconstruction of Places, Humans, and Cameras from Multi-view Videos
Abstract page for arXiv paper 2606.02350: TROPHIES: Temporal Reconstruction of Places, Humans, and Cameras from Multi-view Videos
[2606.02352] Multi-modal Video Representation Alignment for Robust Self-supervised Driver Distraction Detection
Abstract page for arXiv paper 2606.02352: Multi-modal Video Representation Alignment for Robust Self-supervised Driver Distraction Detection
[2606.02402] Explainable Forensics of Manipulated Segments in Untrimmed Long Videos
Abstract page for arXiv paper 2606.02402: Explainable Forensics of Manipulated Segments in Untrimmed Long Videos
[2606.02379] Honey, I Shrunk the Arc de Triomphe!
Abstract page for arXiv paper 2606.02379: Honey, I Shrunk the Arc de Triomphe!
[2606.01608] Exploiting Semantic and Pixel Representations for Ultra-Low Bitrate Image Compression
Abstract page for arXiv paper 2606.01608: Exploiting Semantic and Pixel Representations for Ultra-Low Bitrate Image Compression
[2605.30399] A Novel Computer Vision Approach for Assessing Fish Responses to Intrusive Objects in Aquaculture
Abstract page for arXiv paper 2605.30399: A Novel Computer Vision Approach for Assessing Fish Responses to Intrusive Objects in Aquaculture
[2605.31283] Topologically Consistent Multi-view 3D Head Reconstruction via Coarse-Guided Layered Surface Sampling
Abstract page for arXiv paper 2605.31283: Topologically Consistent Multi-view 3D Head Reconstruction via Coarse-Guided Layered Surface Sampling
[2507.11075] Joint angle based learning to refine kinematic human pose estimation
Abstract page for arXiv paper 2507.11075: Joint angle based learning to refine kinematic human pose estimation
[2605.29417] ParCo-SDF: Learning Prior-Free Partial-to-Complete Signed Distance Fields of Deformable Objects
Abstract page for arXiv paper 2605.29417: ParCo-SDF: Learning Prior-Free Partial-to-Complete Signed Distance Fields of Deformable Objects
[2605.30111] xModel-KD: Cross-modal Knowledge Distillation for 3D Scene Perception using LiDAR
Abstract page for arXiv paper 2605.30111: xModel-KD: Cross-modal Knowledge Distillation for 3D Scene Perception using LiDAR
Robust rigid registration via maximum correntropy criterion: a novel approach
Point set registration is essential for computer vision, pattern recognition and intelligent robotics. Existing registration methods exhibit limited robustness ...
[2605.28806] Personal Visual Memory from Explicit and Implicit Evidence
Abstract page for arXiv paper 2605.28806: Personal Visual Memory from Explicit and Implicit Evidence
[2605.27460] D$^2$Turb: Depth-Aware Simulation and Decoupled Learning for Single-Frame Atmospheric Turbulence Mitigation
Abstract page for arXiv paper 2605.27460: D$^2$Turb: Depth-Aware Simulation and Decoupled Learning for Single-Frame Atmospheric Turbulence Mitigation
[2605.28257] Category-Level 3D Correspondence in Camera Space via Morphable Object Priors
Abstract page for arXiv paper 2605.28257: Category-Level 3D Correspondence in Camera Space via Morphable Object Priors
[2605.28261] MORI-Seg: Learning Morphological Geometry for Instance Segmentation without Instance Annotations
Abstract page for arXiv paper 2605.28261: MORI-Seg: Learning Morphological Geometry for Instance Segmentation without Instance Annotations
[2605.28270] Every9D-21M: Large-Scale Real-World 9D Canonicalization of Everyday Objects
Abstract page for arXiv paper 2605.28270: Every9D-21M: Large-Scale Real-World 9D Canonicalization of Everyday Objects
[2605.28587] Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillation
Abstract page for arXiv paper 2605.28587: Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillation
[2605.27962] Bridging the Generalization Gap in Adverse Weather Segmentation: A Training Recipe Perspective
Abstract page for arXiv paper 2605.27962: Bridging the Generalization Gap in Adverse Weather Segmentation: A Training Recipe Perspective
[2605.28125] CLEAR-NeRF: Collinearity and Local-region Enhanced Accurate 3D Reconstruction in Unbounded Scenes
Abstract page for arXiv paper 2605.28125: CLEAR-NeRF: Collinearity and Local-region Enhanced Accurate 3D Reconstruction in Unbounded Scenes