ArXiv Computer Vision research for Friday, June 07, 2024. 00:20: Image Processing Based Forest Fire Detection 01:08: STAR: Skeleton-aware Text-based 4D Avatar Generation with In-Network Motion Retargeting 03:05: UVCPNet: A UAV-Vehicle Collaborative Perception Network for 3D Object Detection 04:47: UCDNet: Multi-UAV Collaborative 3D Object Detection Network by Reliable Feature Mapping 06:14: SMART: Scene-motion-aware human action recognition framework for mental disorder group 08:12: LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model 09:34: Evaluating and Mitigating IP Infringement in Visual Generative AI 11:01: MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models 12:20: OVMR: Open-Vocabulary Recognition with Multi-Modal References 13:57: ACE Metric: Advection and Convection Evaluation for Accurate Weather Forecasting 15:11: XctDiff: Reconstruction of CT Images with Consistent Anatomical Structures from a Single Radiographic Projection Image 16:22: MTS-Net: Dual-Enhanced Positional Multi-Head Self-Attention for 3D CT Diagnosis of May-Thurner Syndrome 17:58: CDeFuse: Continuous Decomposition for Infrared and Visible Image Fusion 19:41: MGIMM: Multi-Granularity Instruction Multimodal Model for Attribute-Guided Remote Sensing Image Detailed Description 21:24: PQPP: A Joint Benchmark for Text-to-Image Prompt and Query Performance Prediction 22:58: Interpretable Multimodal Out-of-context Detection with Soft Logic Regularization 24:24: SMC++: Masked Learning of Unsupervised Video Semantic Compression 26:19: Diffusion-based Generative Image Outpainting for Recovery of FOV-Truncated CT Images 27:09: MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks 28:35: Predictive Dynamic Fusion 29:43: Online Continual Learning of Video Diffusion Models From a Single Video Stream 30:40: A short review on graphonometric evaluation tools in children 31:49: Navigating Efficiency in MobileViT through Gaussian Process on Global Architecture Factors 33:04: EGOR: Efficient Generated Objects Replay for incremental object detection 34:37: 3rd Place Solution for MeViS Track in CVPR 2024 PVUW workshop: Motion Expression guided Video Segmentation 36:02: Multi-Granularity Language-Guided Multi-Object Tracking 37:56: Normal-guided Detail-Preserving Neural Implicit Functions for High-Fidelity 3D Surface Reconstruction 39:52: Ada-VE: Training-Free Consistent Video Editing Using Adaptive Motion Prior 41:48: 3DRealCar: An In-the-wild RGB-D Car Dataset with 360-degree Views 43:54: Seeing the Unseen: Visual Metaphor Captioning for Videos 45:09: Zero-Shot Video Editing through Adaptive Sliding Score Distillation 46:28: Labeled Data Selection for Category Discovery