ArXiv Computer Vision research for Friday, June 07, 2024.

00:21: RU-AI: A Large Multimodal Dataset for Machine Generated Content Detection

01:52: AGBD: A Global-scale Biomass Dataset

03:30: MA-AVT: Modality Alignment for Parameter-Efficient Audio-Visual Transformers

04:52: Faster Than Lies: Real-time Deepfake Detection using Binary Neural Networks

06:03: Leveraging Activations for Superpixel Explanations

07:02: Joint Spatial-Temporal Modeling and Contrastive Learning for Self-supervised Heart Rate Measurement

08:28: Nacala-Roof-Material: Drone Imagery for Roof Detection, Classification, and Segmentation to Support Mosquito-borne Disease Risk Assessment

10:10: Multi-style Neural Radiance Field with AdaIN

10:52: Multiplane Prior Guided Few-Shot Aerial Scene Rendering

12:15: Semantic Segmentation on VSPW Dataset through Masked Video Consistency

13:24: CityCraft: A Real Crafter for 3D City Generation

15:21: ProMotion: Prototypes As Motion Learners

16:57: AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation

18:00: Clarifying Myths About the Relationship Between Shape Bias, Accuracy, and Robustness

19:50: GANetic Loss for Generative Adversarial Networks with a Focus on Medical Applications

21:35: Efficient 3D Shape Generation via Diffusion Mamba with Bidirectional SSMs

23:28: Bootstrapping Referring Multi-Object Tracking

24:50: Prototype Correlation Matching and Class-Relation Reasoning for Few-Shot Medical Image Segmentation

26:48: GenHeld: Generating and Editing Handheld Objects

27:57: Classification Metrics for Image Explanations: Towards Building Reliable XAI-Evaluations

29:11: Hibou: A Family of Foundational Vision Transformers for Pathology

30:41: Diving Deep into the Motion Representation of Video-Text Models

31:46: CoNo: Consistency Noise Injection for Tuning-free Long Video Diffusion

33:18: A Novel Time Series-to-Image Encoding Approach for Weather Phenomena Classification

34:48: LLavaGuard: VLM-based Safeguards for Vision Dataset Curation and Safety Assessment

36:06: Contextual fusion enhances robustness to image blurring

37:01: Energy Propagation in Scattering Convolution Networks Can Be Arbitrarily Slow

38:12: Towards Semantic Equivalence of Tokenization in Multimodal LLM

39:33: PatchSVD: A Non-uniform SVD-based Image Compression Algorithm

40:29: DVOS: Self-Supervised Dense-Pattern Video Object Segmentation

42:16: 3D-GRAND: Towards Better Grounding and Less Hallucination for 3D-LLMs