Hirokatsu Kataoka

14

Papers

42

Total Citations

Papers (14)

Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models

AgroBench: Vision-Language Model Benchmark in Agriculture

AnimalClue: Recognizing Animals by their Traces

Point Cloud Pre-Training With Natural 3D Structures

Replacing Labeled Real-Image Datasets With Auto-Generated Contours

Visual Atoms: Pre-Training Vision Transformers With Sinusoidal Waves

Graph Representation for Order-Aware Visual Transformation

Describing and Localizing Multiple Changes With Transformers

Frequency-aware GAN for Adversarial Manipulation Generation

Pre-training Vision Transformers with Very Limited Synthesized Images

SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learning

Neural Density-Distance Fields

Anticipating Traffic Accidents With Adaptive Loss and Large-Scale Incident DB

Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?