A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Joel Haskin Saltz, Rajarsi Gupta, Le Hou, et al.
Deep learning classifies H&E image patches to map tumor-infiltrating lymphocytes across 13 TCGA tumor types, revealing spatial patterns linked to survival and molecular subtypes.
Xiangbin Liu, Liping Song, Shuai Liu, et al.
A comprehensive review of deep-learning-based medical image segmentation methods, summarizing three main approaches, their limitations, and future directions to address accuracy and data challenges.
Baoguang Shi, Xiang Bai, Cong Yao
A novel end-to-end trainable neural network integrates feature extraction, sequence modeling, and transcription for scene text recognition without character segmentation.
Catherine Wah
CUB-200-2011 extends the CUB-200 dataset to 200 bird species with doubled images per category, new part localization annotations, and benchmarks for categorization and part localization.
Alain Trémeau, Philippe Colantoni
Presents algorithms combining region adjacency graph and line graph structures to enhance color image segmentation via region growing and watershed transformation.
Shervin Minaee, Yuri Y. Boykov, Fatih Porikli, et al.
A comprehensive survey of deep learning approaches for image segmentation, covering architectures, datasets, performance comparisons, and future directions.
Chao Dong, Chen Change Loy, Kaiming He, et al.
This paper introduces SRCNN, a deep CNN that learns an end-to-end mapping for single image super-resolution, outperforming sparse-coding methods.
Vijay Badrinarayanan, Alex Kendall, Roberto Cipolla
SegNet introduces a deep encoder-decoder architecture for semantic segmentation that uses max-pooling indices for efficient non-linear upsampling, achieving competitive accuracy with low memory and inference time.
Unknown
Viewformer is a NeRF-free neural rendering method that uses transformers to synthesize novel views from few sparsely covering context images.
Unknown
Neutex introduces neural texture mapping for volumetric neural rendering, enabling realistic image synthesis by leveraging volumetric neural rendering techniques.
Unknown
Tune-A-Video enables one-shot text-to-video generation by tuning a pretrained image diffusion model on a single video.
Liangchen Li, Jiajun He
Bidirectional consistency models extend consistency models to enable both forward and reverse sampling, improving image generation quality and flexibility.