A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Patrick Bilic, Patrick Ferdinand Christ, Hongwei Li, et al.
The LiTS benchmark evaluates liver and tumor segmentation algorithms on a diverse CT dataset, finding no single algorithm excels at both tasks and highlighting the need for improved tumor detection.
Matteo Stefanini, Marcella Cornia, Lorenzo Baraldi, et al.
A comprehensive survey of deep learning-based image captioning, covering visual encoding, text generation, training strategies, datasets, and evaluation metrics.
Shuai Liu, Dongye Liu, Gautam Srivastava, et al.
Survey of correlation filter algorithms for real-time object tracking, covering background, key technologies, datasets, and reliability-based methods.
Paul Bergmann, Kilian Batzner, Michael Fauser, et al.
Introduces MVTec AD, a comprehensive dataset with 5354 high-resolution images across 15 categories for unsupervised anomaly detection, and benchmarks state-of-the-art methods.
Isabel O. Gallegos, Ryan A. Rossi, Joe Barrow, et al.
A comprehensive survey of bias evaluation and mitigation techniques for LLMs, proposing taxonomies for metrics, datasets, and mitigation methods.
Rabeeh Karimi Mahabadi, Yonatan Belinkov, James Henderson
Proposes two learning strategies to train neural models that are more robust to dataset biases and transfer better to out-of-domain datasets.
Nathan Shone, Trần Nguyên Ngọc, Vu Dinh Phai, et al.
Proposes a nonsymmetric deep autoencoder (NDAE) for unsupervised feature learning and a stacked NDAE classifier for network intrusion detection, evaluated on KDD Cup '99 and NSL-KDD datasets.
William T. Katz, Stephen M. Plaza
DVID is a distributed versioned image-oriented dataservice for EM-based connectomics datasets that supports branching, versioning, and flexible reintegration of data modifications.
Simon Baker, Daniel Scharstein, John Lewis, et al.
Proposes a new benchmark and evaluation methodology for optical flow algorithms, including diverse datasets and improved error metrics, to address challenges in complex natural scenes.
Zhenqin Wu, Bharath Ramsundar, Evan N. Feinberg, et al.
MoleculeNet provides a standardized benchmark for molecular machine learning, curating datasets and evaluating featurization and learning algorithms.
Takaya Saito, Marc Rehmsmeier
This paper demonstrates that Precision-Recall (PRC) plots are more informative than ROC plots for evaluating binary classifiers on imbalanced datasets, as ROC plots can be misleading due to misinterpretation of specificity.
Emilio Ferrara
This survey explores early trends, datasets, and challenges in applying large language models to wearable sensor data for human activity recognition, health monitoring, and behavioral modeling.