AI Research

AI & ML Research Papers

A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.

All Papers

29 papers

JournalProceedings of the National Academy of Sciences2018

Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning

Mohammad Sadegh Norouzzadeh, Anh‐Tu Nguyen, Margaret Kosmala, et al.

This paper demonstrates that deep convolutional neural networks can automatically identify, count, and describe behaviors of 48 animal species in camera-trap images, achieving human-level accuracy and saving years of manual labeling effort.

1.2kJun 5, 2018Neural Networks

ConferenceAAAI Conference on Artificial Intelligence2020

EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs

Aldo Pareja, Giacomo Domeniconi, Jie Chen, et al.

EvolveGCN adapts GCN parameters over time using an RNN to handle dynamic graphs without relying on node embeddings.

1.6kApr 3, 2020Neural Networks

arXiv

PreprintMedical Image Analysis2018

Weakly-supervised convolutional neural networks for multimodal image registration

Yipeng Hu, Marc Modat, Eli Gibson, et al.

This paper introduces a weakly-supervised CNN approach for multimodal image registration that learns voxel-level transformations from anatomical labels, enabling real-time, fully-automated inference without labels.

466Jul 4, 2018MultimodalNeural Networks

arXiv

PreprintarXiv.org2025

Universal Reasoning Model

Zitian Gao, Lynx Chen, Yihao Xiao, et al.

The paper proposes the Universal Reasoning Model (URM), which enhances universal transformers with short convolution and truncated backpropagation, achieving state-of-the-art results on ARC-AGI benchmarks.

5Dec 16, 2025TransformersReasoning

arXiv

Preprint2026

Correlated low-rank adaptation for convnets

Unknown

Introduces Correlated Low-Rank Adaptation (CoLoRA), a novel framework that explicitly models correlations among low-rank factors to improve parameter-efficient fine-tuning of convolutional networks.

0Jan 1, 2026

PreprintQatar University QSpace (Qatar University)2021

1D convolutional neural networks and applications: A survey

Kiranyaz, Mustafa Serkan, Onur Avcı, Osama Abdeljaber, et al.

This paper provides the first comprehensive review of 1D CNNs, covering their architecture, applications, and state-of-the-art performance in fields like biomedical data classification and structural health monitoring.

2.7kJan 1, 2021BenchmarksComputer Vision

arXiv

JournalIEEE Transactions on Intelligent Transportation Systems2017

ERFNet: Efficient Residual Factorized ConvNet for Real-Time Semantic Segmentation

Eduardo Romera, Jose M. Álvarez, Luis M. Bergasa, et al.

ERFNet introduces a novel efficient residual factorized convolutional layer for real-time semantic segmentation, achieving high accuracy at over 83 FPS on Titan X and 7 FPS on Jetson TX1.

1.5kOct 9, 2017Neural Networks

JournalApplied Sciences2023

A New Method to Detect Splicing Image Forgery Using Convolutional Neural Network

Khalid M. Hosny, Akram M. Mortda, Nabil A. Lashin, et al.

A lightweight CNN with only four convolutional layers achieves high accuracy (99.1-100%) for detecting splicing image forgery across multiple datasets.

34Jan 18, 2023Neural Networks

JournalPLoS Computational Biology2018

Deep convolutional networks do not classify based on global object shape

Nicholas Baker, Hongjing Lu, Gennady Erlikhman, et al.

Deep convolutional networks classify objects using local edge features, not global shape, unlike human vision.

400Dec 7, 2018Computer Vision

PreprintSensors2018

SECOND: Sparsely Embedded Convolutional Detection

Yan Yan, Yuxing Mao, Bo Li

Proposes SECOND, a sparse convolutional network with angle loss regression and data augmentation for fast and accurate 3D object detection from LiDAR.

3.6kOct 6, 2018BenchmarksComputer Vision

ConferenceIEEE Transactions on Pattern Analysis and Machine Intelligence2016Featured

Fully Convolutional Networks for Semantic Segmentation

Evan Shelhamer, Jonathan Long, Trevor Darrell

Fully convolutional networks trained end-to-end for semantic segmentation achieve state-of-the-art results by adapting classification nets and using a skip architecture for detailed predictions.

11kMay 24, 2016Fine Tuning

ConferenceIEEE Transactions on Pattern Analysis and Machine Intelligence2017Featured

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, et al.

DeepLab advances semantic segmentation via atrous convolution, ASPP, and fully connected CRFs, achieving state-of-the-art on multiple benchmarks.

22kApr 27, 2017Neural Networks

arXiv