https://github.com/easylearningscores/pastnet
공식 코드PastNet: Introducing Physical Inductive Biases for Spatio-temporal Video Prediction
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
PastNet: Introducing Physical Inductive Biases for Spatio-temporal Video Prediction
SPAP: Simultaneous Demand Prediction and Planning for Electric Vehicle Chargers in a New City
Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction
Multi-axis Attentive Prediction for Sparse EventData: An Application to Crime Prediction
How Many and Which Training Points Would Need to be Removed to Flip this Prediction?
SA-Attack: Speed-adaptive stealthy adversarial attack on trajectory prediction
Rethinking Transformer-based Set Prediction for Object Detection
PowerBEV: A Powerful Yet Lightweight Framework for Instance Prediction in Bird's-Eye View
Uncertainty and Prediction Quality Estimation for Semantic Segmentation via Graph Neural Networks
Optimal Operation of a Building with Electricity-Heat Networks and Seasonal Storage
Personal-ITY: A Novel YouTube-based Corpus for Personality Prediction in Italian
Distribution-Free Predictive Inference under Unknown Temporal Drift
PIVEN: A Deep Neural Network for Prediction Intervals with Specific Value Prediction
BioBLP: A Modular Framework for Learning on Multimodal Biomedical Knowledge Graphs
Exploring evolution-aware & -free protein language models as protein function predictors
ALBRT: Cellular Composition Prediction in Routine Histology Images
Object-aware Monocular Depth Prediction with Instance Convolutions
Lightweight Facial Attractiveness Prediction Using Dual Label Distribution
Forecasting Future International Events: A Reliable Dataset for Text-Based Event Modeling
Meta Transfer Learning for Early Success Prediction in MOOCs
Personalized Collaborative Fine-Tuning for On-Device Large Language Models
Sparse Prototype Network for Explainable Pedestrian Behavior Prediction
Multi-model Ensemble Conformal Prediction in Dynamic Environments
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.