https://github.com/D-ST-Sword/ATD
공식 코드Alternative Telescopic Displacement: An Efficient Multimodal Alignment Method
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
This task asks models to answer questions about which times certain events could have occurred.
Source: BIG-bench
Image source: BIG-bench
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Alternative Telescopic Displacement: An Efficient Multimodal Alignment Method
Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs
Scalable Mechanistic Neural Networks for Differential Equations and Machine Learning
Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks
Explainable Graph Pyramid Autoformer for Long-Term Traffic Forecasting
Remaining Useful Life Prediction for Aircraft Engines using LSTM
NuTime: Numerically Multi-Scaled Embedding for Large-Scale Time-Series Pretraining
SpikeReveal: Unlocking Temporal Sequences from Real Blurry Inputs with Spike Streams
Cross-attention Spatio-temporal Context Transformer for Semantic Segmentation of Historical Maps
Leveraging Language Foundation Models for Human Mobility Forecasting
TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data
A Graph Attention Spatio-temporal Convolutional Network for 3D Human Pose Estimation in Video
TrajSceneLLM: A Multimodal Perspective on Semantic GPS Trajectory Analysis
Using stigmergy as a computational memory in the design of recurrent neural networks
Learning future terrorist targets through temporal meta-graphs
M2A: Motion Aware Attention for Accurate Video Action Recognition
Representation Learning via Global Temporal Alignment and Cycle-Consistency
Reducing ANN-SNN Conversion Error through Residual Membrane Potential
KAN-AD: Time Series Anomaly Detection with Kolmogorov-Arnold Networks
tSPM+; a high-performance algorithm for mining transitive sequential patterns from clinical data
tSPM+; a high-performance algorithm for mining transitive sequential patterns from clinical data
Human or Machine? It Is Not What You Write, But How You Write It
Proactive Robot Assistance via Spatio-Temporal Object Modeling
xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories
TiMo: Spatiotemporal Foundation Model for Satellite Image Time Series
Robust Explainer Recommendation for Time Series Classification
Working memory facilitates reward-modulated Hebbian learning in recurrent neural networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.