https://github.com/fwesterhout/Smooth-Trajectron
공식 코드Smooth-Trajectron++: Augmenting the Trajectron++ behaviour prediction model with smooth attention
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Trajectory Prediction is the problem of predicting the short-term (1-3 seconds) and long-term (3-5 seconds) spatial coordinates of various road-agents such as cars, buses, pedestrians, rickshaws, and animals, etc. These road-agents have different dynamic behaviors that may correspond to aggressive or conservative driving styles.
Source: Forecasting Trajectory and Behavior of Road-Agents Using Spectral Clustering in Graph-LSTMs
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Smooth-Trajectron++: Augmenting the Trajectron++ behaviour prediction model with smooth attention
MART: MultiscAle Relational Transformer Networks for Multi-agent Trajectory Prediction
Robots That Can See: Leveraging Human Pose for Trajectory Prediction
Peeking into the Future: Predicting Future Person Activities and Locations in Videos
Learning Semantic Latent Directions for Accurate and Controllable Human Motion Prediction
Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion
OOSTraj: Out-of-Sight Trajectory Prediction With Vision-Positioning Denoising
Homomorphism Autoencoder -- Learning Group Structured Representations from Observed Transitions
AMENet: Attentive Maps Encoder Network for Trajectory Prediction
MCENET: Multi-Context Encoder Network for Homogeneous Agent Trajectory Prediction in Mixed Traffic
Sparse Representations for Object and Ego-motion Estimation in Dynamic Scenes
Trajectory Prediction with Graph-based Dual-scale Context Fusion
PVRED: A Position-Velocity Recurrent Encoder-Decoder for Human Motion Prediction
Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving
Stochastic Human Motion Prediction with Memory of Action Transition and Action Characteristic
Temporal Continual Learning with Prior Compensation for Human Motion Prediction
Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformers
Physical Plausibility-aware Trajectory Prediction via Locomotion Embodiment
EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting
Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction
Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction
Non-Probability Sampling Network for Stochastic Human Trajectory Prediction
SingularTrajectory: Universal Trajectory Predictor Using Diffusion Model
GlucoBench: Curated List of Continuous Glucose Monitoring Datasets with Prediction Benchmarks
Novel Diffusion Models for Multimodal 3D Hand Trajectory Prediction
Progressive Pretext Task Learning for Human Trajectory Prediction
Learning Constrained Dynamic Correlations in Spatiotemporal Graphs for Motion Prediction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.