https://github.com/xiaogangpeng/socialtgcn
공식 코드The MI-Motion Dataset and Benchmark for 3D Multi-Person Motion Prediction
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Predict human activities in videos
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
The MI-Motion Dataset and Benchmark for 3D Multi-Person Motion Prediction
GRIP++: Enhanced Graph-based Interaction-aware Trajectory Prediction for Autonomous Driving
Safety-aware Motion Prediction with Unseen Vehicles for Autonomous Driving
Unsupervised Kinematic Motion Detection for Part-segmented 3D Shape Collections
Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks
DisenHCN: Disentangled Hypergraph Convolutional Networks for Spatiotemporal Activity Prediction
SmartPretrain: Model-Agnostic and Dataset-Agnostic Representation Learning for Motion Prediction
OFMPNet: Deep End-to-End Model for Occupancy and Flow Prediction in Urban Environment
Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning
BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving
Motion-aware Memory Network for Fast Video Salient Object Detection
Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encoding
TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction
Pose Constraints for Consistent Self-supervised Monocular Depth and Ego-motion
BEVWorld: A Multimodal World Model for Autonomous Driving via Unified BEV Latent Space
Improving SIEM for Critical SCADA Water Infrastructures Using Machine Learning
Scene Transformer: A unified architecture for predicting multiple agent trajectories
Deep Ensemble Learning with Frame Skipping for Face Anti-Spoofing
Joint Learning Architecture for Multiple Object Tracking and Trajectory Forecasting
Learning Trajectory Dependencies for Human Motion Prediction
Peeking into the Future: Predicting Future Person Activities and Locations in Videos
Deep Ensemble Learning with Frame Skipping for Face Anti-Spoofing
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.