https://github.com/sta8is/futurist
공식 코드Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers
Borrowing from yourself: Faster future video segmentation with partial channel update
HelmFluid: Learning Helmholtz Dynamics for Interpretable Fluid Prediction
DeepLag: Discovering Deep Lagrangian Dynamics for Intuitive Fluid Prediction
TrajAgent: An Agent Framework for Unified Trajectory Modelling
Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning
FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras
MTD: Multi-Timestep Detector for Delayed Streaming Perception
AutoSAM: Towards Automatic Sampling of User Behaviors for Sequential Recommender Systems
BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving
DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents
PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos
Peeking into the Future: Predicting Future Person Activities and Locations in Videos
DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents
TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting
Probabilistic Video Generation using Holistic Attribute Control
Temporal Aggregate Representations for Long-Range Video Understanding
ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning
Decomposing Motion and Content for Natural Video Sequence Prediction
MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Prediction
MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Prediction
DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents
Personalized Gaussian Processes for Future Prediction of Alzheimer's Disease Progression
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.