MS-LSTM: Exploring Spatiotemporal Multiscale Representations in Video Prediction Domain
원문 초록
The drastic variation of motion in spatial and temporal dimensions makes the video prediction task extremely challenging. Existing RNN models obtain higher performance by deepening or widening the model. They obtain the multi-scale features of the video only by stacking layers, which is inefficient and brings unbearable training costs (such as memory, FLOPs, and training time). Different from them, this paper proposes a spatiotemporal multi-scale model called MS-LSTM wholly from a multi-scale perspective. On the basis of stacked layers, MS-LSTM incorporates two additional efficient multi-scale designs to fully capture spatiotemporal context information. Concretely, we employ LSTMs with mirrored pyramid structures to construct spatial multi-scale representations and LSTMs with different convolution kernels to construct temporal multi-scale representations. We theoretically analyze the training cost and performance of MS-LSTM and its components. Detailed comparison experiments with twelve baseline models on four video datasets show that MS-LSTM has better performance but lower training costs.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Epona: Autoregressive Diffusion World Model for Autonomous Driving
Autoregression-free video prediction using diffusion model for mitigating error propagation
Programmatic Video Prediction Using Large Language Models
SRVP: Strong Recollection Video Prediction Model Using Attention-Based Spatiotemporal Correlation Fusion
SyncVP: Joint Diffusion for Synchronous Multi-Modal Video Prediction
Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Models
토론
이 논문과 연결된 포럼 글이 아직 없습니다.