No article text was recorded for this version.
decoupled spatio-temporal attention
Version 1 of 1538 papers691 conceptsfrozen 2026-10-04
Papers in this version
- Blog: PredFormer: Transformers Are Effective Spatial-Temporal Predictive Learners
- Blog: SSAN: Separable Self-Attention Network for Video Representation Learning
- Blog: ViViT: A Video Vision Transformer
- Blog: Is Space-Time Attention All You Need for Video Understanding?
- Blog: Spatial-Temporal Transformer for Video Snapshot Compressive Imaging
- Blog: A Spatio-temporal Transformer for 3D Human Motion Prediction
- Blog: Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking
- Blog: Motion-state Alignment for Video Semantic Segmentation
- Blog: Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning
- Blog: Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection
- Blog: Spherical Vision Transformers for Audio-Visual Saliency Prediction in 360-Degree Videos
- Blog: Panacea: Panoramic and Controllable Video Generation for Autonomous Driving
- Blog: TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding
- Blog: ViViT: A Video Vision Transformer
- Blog: GLGait: A Global-Local Temporal Receptive Field Network for Gait Recognition in the Wild
- Blog: Scene Transformer: A unified architecture for predicting future trajectories of multiple agents
- Blog: Parallel Spatio-Temporal Attention Transformer for Video Frame Interpolation
- Blog: TranSPORTmer: A Holistic Approach to Trajectory Understanding in Multi-Agent Sports
- Blog: Implicit Motion-Compensated Network for Unsupervised Video Object Segmentation
- Blog: CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation
- Blog: Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better
- Blog: DriveVGGT: Visual Geometry Transformer for Autonomous Driving
- Blog: Video Prediction Transformers without Recurrence or Convolution
- Blog: Flow-Guided Transformer for Video Inpainting
- Blog: Multi-Stage Spatio-Temporal Aggregation Transformer for Video Person Re-Identification
- Blog: DREAM: Adaptive Reinforcement Learning based on Attention Mechanism for Temporal Knowledge Graph Reasoning
- Blog: VidTr: Video Transformer Without Convolutions
- Blog: GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions
- Blog: PilotWiMAE: Wireless Channel Pilots Are All You Need
- Blog: VidTr: Video Transformer Without Convolutions
- Blog: UNSPAT: Uncertainty-Guided SpatioTemporal Transformer for 3D Human Pose and Shape Estimation on Videos
- Blog: Flow-Guided Transformer for Video Inpainting
- Blog: Tenma: Robust Cross-Embodiment Robot Manipulation with Diffusion Transformer
- Blog: Guiding Audio-Visual Question Answering with Collective Question Reasoning
- Blog: 3D Mitochondria Instance Segmentation with Spatio-Temporal Transformers
- Blog: RmGPT: A Foundation Model with Generative Pre-trained Transformer for Fault Diagnosis and Prognosis in Rotating Machinery
- Blog: Video Frame Interpolation Transformer
- Blog: EventTransAct: A video transformer-based framework for Event-camera based action recognition
- Blog: Planner-Refiner: Dynamic Space-Time Refinement for Vision-Language Alignment in Videos
- Blog: Emergent Temporal Correspondences from Video Diffusion Transformers
- Blog: A Unified Model for Tracking and Image-Video Detection Has More Power
- Blog: Fine-grained Text-Video Retrieval with Frozen Image Encoders
- Blog: Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking
- Blog: DynamicStereo: Consistent Dynamic Depth from Stereo Videos
- Blog: Motion2VecSets: 4D Latent Vector Set Diffusion for Non-Rigid Shape Reconstruction and Tracking
- Blog: Latent Video Diffusion Models for High-Fidelity Video Generation with Arbitrary Lengths
- Blog: Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective
- Blog: MaXTron: Mask Transformer with Trajectory Attention for Video Panoptic Segmentation
- Blog: Optimizing ViViT Training: Time and Memory Reduction for Action Recognition
- Blog: Hierarchical Separable Video Transformer for Snapshot Compressive Imaging
- Blog: Latte: Latent Diffusion Transformer for Video Generation
- Blog: SyncVP: Joint Diffusion for Synchronous Multi-Modal Video Prediction
- Blog: Vidtr: Video transformer without convolutions
- Blog: ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video
- Blog: AutoRemover: Automatic Object Removal for Autonomous Driving Videos
- Blog: MAPLE: Masked Pseudo-Labeling autoEncoder for Semi-supervised Point Cloud Action Recognition
- Blog: DCRA-Net: Attention-Enabled Reconstruction Model for Dynamic Fetal Cardiac MRI
- Blog: Video Prediction Transformers without Recurrence or Convolution
- Blog: Gated Spatio-Temporal Attention-Guided Video Deblurring
- Blog: Toyota Smarthome: Real-World Activities of Daily Living
Showing 60 of 538 papers.
History & citation
Current · Permanent link
- Factorized Spatio-temporal Attention for Efficient Sequence Modeling merged into this direction (93% overlap)
- Factorized Space Time Attention for Video Transformers merged into this direction (59% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_decoupled_spatio_temporal_attention_5cdd471a,
title = {decoupled spatio-temporal attention},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/decoupled-spatio-temporal-attention/rdr_5cdd471ad20f4313ab99337b582c88e0},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_decoupled_spatio_temporal_attention_5cdd471a_v1,
title = {decoupled spatio-temporal attention},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/decoupled-spatio-temporal-attention/rdr_5cdd471ad20f4313ab99337b582c88e0/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}