Learning Long Range Spatio-Temporal Representations
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space Models
arXiv:2606.04672v1 Announce Type: new Abstract: Continuous-time dynamic graphs (CTDGs) provide a richer framework to capture fine-grained temporal patterns in evolving relational data. Long-range information propagation is a key challenge while learning representations, wherein it is important to retain and update information over long temporal horizons. Existing approaches restrict models to capture one-hop or local temporal neighborhoods and fail to capture multi-hop or global structural...
Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space Models
arXiv:2606.04672v2 Announce Type: replace Abstract: Continuous-time dynamic graphs (CTDGs) provide a richer framework to capture fine-grained temporal patterns in evolving relational data. Long-range information propagation is a key challenge while learning representations, wherein it is important to retain and update information over long temporal horizons. Existing approaches restrict models to capture one-hop or local temporal neighborhoods and fail to capture multi-hop or global...
4DPC$^2$hat: Towards Dynamic Point Cloud Understanding with Failure-Aware Bootstrapping
arXiv:2602.03890v3 Announce Type: replace Abstract: Point clouds provide a compact and expressive representation of 3D objects, and have recently been integrated into multimodal large language models (MLLMs). However, existing methods primarily focus on static objects, while understanding dynamic point cloud sequences remains largely unexplored. This limitation is mainly caused by the lack of large-scale cross-modal datasets and the difficulty of modeling motions in spatio-temporal contexts.