Related papers: FieldFormer: Locality-Aware Transformers for Spati…
Predicting accurate future trajectories of multiple agents is essential for autonomous systems, but is challenging due to the complex agent interaction and the uncertainty in each agent's future behavior. Forecasting multi-agent…
Autonomous surveillance missions in Internet of Things (IoT) networks often involve solving NP-hard combinatorial optimization problems to ensure efficient resource utilization. To address the limitations of conventional heuristics in…
Due to various and complicated snow degradations, single image desnowing is a challenging image restoration task. As prior arts can not handle it ideally, we propose a novel transformer, SnowFormer, which explores efficient cross-attentions…
Transformer-based visual object tracking has been utilized extensively. However, the Transformer structure is lack of enough inductive bias. In addition, only focusing on encoding the global feature does harm to modeling local details,…
Spatial grounding, the process of associating natural language expressions with corresponding image regions, has rapidly advanced due to the introduction of transformer-based models, significantly enhancing multimodal representation and…
We introduce VistaFormer, a lightweight Transformer-based model architecture for the semantic segmentation of remote-sensing images. This model uses a multi-scale Transformer-based encoder with a lightweight decoder that aggregates global…
Transforming road network data into vector representations using deep learning has proven effective for road network analysis. However, urban road networks' heterogeneous and hierarchical nature poses challenges for accurate representation…
Reconstructing PDE-governed fields from sparse and irregular measurements is challenging due to their ill-posed nature. Deterministic surrogates are trained on dense fields that struggle with limited measurements and uncertainty…
In remote sensing there exists a common need for learning scale invariant shapes of objects like buildings. Prior works relies on tweaking multiple loss functions to convert segmentation maps into the final scale invariant representation,…
Convolution neural networks (CNNs) have succeeded in compressive image sensing. However, due to the inductive bias of locality and weight sharing, the convolution operations demonstrate the intrinsic limitations in modeling the long-range…
Convolutional neural networks and attention mechanisms have greatly benefited remote sensing change detection (RSCD) because of their outstanding discriminative ability. Existent RSCD methods often follow a paradigm of using a…
Reliably reconstructing physical fields from sparse sensor data is a challenge that frequently arises in many scientific domains. In practice, the process generating the data often is not understood to sufficient accuracy. Therefore, there…
As a core technology of Intelligent Transportation System, traffic flow prediction has a wide range of applications. The fundamental challenge in traffic flow prediction is to effectively model the complex spatial-temporal dependencies in…
Patch-wise Transformer based time series forecasting achieves superior accuracy. However, this superiority relies heavily on intricate model design with massive parameters, rendering both training and inference expensive, thus preventing…
Accurate spatio-temporal prediction is crucial for the sustainable development of smart cities. However, current approaches often struggle to capture important spatio-temporal relationships, particularly overlooking global relations among…
Sophisticated learning architectures, e.g., Transformers, present a unique opportunity for robots to understand complex vehicle-terrain kinodynamic interactions for off-road mobility. While internet-scale data are available for Natural…
Theoretical efforts to prove advantages of Transformers in comparison with classical architectures such as feedforward and recurrent neural networks have mostly focused on representational power. In this work, we take an alternative…
Most pipelines for Augmented and Virtual Reality estimate the ego-motion of the camera by creating a map of sparse 3D landmarks. In this paper, we tackle the problem of depth completion, that is, densifying this sparse 3D map using RGB…
Reconstruction of fine-scale information from sparse data is relevant to many practical fluid dynamic applications where the sensing is typically sparse. Fluid flows in an ideal sense are manifestations of nonlinear multiscale PDE dynamical…
LiDAR-based world models offer more structured and geometry-aware representations than their image-based counterparts. However, existing LiDAR world models are narrowly trained; each model excels only in the domain for which it was built.…