Spectral‑Spatial Interpretation (SSI) is a new full‑grid attribution method that assigns importance to each position‑channel pair in multispectral images. By fixing the surrounding context at each spatial location and applying Shapley values to the local channel game, SSI produces a spectral‑spatial attribution matrix rather than a single heatmap or global channel ranking. Experiments on HLS Burn Scar, CUB‑200, and EuroSAT show that SSI outperforms existing estimators in deletion/insertion metrics, achieves strong spectral hit rates, and improves spatial localization on annotated datasets.
arXiv:2607. 11548v1 Announce Type: cross Abstract: Spatial football metrics such as pitch control assume access to the positions of all 22 players, yet the most widely available source of positional data -- the broadcast main camera -- shows only 10-16 of them at any moment.
The paper introduces Graph-to-Grid (G2G), a method that paints continuous‑coordinate player features onto a grid using bilinear interpolation, enabling end‑to‑end training of per‑player encoders for pass surface prediction. On 53,628 World Cup passes, this painting approach improves selection likelihood by about a quarter of a nat compared to raster‑only inputs, with further gains from learned encoders and message passing. The study also shows that painting benefits existing models like SoccerMap and U‑Net, while other variants such as offset channels or raster‑free decoders do not provide similar improvements.
Location encoders transform geographic coordinates into high‑dimensional embeddings for machine learning, yet it is unclear how well these embeddings capture interpretable spatial effects. This study benchmarks GeoShapley—a game‑theoretic explainer treating all location features as a single joint player—against eleven TorchSpatial encoders on a synthetic process with known coefficients, across grid, county, and global scales, with and without raw coordinates and under different training regimes. The results show that primary coefficient recovery is consistently high across encoders, while secondary coefficient recovery varies more with scale, especially at the global level, and raw‑coordinate baselines remain competitive throughout.
OVO‑S‑Bench is a fully human‑annotated benchmark designed to evaluate streaming spatial intelligence in multimodal large language models (MLLMs). It contains 1,680 questions derived from 348 source videos, each with a query timestamp and evidence interval, and tests models on four levels of abstraction: instantaneous egocentric perception, spatiotemporal context tracking, generative spatial reasoning, and allocentric spatial mapping. Across 38 MLLMs, Gemini‑3.1‑Pro scored 59.2 versus 92.2 for human experts, with allocentric spatial mapping identified as the main challenge, and the benchmark reveals that chain‑of‑thought reasoning can worsen spatial errors when not grounded in the stream.
arXiv:2610.19520v1 Announce Type: new Abstract: Cameras and the foundation models built on them recognize what a 3D scene contains, but not what it is made of: surfaces of the same colour can be diff...
arXiv:2610.32894v1 Announce Type: new Abstract: Location encoders map geographic coordinates to high-dimensional descriptors through contrastive alignment with paired Earth Observation imagery. We pr...
LESSViT introduces a sensor‑flexible Vision Transformer for hyperspectral imagery that uses a low‑rank structured attention mechanism (LESS Attention) to efficiently model joint spatial‑spectral interactions. By reducing the complexity from ≠O(N^2C^2) to ≠O(rNC) and adding channel‑agnostic patch embedding with wavelength‑aware positional encoding, it supports flexible spectral inputs. A hyperspectral masked autoencoder (HyperMAE) with decoupled spatial‑spectral masking further enables robust pretraining, and experiments on the SpectralEarth benchmark show improved robustness to spectral shifts while maintaining competitive in‑distribution performance.
arXiv:2608. 14982v1 Announce Type: cross Abstract: Transformers applied to spatial imperfect-information games must represent map geometry while tracking hidden entities through time.
arXiv:2608.21832v1 Announce Type: new Abstract: Computer-use agents ground natural-language instructions in screenshots to locate interface elements, yet existing benchmarks do not isolate whether mo...
arXiv:2606.01914v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) remain unreliable on spatial multiple-choice questions, and their failures are often attributed to poorly...
DCA-MoE is a crowd‑counting framework that keeps a frozen DINOv3 encoder while introducing two content‑dependent modules: Spatially Adaptive Layer Fusion (SALF) assigns position‑wise weights to four backbone features, and Density‑Routed Multi‑Receptive‑Field Experts (DR‑MoE) mixes local, mid‑range, and large‑context residual experts for each location. An EBC‑style head reconstructs block density, and the model is trained with DMCount supervision plus a routing‑balance term. On the NWPU‑Crowd validation split, the best configuration based on DINOv3 ViT‑L/16 achieves 31.7 MAE and 72.2 RMSE, while the ViT‑B/16 full model records 32.2/75.9.
The paper introduces MIND, a method that distills specialist geospatial model embeddings into a single generalist coordinate embedding with adjustable spatial granularity, using nested supervision across multiple embedding dimensions. MIND’s design allows downstream predictors to use only leading chunks or apply a Chunked Penalty to downweight finer details without retraining the INR. The authors evaluate MIND on CoordBench, a large INR benchmark of 52 datasets and 78 targets, and report that MIND and its Chunked Penalty variant achieve the highest regression and classification scores, especially under regional holdout, establishing a new state‑of‑the‑art for geographic implicit neural representations.