WATCH: Wide-Area Archaeological Site Tracking for Change Detection

• URL: http://arxiv.org/abs/2605.08160v1
• Date: Mon, 04 May 2026 12:35:59 GMT
• Title: WATCH: Wide-Area Archaeological Site Tracking for Change Detection
• Abstract summary: Monitoring archaeological sites at scale is vital for protecting cultural heritage, yet pinpointing when disturbances occur remains difficult.<n>We introduce WATCH, a framework for month-level change-event localization over PlanetScope satellite mosaics.<n>We benchmark WATCH on 1,943 archaeological sites in Afghanistan using embeddings from six foundation models.
• Score: 6.328778011578591
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Monitoring archaeological sites at scale is vital for protecting cultural heritage, yet pinpointing when disturbances occur remains difficult because visual cues are subtle and ground-truth data are sparse. We introduce WATCH, a framework for month-level change-event localization over PlanetScope satellite mosaics (2017-2024, 4.7 m/px) that supports three complementary scoring approaches: (i) Temporal Embedding Distance (TED), a training-free method that scores month-to-month deviations from a local temporal reference; (ii) Self-Supervised Change Detection (SSCD), an ensemble of reconstruction, forecasting, and latent-novelty signals; and (iii) a Weakly Supervised (WS) temporal localization model trained with sparse event-month labels. We benchmark WATCH on 1,943 archaeological sites in Afghanistan using embeddings from six foundation models (CLIP, GeoRSCLIP, SatMAE, Prithvi-EO-2.0, DINOv3, and Satlas-Pretrain) alongside a handcrafted spectral and texture baseline, and assess cross-regional generalization on sites in Syria, Turkey, Pakistan, and Egypt. The unsupervised approaches (TED, SSCD) consistently outperform the weakly supervised alternative. TED with SatMAE achieves the highest exact-month recall (55% at m=0), while TED with GeoRSCLIP, CLIP, or Satlas-Pretrain reaches 92.5% within a three-month tolerance (m=3). Handcrafted features remain competitive for exact-month detection under weak supervision. Our directional margin analysis reveals systematic temporal biases: SSCD paired with GeoRSCLIP or Prithvi-EO-2.0 exhibits the strongest early-warning profile, detecting anomalies before the recorded event, while TED favors confirmation-oriented detection after a change has materialized. These results show that satellite imagery combined with foundation-model embeddings enables scalable, decision-relevant heritage monitoring. Code: https://github.com/microsoft/WATCH

Related papers

• Air Quality Downscaling with Station-Guided Pseudo-Supervision [60.31045749983062]
  Super-resolving coarse atmospheric fields to local PM$_2.5$ variations is uniquely challenged by a mismatch in spatial support.<n>We present a station-guided framework for high-resolution PM$_2.5$ downscaling over Europe.
  arXiv  Detail & Related papers  (2026-07-06T16:32:25Z)
• Reconstructing Multi-Decadal Forest Disturbances: A Spatio-Temporal Transformer Approach [5.518551921886323]
  We present a framework that maps 38 years (1984-2022) of forest disturbance across the contiguous United States.<n>By leveraging a vision transformer architecture, our approach effectively filters noise from weak supervision signals.<n>Our method offers a promising foundation for consistent forest monitoring.
  arXiv  Detail & Related papers  (2026-06-05T13:20:49Z)
• CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating [49.94171749437024]
  We propose Concentrate and Concentrate (CaC), a coarse-to-fine anomaly reward model based on Vision-Language Models.<n>We construct the first largescale generated video anomaly dataset with per-frame bounding-box annotations, temporal anomaly windows, and fine-grained attribution labels.<n>In experiments, CaC can stably concentrate on subtle anomalies, achieving a 25.7% accuracy improvement on fine-grained anomaly benchmarks.
  arXiv  Detail & Related papers  (2026-05-12T08:08:33Z)
• Reducing the labeling burden in time-series mapping using Common Ground: a semi-automated approach to tracking changes in land cover and species over time [0.0]
  We show that a model with access to reference data solely from time step t0 can perform competitively on both t0 and a future time step t1.<n>This finding suggests that effective temporal generalization can be achieved without requiring manual updates to reference labels beyond the initial time step t0.
  arXiv  Detail & Related papers  (2026-02-04T09:49:36Z)
• Anomaly detection in satellite imagery through temporal inpainting [28.023703674946223]
  We show that deep learning can leverage the temporal redundancy of satellite time series to detect anomalies at unprecedented sensitivity.<n>We train an inpainting model built upon the SATLAS foundation model to reconstruct the last frame of a Sentinel-2 time series.<n>When applied to regions affected by sudden surface changes, the discrepancy between prediction and observation reveals anomalies that traditional change detection methods miss.
  arXiv  Detail & Related papers  (2025-12-30T04:58:13Z)
• Needles in the Landscape: Semi-Supervised Pseudolabeling for Archaeological Site Discovery under Label Scarcity [0.3957768262206626]
  Archaeological predictive modelling estimates where undiscovered sites are likely to occur by combining known locations with environmental, cultural, and geospatial variables.<n>We address this challenge using a deep learning approach but must contend with structural label scarcity inherent to archaeology: positives are rare, and most locations are unlabeled.<n>Our results indicate that semi-supervised learning offers a promising approach to identifying undiscovered sites across large, sparsely annotated landscapes.
  arXiv  Detail & Related papers  (2025-10-19T12:54:38Z)
• A Deep Learning Architecture for Land Cover Mapping Using Spatio-Temporal Sentinel-1 Features [1.907072234794597]
  The study focuses on three distinct regions - Amazonia, Africa, and Siberia - and evaluates the model performance across diverse ecoregions within these areas.<n>The results demonstrate the effectiveness and the capabilities of the proposed methodology in achieving overall accuracy (O.A.) values, even in regions with limited training data.
  arXiv  Detail & Related papers  (2025-03-10T12:15:35Z)
• Temporal Action Localization with Enhanced Instant Discriminability [66.76095239972094]
  Temporal action detection (TAD) aims to detect all action boundaries and their corresponding categories in an untrimmed video. We propose a one-stage framework named TriDet to resolve imprecise predictions of action boundaries by existing methods. Experimental results demonstrate the robustness of TriDet and its state-of-the-art performance on multiple TAD datasets.
  arXiv  Detail & Related papers  (2023-09-11T16:17:50Z)
• Implicit neural representation for change detection [15.741202788959075]
  Most commonly used approaches to detecting changes in point clouds are based on supervised methods. We propose an unsupervised approach that comprises two components: Implicit Neural Representation (INR) for continuous shape reconstruction and a Gaussian Mixture Model for categorising changes. We apply our method to a benchmark dataset comprising simulated LiDAR point clouds for urban sprawling.
  arXiv  Detail & Related papers  (2023-07-28T09:26:00Z)
• Contracting Skeletal Kinematics for Human-Related Video Anomaly Detection [43.72042594414675]
  COSKAD is a novel model that encodes skeletal human motion by a graph convolutional network. It learns to COntract SKeletal embeddings onto a latent hypersphere of minimum volume for Video Anomaly Detection. All variants outperform the state-of-the-art on the most recent UBnormal dataset.
  arXiv  Detail & Related papers  (2023-01-23T15:32:27Z)
• SRRT: Exploring Search Region Regulation for Visual Object Tracking [58.68120400180216]
  We propose a novel tracking paradigm, called Search Region Regulation Tracking (SRRT) SRRT applies a proposed search region regulator to estimate an optimal search region dynamically for each frame. On the large-scale LaSOT benchmark, SRRT improves SiamRPN++ and TransT with absolute gains of 4.6% and 3.1% in terms of AUC.
  arXiv  Detail & Related papers  (2022-07-10T11:18:26Z)
• Video-based Person Re-identification without Bells and Whistles [49.51670583977911]
  Video-based person re-identification (Re-ID) aims at matching the video tracklets with cropped video frames for identifying the pedestrians under different cameras. There exists severe spatial and temporal misalignment for those cropped tracklets due to the imperfect detection and tracking results generated with obsolete methods. We present a simple re-Detect and Link (DL) module which can effectively reduce those unexpected noise through applying the deep learning-based detection and tracking on the cropped tracklets.
  arXiv  Detail & Related papers  (2021-05-22T10:17:38Z)
• Dense Label Encoding for Boundary Discontinuity Free Rotation Detection [69.75559390700887]
  This paper explores a relatively less-studied methodology based on classification. We propose new techniques to push its frontier in two aspects. Experiments and visual analysis on large-scale public datasets for aerial images show the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-11-19T05:42:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.