mlsanityData to 14 Oct 2026

FPV-CRASH: A Dataset for Offline Crash Moment Localization in Drone First-Person-View Videos

arXiv 2610.19785 ↗First posted 14 Oct 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Crash Moment Localization aims to localize the major physical impact that interrupts controlled flight in an onboard first-person-view (FPV) video recorded by a drone, thereby providing a temporal reference for retrospective crash analysis in aerial robotics. However, existing crash-video datasets predominantly target surveillance or dash-camera footage, and their annotation schemes and task formulations are not designed for temporal localization of the major physical impact in UAV onboard FPV videos. To address this gap, we present FPV-CRASH, a dataset and fixed-protocol reference evaluation for offline Crash Moment Localization in drone FPV videos. FPV-CRASH contains 1,052 drone FPV clips (526 Crash and 526 Normal); each Crash clip has a single-frame reference annotation for the Crash Moment, and every clip is paired with four English captions automatically generated from sampled frames and the known Crash/Normal label. Normal clips carry no timestamp target and provide training-time background supervision. The captions support an auxiliary Text-to-Video Retrieval task, whereas localization inference remains video-only. We further provide a heatmap-based reference model that estimates a continuous Crash Moment timestamp from sparsely sampled frames. Under the fixed, non-source-disjoint clip-level protocol, the reference model reduces MAE from 1.12 s for the strongest fixed timing-prior baseline to 0.56 s (a 50% relative reduction) and achieves a median absolute error (MedAE) of 0.33 s; the fraction of clips localized within 0.5 s rises from 37.14% to 65.71%. The release includes annotations, available source video identifiers and URLs, clipping metadata, fixed split lists, and preprocessing code so that the reportable portion can be reconstructed without redistributing source footage. At submission time, all source-compilation URLs remained accessible.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 44 references that are in the map. First posted on arXiv 14 Oct 2026.

Builds on

29 of 44 references.

References · 29

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
  5. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,188
  6. 2021Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrievalcited by 1,177
  7. 2017Dense-Captioning Events in Videoscited by 793
  8. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 691
  9. 2021CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrievalcited by 651
  10. 2019BMN: Boundary-Matching Network for Temporal Action Proposal Generationcited by 329
  11. 2025Perception Encoder: The best visual embeddings are not at the output of the networkcited by 326
  12. 2022ActionFormer: Localizing Moments of Actions with Transformerscited by 311
17 more
  1. 2019Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Languagecited by 285
  2. 2017Integral Human Pose Regressioncited by 256
  3. 2018SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videoscited by 150
  4. 2020Each Part Matters: Local Patterns Facilitate Cross-view Geo-localizationcited by 97
  5. 2024Gramian Multimodal Representation Learning and Alignmentcited by 54
  6. 2023Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatial Relation Matchingcited by 42
  7. 2017Learning to Fly by Crashingcited by 41
  8. 2024Vision Transformers for End-to-End Vision-Based Quadrotor Obstacle Avoidancecited by 14
  9. 2023Time-Optimal Gate-Traversing Planner for Autonomous Drone Racingcited by 7
  10. 2026ACCIDENT: A Benchmark Dataset for Vehicle Accident Detection from Traffic Surveillance Videoscited by 7
  11. 2024CloudTrack: Scalable UAV Tracking with Cloud Semanticscited by 4
  12. 2019Automatic Real-time Anomaly Detection for Autonomous Aerial Vehiclescited by 3
  13. 2023Race Against the Machine: a Fully-annotated, Open-design Dataset of Autonomous and Piloted High-speed Flightcited by 2
  14. 2022INSANE: Cross-Domain UAV Data Sets with Increased Number of Sensors for developing Advanced and Novel Estimatorscited by 1
  15. 2023Air Bumper: A Collision Detection and Reaction Framework for Autonomous MAV Navigationcited by 1
  16. 2023RflyMAD: A Dataset for Multicopter Fault Detection and Health Assessmentcited by 1
  17. 2025CGTrack: Cascade Gating Network with Hierarchical Feature Aggregation for UAV Trackingcited by 1

Built on by

Not cited yet.