Paper Citation Record · LEDGER

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives

As of 14 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2506.03709.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2506.03709 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:00:54.910555Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

38 of 38 outbound references displayed

verified exact1
verified fuzzy22
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 61bcb3ed-c11e-41de-9292-9953c27c056d · outbound

This paper cites Syn2real domain generalization for underwater mine-like object de- tection using side-scan sonar.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Syn2real domain generalization for underwater mine-like object de- tection using side-scan sonar

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:00:55.544548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 76eaad89-6c37-4ea9-b870-15590b3a0629 · outbound

This paper cites What a mess: Multi-domain evaluation of zero-shot semantic segmentation.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives What a mess: Multi-domain evaluation of zero-shot semantic segmentation

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:00:55.527529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f1354a32-ad22-4205-8099-8c7d5cd78189 · outbound

This paper cites Coco- stuff: Thing and stuff classes in context.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Coco- stuff: Thing and stuff classes in context

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:00:55.505663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c040cc88-6947-4f53-9256-b894433ba3e1 · outbound

This paper cites Cat- seg: Cost aggregation for open-vocabulary semantic seg- mentation.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Cat- seg: Cost aggregation for open-vocabulary semantic seg- mentation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T11:00:54.755631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8225a432-8fb9-4c19-862f-d9d99a7f709f · outbound

This paper cites De- coupling zero-shot semantic segmentation.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives De- coupling zero-shot semantic segmentation

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:00:55.475641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e34b6372-d23f-449d-9ade-7634d1f958e0 · outbound

This paper cites Open- vocabulary panoptic segmentation maskclip.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Open- vocabulary panoptic segmentation maskclip

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T11:00:54.765166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2defca1-eca3-4294-8507-7965987b4cf6 · outbound

This paper cites The pascal visual object classes challenge: A retrospective.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives The pascal visual object classes challenge: A retrospective

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:00:55.447014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9b8589ed-ec1e-42b0-978d-9ee7e4c0c37f · outbound

This paper cites Scal- ing open-vocabulary image segmentation with image-level labels.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Scal- ing open-vocabulary image segmentation with image-level labels

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:00:55.430009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e6b3209c-6663-4ac3-a950-a2d85c81a5be · outbound

This paper cites Multispectral video se- mantic segmentation: A benchmark dataset and baseline.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Multispectral video se- mantic segmentation: A benchmark dataset and baseline

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:00:55.413145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 06b53928-1b0a-4d3b-bc2f-cd6a3eee769d · outbound

This paper cites Scaling up visual and vision-language representa- tion learning with noisy text supervision.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Scaling up visual and vision-language representa- tion learning with noisy text supervision

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T11:00:54.783608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7709b8c-c5ef-4dcd-a154-628bb19fb673 · outbound

This paper cites An efficient approach with dynamic multiswarm of uavs for forest firefighting.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives An efficient approach with dynamic multiswarm of uavs for forest firefighting

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:00:55.378331Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b71fb33b-2ef7-4282-a8eb-dc0dad063e5d · outbound

This paper cites A resource-efficient decentralized sequential planner for spa- tiotemporal wildfire mitigation.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives A resource-efficient decentralized sequential planner for spa- tiotemporal wildfire mitigation

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:00:55.362057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3b7a43fd-23ec-47e4-bee7-cee29268ed97 · outbound

This paper cites Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T11:00:54.797427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d925f3fa-41e5-42e1-b517-93bc93e31d41 · outbound

This paper cites Caltech aerial rgb-thermal dataset in the wild.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Caltech aerial rgb-thermal dataset in the wild

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:00:55.342852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 26dfce84-5c02-4655-82dd-55a0c1e62a1e · outbound

This paper cites Open-vocabulary semantic segmentation with mask-adapted clip.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Open-vocabulary semantic segmentation with mask-adapted clip

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:00:55.326883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 734ea006-f8da-425d-8a43-001721b94a15 · outbound

This paper cites Holistic Evaluation of Language Models.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Holistic Evaluation of Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T11:00:54.811123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6df921a1-10ad-4f78-a4fc-df9e1ce36f49 · outbound

This paper cites Uavid: A semantic segmentation dataset for uav imagery.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Uavid: A semantic segmentation dataset for uav imagery

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:00:55.310869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1986572b-a1de-4181-ad50-be376089ffeb · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Learning transferable visual models from natural language supervi- sion

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T11:00:54.820409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 067a8bb2-80b0-42a1-9339-c6959c4d70c3 · outbound

This paper cites LCA-on-the-Line: Benchmarking Out-of-Distribution Generalization with Class Taxonomies.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives LCA-on-the-Line: Benchmarking Out-of-Distribution Generalization with Class Taxonomies

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T11:00:54.824912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62af2453-9620-4cfe-a25e-31f460f59953 · outbound

This paper cites Fully complex-valued fully con- volutional multi-feature fusion network (fc 2 mfn) for build- ing segmentation of insar images.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Fully complex-valued fully con- volutional multi-feature fusion network (fc 2 mfn) for build- ing segmentation of insar images

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T11:00:54.829772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ccb78e6-1308-460d-8d51-125ba0a0f238 · outbound

This paper cites Deepmao: Deep multi-scale aware over- complete network for building segmentation in satellite im- agery.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Deepmao: Deep multi-scale aware over- complete network for building segmentation in satellite im- agery

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:00:55.267194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6e874028-ec58-4e5d-add3-6f0fcd8580c3 · outbound

This paper cites Ssl-rgb2ir: Semi-supervised rgb-to-ir image-to-image translation for enhancing visual task train- ing in semantic segmentation and object detection.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Ssl-rgb2ir: Semi-supervised rgb-to-ir image-to-image translation for enhancing visual task train- ing in semantic segmentation and object detection

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:00:55.248554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 769d20ca-7863-4742-95e1-78745631a294 · outbound

This paper cites Skd- net: Spectral-based knowledge distillation in low-light ther- mal imagery for robotic perception.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Skd- net: Spectral-based knowledge distillation in low-light ther- mal imagery for robotic perception

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:00:55.232254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8cc2452f-7b70-46a4-b991-7dde6f189603 · outbound

This paper cites SAGA: Semantic-Aware Gray color Augmentation for Visible-to-Thermal Domain Adaptation across Multi-View Drone and Ground-Based Vision Systems.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives SAGA: Semantic-Aware Gray color Augmentation for Visible-to-Thermal Domain Adaptation across Multi-View Drone and Ground-Based Vision Systems

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-08-07T11:00:54.976223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8ce25091-7025-4975-9e0b-153017e6e999 · outbound

This paper cites Ogp- net: Optical guidance meets pixel-level contrastive distilla- tion for robust multi-modal and missing modality segmen- tation.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Ogp- net: Optical guidance meets pixel-level contrastive distilla- tion for robust multi-modal and missing modality segmen- tation

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:00:55.215098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ee30a712-b673-4314-8d98-5b34950791ca · outbound

This paper cites Isprs potsdam dataset within the isprs test project on urban classification, 3d building reconstruction and semantic labeling, 2012.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Isprs potsdam dataset within the isprs test project on urban classification, 3d building reconstruction and semantic labeling, 2012

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:00:55.197910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cb27bcad-15a0-4ec2-960f-e1b7af728c17 · outbound

This paper cites Piafusion: A progressive infrared and visible im- age fusion network based on illumination aware.Information Fusion, 83:79–92, 2022.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Piafusion: A progressive infrared and visible im- age fusion network based on illumination aware.Information Fusion, 83:79–92, 2022

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:00:55.180836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 421215af-8ad4-40dc-b6ac-f8264a09775b · outbound

This paper cites Mrfp: Learning generalizable semantic segmentation from sim-2-real with multi-resolution feature perturbation.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Mrfp: Learning generalizable semantic segmentation from sim-2-real with multi-resolution feature perturbation

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T11:00:54.867104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2fb9c41-8b64-4f50-8232-ff423100053e · outbound

This paper cites Robust fine-tuning of zero-shot models.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Robust fine-tuning of zero-shot models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T11:00:54.871492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 733ca119-7afd-4c32-ab4b-5ca1414260bd · outbound

This paper cites Open-vocabulary panop- tic segmentation with text-to-image diffusion models.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Open-vocabulary panop- tic segmentation with text-to-image diffusion models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T11:00:54.875749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3158162-599b-40c0-bdc4-3f476c4dc7bd · outbound

This paper cites A simple baseline for open- vocabulary semantic segmentation with pre-trained vision- language model.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives A simple baseline for open- vocabulary semantic segmentation with pre-trained vision- language model

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:00:55.131905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2e0849b6-a601-4887-a56d-6f4e2d2eff9e · outbound

This paper cites Side adapter network for open-vocabulary semantic segmentation.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Side adapter network for open-vocabulary semantic segmentation

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:00:55.116220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a81cd960-f265-4d4f-b8ae-2be8a902effd · outbound

This paper cites Convolutions die hard: Open-vocabulary seg- mentation with single frozen convolutional clip.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Convolutions die hard: Open-vocabulary seg- mentation with single frozen convolutional clip

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T11:00:54.888526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ccf68ea-ae7e-4348-8e1b-26ffb316dae1 · outbound

This paper cites Florence: A New Foundation Model for Computer Vision.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Florence: A New Foundation Model for Computer Vision

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T11:00:54.892839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4e0a183-1163-4ecf-8f73-f270a7e94a20 · outbound

This paper cites Dept: Decoupled prompt tuning.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Dept: Decoupled prompt tuning

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:00:55.085451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d905bb80-3118-487a-bd14-c44d85bafd18 · outbound

This paper cites Semantic under- standing of scenes through the ade20k dataset.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Semantic under- standing of scenes through the ade20k dataset

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:00:55.069426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0738a1bc-72a2-489a-8a01-338c1c816f09 · outbound

This paper cites Extract free dense labels from clip.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Extract free dense labels from clip

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T11:00:54.906244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c03845bb-6da7-42aa-9abe-26da37c6d0dc · outbound

This paper cites Generalized decoding for pixel, image, and lan- guage.

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives Generalized decoding for pixel, image, and lan- guage

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T11:00:54.910555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.