Pith.

Computer Vision and Pattern Recognition · arXiv:2611.16413 v1 · submitted 12 Nov 2026 · 52 references

RICapBench: A Fine-Grained Visual Understanding Benchmark Dataset for Vision-Language Models in Remote Sensing

Xue Wang, Yubin Xu, Kun Tan

The paper says

“Advances in vision-language models (VLMs) have improved remote sensing image analysis and supported geospatial decision-making. However, fine-grained understanding of remote sensing imagery remains challenging for VLMs.”

more of the abstract

Large variations in object scale, complex geospatial relations among instances, and limited visual detail hinder precise instance localization, visible attribute identification, and spatial relation understanding, potentially leading to descriptions that lack visual grounding. Existing datasets and benchmarks insufficiently assess end-to-end instance localization and captioning without target-specific textual cues. To support this evaluation, we introduce RICapBench, a dataset and benchmark that unifies instance localization and fine-grained captioning in remote sensing. RICapBench contains 245,466 instance-level annotations and 498,005 spatial relation tuples spanning general remote sensing, UAV remote sensing, and dense small-object scenarios. Each annotation pairs an object's oriented bounding box with a natural language description of its visible attributes and spatial relations to surrounding instances and environmental elements. To evaluate the accuracy and completeness of spatial relation captioning, we propose a remote sensing spatial relation parser and the RelCap-F1 metric. We combine RelCap-F1 with instance localization and attribute captioning metrics into a composite metric, RICScore. Our evaluation of 15 advanced open-source and closed-source VLMs identifies instance localization as a major bottleneck for these models. LocateAnything achieves the highest RICScore of 31.68, but scores lower on spatial relation captioning than other task-fine-tuned open-source VLMs. Code and dataset are available at https://github.com/Xldln/RICapBench.

from the abstract

Pith says

Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded · not checked by a person

It can be wrong. Challenge this review or reply to it.

The passes disagreed. Reader: holds up. Skeptic: agrees with the reader. Referee: major revision.

Solid benchmark with a clear instance-localization result, but the spatial relation metric rests on an unvalidated parser. This line is wrong

2 major objections · 4 minor

How often objections from reviews like this one are right: not yet measured

Are you an author? What you can do.

Not checked: figures, code, what the 52 references say.

The paper says, at Section 3.2, Spatial Relationship Parser

The review did not quote this passage.

Pith says: Objection 1 of 2 · major

The spatial relation parser is central to computing RelCap-F1 and RICScore, yet its accuracy is never quantitatively evaluated. The construction process (two rounds of manual validation with LLM assistance) is described, but no precision, recall, or F1 score of the parser against a held-out human-annotated set is reported.

more of objection 1

Without this, differences in RelCap-F1 across models (e.g., LLaVA-OneVision-2-8B at 30.76% vs. LocateAnything at 23.40%) may reflect parser artifacts (e.g., sensitivity to linguistic variation, rule coverage gaps) rather than genuine differences in spatial relation understanding. This undermines the spatial relation captioning conclusions, which are a significant dimension of the benchmark. The authors should report parser performance on a representative test set and discuss its impact on metric reliability.

The paper says, at Section 3.2, Construction and Quality Control

The review did not quote this passage.

Pith says: Objection 2 of 2 · major

The manual verification of instance captions is described but not quantified. No inter-annotator agreement (e.g., Cohen's kappa or Fleiss' kappa) is reported for the human reviews that check visual grounding and spatial relation accuracy. While manual verification is standard, the reliability of the ground truth is unknown.

more of objection 2

Given that the dataset serves as a benchmark, the degree of annotator consistency should be documented to assure users of label quality. The authors should provide an estimate of agreement, even on a subset, to strengthen trust in the annotations.

4 minor objections

The paper says, at Table 1

Pith says: minor objection 1 of 4

The 'Samples' column for RICapBench lists 245.5K, which corresponds to instance-level annotations, not image count (which is 26,854). The column heading is ambiguous; consider renaming it to 'Instance Annotations' or adding a note to clarify what is being counted, as other rows (e.g., DIOR-RSVG, 38.3K) likely refer to image-level samples.

The paper says, at Abstract and Section 5.1

Pith says: minor objection 2 of 4

The last sentence of the abstract states that LocateAnything 'scores lower on spatial relation captioning than other task-fine-tuned open-source VLMs.' This is vague; specify which models are being compared (e.g., all other fine-tuned models, or the highest-scoring one) for clarity.

show 2 more

The paper says, at Section 4.2, Eq. (2)

Pith says: minor objection 3 of 4

The term 'CIDEr-D(ˆcp, Sg)/10' is unusual because standard CIDEr-D is typically on a 0–10 scale; scaling by 1/10 is fine but should be briefly justified or referenced. Additionally, the composite CapA combines METEOR, CIDEr-D/10, and SPICE-OA, but the relative weighting is equally weighted; consider commenting on the sensitivity to this choice.

The paper says, at Section 5.2, Figure 4 caption

Pith says: minor objection 4 of 4

The heatmaps share a common color scale but the figure is grayscale in the PDF; ensure the final version uses color or distinguishable patterns to convey the scores clearly.

What would settle it

Manually annotate spatial relation triples for a random subset of 200 evaluation images (covering all three data sources) with at least two independent annotators, then compute the parser's precision and recall against this ground truth. Report inter-annotator agreement (e.g., Cohen's kappa). If precision < 85% or recall < 80%, the parser is insufficient for reliable metric-based comparisons. If both exceed 90%, the concern is largely mitigated.

from the skeptic's reading

How the review went

4 readings by deepseek-v4-flash · 13 Nov 2026

  1. Reader holds up confidence moderate
  2. Skeptic agrees 17 s · 15,160 tokens read, 2,067 written
  3. Editor wrote the verdict above 9 s · 15,899 tokens read, 922 written
  4. Referee major revision: 2 major objections, 4 minor 19 s · 15,503 tokens read, 2,309 written

Not run on this paper: the simulated authors' defence.

Pith did not check this review's objections against the paper.

The review in full

The review in brief, machine-written

The paper builds a large, careful dataset (245K instance annotations, 498K spatial relation tuples) combining OBBs with fine-grained captions, and evaluates 15 VLMs in a no-text-cue setting. The central finding—that instance localization is the main bottleneck—is convincingly supported by DetA scores and holds regardless of the parser question. That part is useful and likely reproducible.

The soft spot is the spatial relation parser. The stress test is right: parser accuracy is never quantified. The paper describes two rounds of manual validation, which is more than many benchmarks do, but absence of precision/recall/F1 on a held-out set means we cannot judge whether RelCap-F1 gaps are real or artifacts of rule coverage. The authors acknowledge the parser's construction but do not add a limitation statement about unmeasured accuracy. This matters because the claim that strong localization does not imply good spatial understanding (LLaVA-OneVision vs. LocateAnything) relies on RelCap-F1. That gap is plausible—different model designs could trade off—but the metric is the only evidence and it is unvalidated.

The detection and attribute metrics (DetA, CapA) are on firmer ground. The composite RICScore is thus only as trustworthy as its weakest component. For a benchmark paper, this is a fixable issue: a small human-annotated test set of spatial relation triples plus parser F1 would settle it.

Who this is for: anyone working on remote sensing VLMs or fine-grained vision-language evaluation. The dataset is the main asset; the evaluation protocol is a second asset with a fixable weakness.

Recommendation: send to review. The core contribution (dataset, instance-localization bottleneck) is solid. The spatial relation component needs stronger evidence before the paper can claim that RelCap-F1 is a reliable metric. Ask the authors to validate the parser and report inter-annotator agreement for the manual caption verification.

The strongest objection

The paper's central claim that existing VLMs struggle with fine-grained understanding rests partly on spatial relation captioning results measured by RelCap-F1, which relies entirely on the custom spatial relation parser (Section 3.2). The parser is built via two rounds of manual validation, but its accuracy is never quantitatively assessed. No precision, recall, or F1 of the parser against a held-out human-annotated set is reported. Without this, differences in RelCap-F1 across models (e.g., LLaVA-OneVision-2-8B highest at 30.76% vs. LocateAnything at 23.40%) could be driven by the parser’s sensitivity to linguistic variation or systematic biases in rule coverage, not by genuine differences in spatial relation understanding. The parser’s rules are tailored to the manually verified captions, which themselves may have unknown quality. Thus, the spatial relation component of the analysis, including the finding that 'strong instance localization does not necessarily coincide with accurate spatial relation understanding,' is not rigorously grounded. This does not undermine the instance localization bottleneck claim (supported by DetA), but it weakens the conclusions about spatial relation captioning, which is a significant dimension of the benchmark.

The reader's weakest assumption exactly identifies the parser accuracy issue. This is indeed the most load-bearing concern because the paper's composite metric and spatial relation analyses depend on it. However, the paper's central claim about instance localization being a bottleneck is supported by DetA, which is less dependent on the parser. The dataset contribution and the instance localization findings are robust even if the parser has moderate errors. The paper could improve by quantifying parser accuracy, but the current lack of quantification does not invalidate the core contributions. Hence, the verdict should remain ACCEPT (UNCHANGED). The reader's moderate confidence is appropriate.

The referee's report

If the proposed parser and metrics are reliable, RICapBench fills a clear gap in remote sensing VLM evaluation by requiring models to autonomously localize instances and generate spatially grounded captions. The finding that instance localization is the dominant bottleneck is valuable for guiding model design, and the public availability of the dataset supports future work. However, the significance hinges on the validity of the spatial relation parser and the reliability of the ground-truth captions, both of which lack quantitative quality assessment.

Pith's reading of the paper (a machine's summary, not the authors')

The paper introduces RICapBench, a dataset and benchmark designed to evaluate vision-language models on fine-grained understanding of remote sensing instances without relying on target-specific textual cues. It contains 245,466 instance-level annotations with oriented bounding boxes and natural-language descriptions covering appearance, location, and spatial relations to surrounding objects. The authors propose a spatial relation parser and the RelCap-F1 metric to measure spatial relation captioning accuracy, and combine them with existing metrics into a composite RICScore. Evaluating 15 open-source and proprietary VLMs, they find instance localization to be the primary bottleneck, with the best model achieving only 44.5% detection accuracy. The work aims to drive progress in end-to-end instance-level visual understanding for remote sensing applications such as disaster monitoring and UAV reconnaissance.

What carries the argument. The central mechanism is the RICapBench dataset (26,854 images, 245,466 instance annotations, 498,005 spatial relation tuples) built from three source datasets (DIOR-R, CODrone, FAIR1Mv2.0) covering general, UAV, and dense small-object remote sensing scenarios. Each instance annotation includes an oriented bounding box, a category label, and a natural-language description covering visible attributes, image location, and spatial relations to surrounding objects. Evaluation uses a custom spatial relation parser that converts captions into structured triples (subject, predicate, object), and the RelCap-F1 metric computes the F1 score over parsed triples. The composite RICScore is the geometric mean of DetA (detection accuracy), CapA (captioning accuracy for attributes and object descriptions), and RelCap-F1.

Core claim. The paper claims that existing general-purpose and remote-sensing-specific vision-language models (VLMs) struggle with fine-grained instance-level understanding in remote sensing imagery, particularly in autonomously localizing instances without text queries. Using the new RICapBench benchmark, the authors show that instance localization (measured by DetA) is the dominant weakness across all 15 tested models, with scores below 25% for most models and below 6% for remote-sensing fine-tuned models. They further discover a dissociation between localization and spatial relation captioning: LocateAnything achieves the highest DetA (44.50%) but low RelCap-F1 (23.40%), while LLaVA-OneVision-2-8B achieves the highest RelCap-F1 (30.76%) but low DetA (9.16%). This suggests that both capabilities need separate improvement.

The premise it rests on. The spatial relation parser correctly and consistently converts natural language captions into structured spatial relation triples; the paper does not report the parser's agreement with human annotations, so any systematic parsing error would propagate directly into RelCap-F1 and RICScore, undermining the validity of the composite evaluation.

If the paper is right (Pith's inferences, not the authors')

Model developers can use RICapBench as a standardized test to drive progress in joint instance localization and fine-grained description, a capability needed for autonomous geospatial analysis.

The identified bottleneck implies that improving visual encoders to retain small-object details and spatial layout during compression is a concrete research direction.

Applications like UAV disaster inspection and remote sensing emergency monitoring, where users cannot provide target-specific text cues, could directly benefit from models that score well on RICapBench.

The dissociation between localization and spatial relation captioning suggests that future work should design training pipelines that explicitly optimize both objectives, rather than relying on a single strong capability.

The spatial relation parser's accuracy is not quantified against human annotation; if the parser introduces systematic errors, the RelCap-F1 and RICScore metrics may misrepresent model capability. Reporting parser precision/recall on a held-out set would strengthen trust in the benchmark.

Because RelCap-F1 is computed only on successfully localized instances, a model with high localization recall (like LocateAnything) may have its spatial captioning unfairly penalized on many easy instances, while a model with low recall (like GeoChat) can appear better on RelCap-F1 by focusing only on a tiny subset. This compositional effect could mislead comparisons if not interpreted carefully.

The benchmark may inspire a new family of tasks that require an agent to 'find, describe, and relate' instances jointly, moving beyond isolated VQA or grounding tasks. This could lead to more holistic evaluation of VLMs for environmental monitoring.

Check this review

Pith stored no record of this review's passes and took no fingerprint of it. Reviews made by code from 13 Nov 2026 on carry both.

How often reviews like this one are right

Reviews like this one: written by deepseek-v4-flash, where what was read was not recorded.

How often objections from reviews like this one are right: not yet measured

Every value above, in the review's public record (JSON)

Reviews by people

This review was written by a machine. No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.

Request a human review

How Pith checks papers · The full audit of this paper

The paper

Abstract

Advances in vision-language models (VLMs) have improved remote sensing image analysis and supported geospatial decision-making. However, fine-grained understanding of remote sensing imagery remains challenging for VLMs. Large variations in object scale, complex geospatial relations among instances, and limited visual detail hinder precise instance localization, visible attribute identification, and spatial relation understanding, potentially leading to descriptions that lack visual grounding. Existing datasets and benchmarks insufficiently assess end-to-end instance localization and captioning without target-specific textual cues. To support this evaluation, we introduce RICapBench, a dataset and benchmark that unifies instance localization and fine-grained captioning in remote sensing. RICapBench contains 245,466 instance-level annotations and 498,005 spatial relation tuples spanning general remote sensing, UAV remote sensing, and dense small-object scenarios. Each annotation pairs an object's oriented bounding box with a natural language description of its visible attributes and spatial relations to surrounding instances and environmental elements. To evaluate the accuracy and completeness of spatial relation captioning, we propose a remote sensing spatial relation parser and the RelCap-F1 metric. We combine RelCap-F1 with instance localization and attribute captioning metrics into a composite metric, RICScore. Our evaluation of 15 advanced open-source and closed-source VLMs identifies instance localization as a major bottleneck for these models. LocateAnything achieves the highest RICScore of 31.68, but scores lower on spatial relation captioning than other task-fine-tuned open-source VLMs. Code and dataset are available at https://github.com/Xldln/RICapBench.

The paper's own sentences, arranged, kept beside the review and separate from it. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.

abstract compiled · 2026-11-13

The authors' main claim, as the classifier picked it out 0.99

“Our evaluation of 15 advanced open-source and closed-source VLMs identifies instance localization as a major bottleneck for these models.”

How the main claim is stated: asserted 1.00

What the abstract itself states, as probabilities: claims first 0.10 · states limitation 0.25 · human participants 0.07 · controlled comparison 0.18 · randomized assignment 0.01 · states quantitative result 0.98 · compares with prior results 0.87 · mentions code or data availability 0.99

The abstract, sentence by sentence

This table labels the abstract only (arXiv listing abstract v1). The number is the probability the classifier gave the label.

SentenceRoleThe authors' own workStates the main conclusionStrength
Advances in vision-language models (VLMs) have improved remote sensing image analysis and supported geospatial decision-making. background 1.00 0.04 0.03 asserted 1.00
However, fine-grained understanding of remote sensing imagery remains challenging for VLMs. gap 0.58 0.08 0.04 asserted 1.00
Large variations in object scale, complex geospatial relations among instances, and limited visual detail hinder precise instance localization, visible attribute identification, and spatial relation understanding, potentially leading to descriptions that lack visual grounding. background 0.86 0.07 0.04 hedged possibility 0.69
Existing datasets and benchmarks insufficiently assess end-to-end instance localization and captioning without target-specific textual cues. gap 0.99 0.06 0.04 asserted 1.00
To support this evaluation, we introduce RICapBench, a dataset and benchmark that unifies instance localization and fine-grained captioning in remote sensing. contribution 1.00 0.94 0.08 asserted 1.00
RICapBench contains 245,466 instance-level annotations and 498,005 spatial relation tuples spanning general remote sensing, UAV remote sensing, and dense small-object scenarios. contribution 0.67 0.86 0.04 asserted 1.00
Each annotation pairs an object's oriented bounding box with a natural language description of its visible attributes and spatial relations to surrounding instances and environmental elements. method 0.75 0.79 0.03 asserted 1.00
To evaluate the accuracy and completeness of spatial relation captioning, we propose a remote sensing spatial relation parser and the RelCap-F1 metric. method 0.83 0.96 0.04 asserted 0.99
We combine RelCap-F1 with instance localization and attribute captioning metrics into a composite metric, RICScore. method 0.80 0.96 0.05 asserted 1.00
Our evaluation of 15 advanced open-source and closed-source VLMs identifies instance localization as a major bottleneck for these models. result 0.99 0.97 0.44 asserted 1.00
LocateAnything achieves the highest RICScore of 31.68, but scores lower on spatial relation captioning than other task-fine-tuned open-source VLMs. result 1.00 0.92 0.17 asserted 1.00
Code and dataset are available at https://github.com/Xldln/RICapBench. contribution 0.82 0.41 0.02 asserted 0.98

What kind of paper the classifier reports this is: dataset or benchmark 1.00 · evidence from observation or experiment 0.98

What was examined, and what was not

Sources read

  • arXiv listing abstract v1

Not examined

  • full text
  • figures and tables
  • references and citing sentences
  • relations to other papers

Levels run

  • P abstract

Not run

  • S sections
  • T body sentences
  • C citations
  • R cross-paper relations

How the labels were made

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-11-13: 1 request, 8,904 input tokens.

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON

Figures (4)
Figure 1 of the paper
Figure 1. Overview of the remote sensing instance spatial relationship captioning task and the annotation format and examples of RICap
Figure 2 of the paper
Figure 2. Pipelines for (a) generating remote sensing instance captions with spatial relationships and (b) constructing the spatial relation
Figure 3 of the paper
Figure 3. Overview of RICapBench dataset statistics. (a) Instance counts and proportions for the 12 most frequent object categories and the
Figure 4 of the paper
Figure 4. Performance of different models across three data sources. D, C, and F denote DIOR-R, CODrone, and FAIR1Mv2.0, respectively.

Figures are the authors', reproduced from the paper.

References (52)
  1. [1] Jang Hyun Cho et al. PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding. In Advances in Neural Information Processing Systems (NeurIPS), volume 38, pages 26659–26721, 2025 on Pith
  2. [2] Long Xing, Qidong Huang, Xiaoyi Dong, Jiajie Lu, Pan Zhang, Yuhang Zang, Yuhang Cao, Conghui He, Jiaqi Wang, Feng Wu, and Dahua Lin. Conical Visual Concentration for Efficient Large Vision-Language Models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern... on Pith
  3. [3] Haotian Liu, Chunyuan Li, Qingyang Wu, and Y ong Jae Lee. Visual Instruction Tuning. In Advances in Neural Information Processing Systems (NeurIPS), volume 36, pages 34892–34916, 2023 on Pith
  4. [4] Haotian Liu, Chunyuan Li, Yuheng Li, and Y ong Jae Lee. Improved Baselines with Visual Instruction Tuning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages 26286–26296, 2024 on Pith
  5. [5] Kartik Kuckreja, Muhammad Sohail Danish, Muzammal Naseer, Abhijit Das, Salman Khan, and Fahad Shahbaz Khan. GeoChat: Grounded Large Vision-Language Model for Remote Sensing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages 278... on Pith
  6. [6] Chao Pang, Xingxing Weng, Jiang Wu, Jiayu Li, Yi Liu, Jiaxing Sun, Weijia Li, Shuai Wang, Litong Feng, Gui-Song Xia, and Conghui He. VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis. In Proceedings of the AAAI Conference on Artificial Intellige... on Pith
  7. [7] Sagar Soni, Akshay Dudhane, Hiyam Debary, Mustansar Fiaz, Muhammad Akhtar Munir, Muhammad Sohail Danish, Paolo Fraccaro, Campbell D. Watson, Levente J. Klein, Fahad Shahbaz Khan, and Salman Khan. EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues. In ... on Pith
  8. [8] Kaiyu Li, Ruixun Liu, Xiangyong Cao, Xueru Bai, Feng Zhou, Deyu Meng, and Zhi Wang. SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages 10... on Pith
  9. [9] Akashah Shabbir, Mohammed Zumri, Mohammed Bennamoun, Fahad Shahbaz Khan, and Salman Khan. GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensing. In Proceedings of the 42nd International Conference on Machine Learning (ICML) , volume 267 of Proceedings of Machine L... on Pith
  10. [10] Junjue Wang, Zhuo Zheng, Zihang Chen, Ailong Ma, and Y anfei Zhong. EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, number 6, pages 5481–5489, 2024 on Pith
  11. [11] Peirong Zhang, Yidan Zhang, Luxiao Xu, Jinliang Lin, Zonghao Guo, Fengxiang Wang, Xue Y ang, Kaiwen Wei, and Lei Wang. GeoViS: Geospatially Rewarded Visual Search for Remote Sensing Visual Grounding. arXiv preprint arXiv:2512.02715, 2025 on PitharXiv
  12. [12] Xiao An, Jiaxing Sun, Zihan Gui, and Wei He. CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language Models. In Advances in Neural Information Processing Systems (NeurIPS) , volume 38, Datasets and Benchmarks Track, pages 146328–146367, 2025 on Pith
  13. [13] Xiang Li, Jian Ding, and Mohamed Elhoseiny. VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding. In Advances in Neural Information Processing Systems (NeurIPS) , volume 37, Datasets and Benchmarks Track, pages 3229–3242, 2024 on Pith
  14. [14] Muhammad Sohail Danish, Muhammad Akhtar Munir, Syed Roshaan Ali Shah, Kartik Kuckreja, Fahad Shahbaz Khan, Paolo Fraccaro, Alexandre Lacoste, and Salman Khan. GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks. In Proceedings of the IEEE/CVF International C... on Pith
  15. [15] Y ang Zhan, Zhitong Xiong, and Yuan Yuan. RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data. IEEE Transactions on Geoscience and Remote Sensing , 61:1–13, 2023. doi:10.1109/TGRS.2023.3250471 on Pithdoi:10.1109/tgrs.2023.3250471
  16. [16] Gabriel Fiastre, Antoine Y ang, and Cordelia Schmid. CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 39518–39528, 2026 on Pith
  17. [17] Yunhao Li, Qin Li, Hao Wang, Xue Ma, Jiali Y ao, Shaohua Dong, Heng Fan, and Libo Zhang. Beyond MOT: Semantic Multi-Object Tracking. In European Conference on Computer Vision (ECCV) , pages 276–293, 2024. 11 on Pith
  18. [18] Bohao Li, Rui Wang, Guangzhi Wang, Yuying Ge, Yixiao Ge, and Ying Shan. SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension. arXiv preprint arXiv:2307.16125, 2023 on PithPith's reviewarXiv
  19. [19] Bohao Li, Yuying Ge, Yi Chen, Yixiao Ge, Ruimao Zhang, and Ying Shan. SEED-Bench-2-Plus: Benchmarking Multimodal Large Language Models with Text-Rich Visual Comprehension. arXiv preprint arXiv:2404.16790, 2024 on PithPith's reviewarXiv
  20. [20] Lin Chen, Jinsong Li, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Zehui Chen, Haodong Duan, Jiaqi Wang, Yu Qiao, Dahua Lin, and Feng Zhao. Are We on the Right Way for Evaluating Large Vision-Language Models? In Advances in Neural Information Processing Systems (NeurIPS), volume 37, p... on Pith
show 32 more
  1. [21] Hao Zhang, Hongyang Li, Feng Li, Tianhe Ren, Xueyan Zou, Shilong Liu, Shijia Huang, Jianfeng Gao, Lei Zhang, Chunyuan Li, and Jianwei Y ang. LLaV A-Grounding: Grounded Visual Chat with Large Multimodal Models. In European Conference on Computer Vision (ECCV) , pages 19–35, 2024 on Pith
  2. [22] Hanoona Rasheed et al. GLaMM: Pixel Grounding Large Multimodal Model. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages 13009–13018, 2024 on Pith
  3. [23] Peter Anderson, Basura Fernando, Mark Johnson, and Stephen Gould. SPICE: Semantic Propositional Image Caption Evaluation. In European Conference on Computer Vision (ECCV) , pages 382–398, 2016. doi:10.1007/978-3-319-46454-1_24 on Pithdoi:10.1007/978-3-319-46454-1_24
  4. [24] Dong-Jin Kim, Jinsoo Choi, Tae-Hyun Oh, and In So Kweon. Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 6271–6280, 2019 on Pith
  5. [25] Danpei Zhao, Bo Yuan, Ziqiang Chen, Tian Li, Zhuoran Liu, Wentao Li, and Yue Gao. Panoptic Perception: A Novel Task and Fine-Grained Dataset for Universal Remote Sensing Image Interpretation. IEEE Transactions on Geoscience and Remote Sensing, 62:1–14, 2024. doi:10.1109/TGRS.2... on Pithdoi:10.1109/tgrs.2024.3392778
  6. [26] Junwei Luo et al. SkySenseGPT: A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language Understanding. arXiv preprint arXiv:2406.10100, 2024 on PithPith's reviewarXiv
  7. [27] Sihan Liu, Yiwei Ma, Xiaoqing Zhang, Haowei Wang, Jiayi Ji, Xiaoshuai Sun, and Rongrong Ji. Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pa... on Pith
  8. [28] Junli Liu et al. AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) , pages 5177–5187, 2025 on Pith
  9. [29] Yuan Hu, Jianlong Yuan, Congcong Wen, Xiaonan Lu, Yu Liu, and Xiang Li. RSGPT: A Remote Sensing Vision Language Model and Benchmark. ISPRS Journal of Photogrammetry and Remote Sensing , 224:272–286, 2025 on Pith
  10. [30] Shuai Bai et al. Qwen3-VL Technical Report. arXiv preprint arXiv:2511.21631, 2025 on PithPith's reviewarXiv
  11. [31] Weiyun Wang et al. InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency. arXiv preprint arXiv:2508.18265, 2025 on PithPith's reviewarXiv
  12. [32] Shiyin Lu et al. Ovis2.5 Technical Report. arXiv preprint arXiv:2508.11737, 2025 on PithPith's reviewarXiv
  13. [33] Gemma Team et al. Gemma 3 Technical Report. arXiv preprint arXiv:2503.19786, 2025 on PithPith's reviewarXiv
  14. [34] Xiang An et al. LLaV A-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training. arXiv preprint arXiv:2509.23661, 2025 on PithPith's reviewarXiv
  15. [35] Xiang An et al. LLaV A-OneVision-2: Towards Next-Generation Perceptual Intelligence. arXiv preprint arXiv:2605.25979, 2026 on PithPith's reviewarXiv
  16. [36] Shihao Wang et al. LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding. arXiv preprint arXiv:2605.27365, 2026. 12 on PithPith's reviewarXiv
  17. [37] Alibaba Cloud. Qwen3.8-Flash. Alibaba Cloud Model Studio documentation, 2026. https://www.alibabacloud.com/help/en/model-studio/qwen3-8-flash . Accessed November 4, 2026 on Pith
  18. [38] Qwen Team. Qwen3.8-Max: A New Bar for Coding and Cowork. Official model release, August 2026. https://qwen.ai/blog?id=qwen3.8. Accessed October 29, 2026 on Pith
  19. [39] OpenAI. Introducing GPT-6 Sol and Luna. Official model release, 2026. https://openai.com/index/introducing-gpt-6-sol-and-luna/ . Accessed October 29, 2026 on Pith
  20. [40] Google DeepMind. Gemini 3.8 Flash. Model card, September 2026. https://deepmind.google/models/model-cards/gemini-3-8-flash/ . Accessed October 29, 2026 on Pith
  21. [41] Dilxat Muhtar, Zhenshi Li, Feng Gu, Xueliang Zhang, and Pengfeng Xiao. LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model. In Computer Vision – ECCV 2024 , volume 15132 of Lecture Notes in Computer Science, pages 440–457, 2025. doi:10.1007/97... on Pithdoi:10.1007/978-3-031-72904-1_26
  22. [42] Ke Li, Di Wang, Ting Wang, Fuyu Dong, Yiming Zhang, Luyao Zhang, Xiangyu Wang, Shaofeng Li, and Quan Wang. RSVG-ZeroOV: Exploring a Training-Free Framework for Zero-Shot Open-Vocabulary Visual Grounding in Remote Sensing Images. In Proceedings of the AAAI Conference on Artific... on Pithdoi:10.1609/aaai.v40i8.37555
  23. [43] Xin Lai, Zhuotao Tian, Yukang Chen, Y anwei Li, Yuhui Yuan, Shu Liu, and Jiaya Jia. LISA: Reasoning Segmentation via Large Language Model. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 9579–9589, 2024 on Pith
  24. [44] Sai Wang, Yutian Lin, and Yu Wu. Omni-Q: Omni-Directional Scene Understanding for Unsupervised Visual Grounding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages 14261–14270, 2024 on Pith
  25. [45] Maëlic Neau. RelateAnything: Real-Time Open-Vocabulary Relation Prediction From Any Inputs. arXiv preprint arXiv:2609.12552, 2026 on PithPith's reviewarXiv
  26. [46] Xingyi Zhou, Anurag Arnab, Chen Sun, and Cordelia Schmid. Dense Video Object Captioning from Disjoint Supervision. In International Conference on Learning Representations (ICLR) , 2025 on Pith
  27. [47] Tsung- Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C. Lawrence Zitnick. Microsoft COCO: Common Objects in Context. In European Conference on Computer Vision (ECCV), pages 740–755, 2014. doi:10.1007/978-3-319-10602-1_48 on Pithdoi:10.1007/978-3-319-10602-1_48
  28. [48] Ramakrishna Vedantam, C. Lawrence Zitnick, and Devi Parikh. CIDEr: Consensus-Based Image Description Evaluation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , pages 4566–4575, 2015. doi:10.1109/CVPR.2015.7299087 on Pithdoi:10.1109/cvpr.2015.7299087
  29. [49] Gong Cheng, Jiabao Wang, Ke Li, Xingxing Xie, Chunbo Lang, Y anqing Y ao, and Junwei Han. Anchor-Free Oriented Proposal Generator for Object Detection. IEEE Transactions on Geoscience and Remote Sensing , 60:1–11, 2022. doi:10.1109/TGRS.2022.3183022 on Pithdoi:10.1109/tgrs.2022.3183022
  30. [50] Kai Y e, Haidi Tang, Bowen Liu, Pingyang Dai, Liujuan Cao, and Rongrong Ji. More Clear, More Flexible, More Precise: A Comprehensive Oriented Object Detection Benchmark for UA V .arXiv preprint arXiv:2504.20032, 2025 on PithPith's reviewarXiv
  31. [51] Xian Sun, Peijin Wang, Zhiyuan Y an, Feng Xu, Ruiping Wang, Wenhui Diao, Jin Chen, Jihao Li, Yingchao Feng, Tao Xu, Martin Weinmann, Stefan Hinz, Cheng Wang, and Kun Fu. FAIR1M: A Benchmark Dataset for Fine-Grained Object Recognition in High-Resolution Remote Sensing Imagery. ... on Pithdoi:10.1016/j.isprsjprs.2021.12.004
  32. [52] Satanjeev Banerjee and Alon Lavie. METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments. In Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, pages 65–72, 2005. h... on Pith

Challenges and discussion

Disagree with the review, or know something it missed? Leave a comment, or challenge this review formally: a challenge becomes a permanent entry in this paper's record, and its decision is published here.

No comments yet.

Sign in to comment