ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model | Paper Citation Record

Observation cc9054c9-867b-423a-b426-2fa2669f5baf · outbound

This paper cites Deep Learning using Rectified Linear Units (ReLU).

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Deep Learning using Rectified Linear Units (ReLU)

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.602727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33724053-7262-4073-b3cf-99c545c9044c · outbound

This paper cites Barron, Fer- ran Marques, and Jitendra Malik.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Barron, Fer- ran Marques, and Jitendra Malik

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.608496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 406c57ea-401b-4377-82dd-566577064de0 · outbound

This paper cites Qwen Technical Report.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Qwen Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.614159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e606117-7d9f-443f-bb03-db732569e074 · outbound

This paper cites CoReS: Orchestrating the Dance of Reasoning and Segmentation.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model CoReS: Orchestrating the Dance of Reasoning and Segmentation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.619538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8670c5ab-c675-4e1c-a7c2-8de69265d678 · outbound

This paper cites PaliGemma: A versatile 3B VLM for transfer.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model PaliGemma: A versatile 3B VLM for transfer

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.625056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation baea3694-043d-48ac-8e92-fe3d7526c3b3 · outbound

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

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Coco- stuff: Thing and stuff classes in context

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.630566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4dae4b5-f4a4-496e-acb3-bec70a780927 · outbound

This paper cites Emerg- ing properties in self-supervised vision transformers.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Emerg- ing properties in self-supervised vision transformers

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.636951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01ddf6a1-4087-4e6b-96da-84fe45560491 · outbound

This paper cites Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.646884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee8b1da5-7b65-49ca-b49a-e87c59f6ab99 · outbound

This paper cites an unresolved cited work.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.655072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c3a0701-eb07-4aa1-a8e6-ac61d243cd8a · outbound

This paper cites Rethinking Atrous Convolution for Semantic Image Segmentation.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Rethinking Atrous Convolution for Semantic Image Segmentation

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.663763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63341173-fefd-42f3-bdce-6bfaa1798857 · outbound

This paper cites A Unified Sequence Interface for Vision Tasks.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model A Unified Sequence Interface for Vision Tasks

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.671530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7eb7c55-f6dd-4d02-bb83-2848e14e3f8e · outbound

This paper cites Schwing, and Alexander Kir- illov.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Schwing, and Alexander Kir- illov

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.678258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a79df8a7-3099-4d6b-b159-806618062944 · outbound

This paper cites Schwing, Alexan- der Kirillov, and Rohit Girdhar.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Schwing, Alexan- der Kirillov, and Rohit Girdhar

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.684396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8a1f219-05f4-46f2-8f6b-6705ee8b53ce · outbound

This paper cites CascadePSP: Toward class-agnostic and very high- resolution segmentation via global and local refinement.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model CascadePSP: Toward class-agnostic and very high- resolution segmentation via global and local refinement

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.690426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 472714cf-0a71-48e2-ad16-e20305fe19bd · outbound

This paper cites Gonzalez, Ion Stoica, and Eric P.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Gonzalez, Ion Stoica, and Eric P

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.694974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cf0912c-d82e-4403-96eb-81220347d1e6 · outbound

This paper cites Instance-aware se- mantic segmentation via multi-task network cascades.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Instance-aware se- mantic segmentation via multi-task network cascades

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.700692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9fde1d8-d406-4036-b6e1-d06598d11d26 · outbound

This paper cites InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.708748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b38e67c-72ca-45f5-9857-f083d57431a7 · outbound

This paper cites Vision-language transformer and query generation for refer- ring segmentation.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Vision-language transformer and query generation for refer- ring segmentation

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.720146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86d48a15-4367-4cad-b139-7a0fd8be5078 · outbound

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

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model De- coupling zero-shot semantic segmentation

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.725466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce5e425e-f964-4565-afbd-cfd6c5d71098 · outbound

This paper cites A discriminatively trained, multiscale, deformable part model.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model A discriminatively trained, multiscale, deformable part model

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.732244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 712ad1f6-051a-4afe-b9ae-0cf631fd18fa · outbound

This paper cites Dual attention network for scene segmentation.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Dual attention network for scene segmentation

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.738344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 468bd23d-d2f5-4d5f-a882-d82b4d1655ea · outbound

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

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Scal- ing open-vocabulary image segmentation with image-level labels

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.744388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3f0ae87-5a05-4d50-a933-63407e84642a · outbound

This paper cites Fast r-cnn.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Fast r-cnn

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.829966Z

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 4e1b00fc-59f0-437c-8b0b-7adb9f285eb7 · outbound

This paper cites Efficient hierarchical graph-based video segmentation.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Efficient hierarchical graph-based video segmentation

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.813092Z

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 feadfcc1-fa40-435e-9f00-49e411c620cf · outbound

This paper cites SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.764202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d406e68-77a8-4547-8ecd-a6be74544aa0 · outbound

This paper cites Global knowledge calibration for fast open-vocabulary segmentation.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Global knowledge calibration for fast open-vocabulary segmentation

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.794206Z

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 695588bf-8ac2-4c5f-b90a-4ce4999a5c09 · outbound

This paper cites Multi-modal instruction tuned llms with fine-grained visual perception.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Multi-modal instruction tuned llms with fine-grained visual perception

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.772644Z

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 8328d994-4c35-4f3c-855e-87f1083541ca · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model LoRA: Low-Rank Adaptation of Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.787127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 667a8c61-474c-4eb2-bdc1-a78bf072d809 · outbound

This paper cites Bi-directional relationship inferring network for referring image segmentation.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Bi-directional relationship inferring network for referring image segmentation

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.751208Z

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 f72b2860-a780-43f2-94a4-44a5abbbbb04 · outbound

This paper cites Referring im- age segmentation via cross-modal progressive comprehen- sion.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Referring im- age segmentation via cross-modal progressive comprehen- sion

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.727435Z

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 8592435d-0e8b-42ed-a9fc-ac42b5963117 · outbound

This paper cites CCNet: Criss-cross attention for semantic segmentation.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model CCNet: Criss-cross attention for semantic segmentation

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.699887Z

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 9b3796b3-aed2-4e82-aa22-ac393def43ef · outbound

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

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Scaling up visual and vision-language representation learning with noisy text supervision

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.817090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f72a46c9-8ce4-4987-be4d-80882b00fa95 · outbound

This paper cites Collaborative vision-text rep- resentation optimizing for open-vocabulary segmentation.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Collaborative vision-text rep- resentation optimizing for open-vocabulary segmentation

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.655968Z

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 7fdc2374-2927-4d20-89ef-ce062cd36847 · outbound

This paper cites Locate then segment: A strong pipeline for referring image segmentation.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Locate then segment: A strong pipeline for referring image segmentation

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.634113Z

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 06feee68-e2b9-4bf9-a4f7-05bc6e827007 · outbound

This paper cites Referitgame: Referring to objects in pho- tographs of natural scenes.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Referitgame: Referring to objects in pho- tographs of natural scenes

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.613695Z

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 6433f450-c112-4599-a060-8f5da956b3be · outbound

This paper cites Segment any- thing.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Segment any- thing

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.593290Z

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 b2c2b052-bab4-4579-a33b-62edd58b93a9 · outbound

This paper cites Large language models are zero-shot reasoners.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Large language models are zero-shot reasoners

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.569494Z

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 83edde41-c518-440b-80c9-ed98b8846423 · outbound

This paper cites Lisa: Reasoning segmenta- tion via large language model.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Lisa: Reasoning segmenta- tion via large language model

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.859899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c36fba00-d6af-4aeb-86a7-9886842fa00a · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model LLaVA-OneVision: Easy Visual Task Transfer

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.867634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 877046cf-543e-44f7-9091-4932d560821a · outbound

This paper cites BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.529184Z

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 690077fb-17d7-47a2-b76e-8a6bd67a5223 · outbound

This paper cites Referring transformer: A one- step approach to multi-task visual grounding.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Referring transformer: A one- step approach to multi-task visual grounding

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.509319Z

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 72a2b959-46dd-4dea-a489-e37fced6d16b · outbound

This paper cites Textbooks are all you need ii: phi-1.5 technical report, 2023.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Textbooks are all you need ii: phi-1.5 technical report, 2023

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.486608Z

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 dec07de0-38ab-4eaa-ac37-913a67839e81 · outbound

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

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Open-vocabulary semantic segmentation with mask-adapted clip

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.452323Z

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 07ea0b25-15aa-4478-8a64-45321df358fc · outbound

This paper cites Microsoft COCO: Common Objects in Context.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Microsoft COCO: Common Objects in Context

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.897561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32b269f7-7bff-4b8b-9bff-f80d8a639b46 · outbound

This paper cites Visual instruction tuning, 2023.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Visual instruction tuning, 2023

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.903182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12d2280a-d8f1-466d-9559-30e2cbbcb6aa · outbound

This paper cites Fully convolutional networks for semantic segmentation.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Fully convolutional networks for semantic segmentation

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.410159Z

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 6e189871-22a0-43f1-b894-35761da8fbf6 · outbound

This paper cites Decoupled Weight Decay Regularization.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Decoupled Weight Decay Regularization

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.913998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2ab0f93-7bd6-42cc-91df-66e21610c6b1 · outbound

This paper cites Cascade grouped attention network for referring expression segmentation.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Cascade grouped attention network for referring expression segmentation

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.388448Z

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 104f859b-3744-4b76-8055-2c3b3d9115d3 · outbound

This paper cites Generation and comprehension of unambiguous object descriptions.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Generation and comprehension of unambiguous object descriptions

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.366413Z

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 872b78b8-0097-48b5-9244-de8b596374c7 · outbound

This paper cites The mapillary vistas dataset for semantic understanding of street scenes.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model The mapillary vistas dataset for semantic understanding of street scenes

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.930956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 019f3a6a-ded3-4691-9e91-19bfd3467ebf · outbound

This paper cites Chatgpt: A language model for conversational ai.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Chatgpt: A language model for conversational ai

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.319108Z

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 dac3c2a1-6ded-4d4f-8369-3e8dc3e16b12 · outbound

This paper cites Gpt-4 technical report, 2023.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Gpt-4 technical report, 2023

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.944616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34c97eb1-eb05-4fbc-b68e-a2a15804a35b · outbound

This paper cites Kosmos-2: Ground- ing multimodal large language models to the world.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Kosmos-2: Ground- ing multimodal large language models to the world

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.278398Z

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 39d0a7dd-ec4e-4fa7-82c8-81ee1552a315 · outbound

This paper cites Kosmos-2: Grounding Multimodal Large Language Models to the World.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Kosmos-2: Grounding Multimodal Large Language Models to the World

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.957551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4484be1f-82de-4194-8d0e-62c05722f88a · outbound

This paper cites an unresolved cited work.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-08-12T10:10:42.255454Z

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 770cf0eb-9593-48f3-9639-6196fc696c0a · outbound

This paper cites Pinheiro, Tsung-Yi Lin, Ronan Collobert, and Piotr Doll´ar.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Pinheiro, Tsung-Yi Lin, Ronan Collobert, and Piotr Doll´ar

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.235786Z

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 c36e3f83-f330-46be-a92a-f67190285945 · outbound

This paper cites Multiscale combinatorial grouping for image segmentation and object proposal gener- ation.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Multiscale combinatorial grouping for image segmentation and object proposal gener- ation

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.217544Z

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 57339680-1a03-4d27-85a4-2380a7780b00 · outbound

This paper cites Learning to segment every referring object point by point.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Learning to segment every referring object point by point

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.197893Z

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 59a4f07e-f360-429a-b3d5-51a7e8aa0aeb · outbound

This paper cites Learning transferable visual models from natural language supervision.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Learning transferable visual models from natural language supervision

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.986159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5f58f64-088c-4ebc-88cd-82efb08cd80c · outbound

This paper cites Learn- ing transferable visual models from natural language super- vision.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Learn- ing transferable visual models from natural language super- vision

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:40.993676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95f21376-6334-48a6-8ff1-4d766b914a40 · outbound

This paper cites Anwer, Eric Xing, Ming-Hsuan Yang, and Fahad S.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Anwer, Eric Xing, Ming-Hsuan Yang, and Fahad S

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.129623Z

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 3e3e2a8f-2770-47de-9ed6-c23a7c8d921d · outbound

This paper cites Deepspeed: System optimizations enable train- ing deep learning models with over 100 billion parameters.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Deepspeed: System optimizations enable train- ing deep learning models with over 100 billion parameters

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.104654Z

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 6084e481-980e-45df-863d-ead855e42446 · outbound

This paper cites Pixellm: Pixel reasoning with large multimodal model.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Pixellm: Pixel reasoning with large multimodal model

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.078881Z

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 091d006e-4246-4292-9933-ae0e13200fe1 · outbound

This paper cites U-net: Convolutional networks for biomedical image segmentation.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model U-net: Convolutional networks for biomedical image segmentation

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.050276Z

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 b01dd00a-2855-4aad-ac96-e22bd1db2263 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model LLaMA: Open and Efficient Foundation Language Models

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:41.022299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efaf51df-9525-4fd6-ae6d-369540f4f34d · outbound

This paper cites Selective search for object recognition.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Selective search for object recognition

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.024766Z

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 4c2effc2-46d7-4be0-96d6-1d5b96e2e933 · outbound

This paper cites Llm-seg: Bridging image segmen- tation and large language model reasoning.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Llm-seg: Bridging image segmen- tation and large language model reasoning

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:42.002608Z

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 2a539345-3b75-4d8e-b1c7-e22198fa5d20 · outbound

This paper cites SegRefiner: Towards model- agnostic segmentation refinement with discrete diffusion process.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model SegRefiner: Towards model- agnostic segmentation refinement with discrete diffusion process

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:41.985143Z

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 9096e147-9792-4ea6-8cbb-84a8b06d9cec · outbound

This paper cites VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:41.049912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7b7176e-bea8-4b06-9999-8cea01f96982 · outbound

This paper cites The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:41.057624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f637c6f-b367-4b98-bea7-b68c8f2122a3 · outbound

This paper cites Non-local neural networks.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Non-local neural networks

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:41.063230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0374e256-6842-4722-ae9b-0d97a4800603 · outbound

This paper cites SOLO: Segmenting objects by locations.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model SOLO: Segmenting objects by locations

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:41.956507Z

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 97186277-4ff4-47fe-a2ae-70c769f44316 · outbound

This paper cites Solov2: Dynamic and fast instance segmentation.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Solov2: Dynamic and fast instance segmentation

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:41.939830Z

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 df85ce4d-d2c9-4611-9ebd-2dc1a549d400 · outbound

This paper cites Images Speak in Images: A Generalist Painter for In-Context Visual Learning.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Images Speak in Images: A Generalist Painter for In-Context Visual Learning

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:41.080050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 125b212e-419c-4753-8ec3-e38a42756858 · outbound

This paper cites SegGPT: Segmenting Everything In Context.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model SegGPT: Segmenting Everything In Context

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:41.085777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59d13369-d98d-4855-b1fd-daaf17007b9c · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Chain-of-thought prompting elicits reasoning in large language models

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:41.922973Z

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 9ec67287-7a75-47a5-86a9-b6c218785426 · outbound

This paper cites Gsva: Generalized segmentation via multimodal large language models.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Gsva: Generalized segmentation via multimodal large language models

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:41.904733Z

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 6104d1f6-685f-4683-bf9a-d92dec4c4a89 · outbound

This paper cites Alvarez, and Ping Luo.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Alvarez, and Ping Luo

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:41.104345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4704578f-c2ad-4907-9140-7b5966b79f5d · outbound

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

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Open-vocabulary panop- tic segmentation with text-to-image diffusion models

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:41.109789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1d07908-f8ea-431a-8854-4ab39d1af1b0 · outbound

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

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model A simple baseline for open- vocabulary semantic segmentation with pre-trained vision- language model

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:41.859266Z

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 730d6885-8b49-43ac-81d3-67320b97a0be · outbound

This paper cites Fine-grained visual prompting, 2023.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Fine-grained visual prompting, 2023

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:41.840574Z

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 68db3912-cd72-4051-b9a4-11fd34e18873 · outbound

This paper cites Ferret: Refer and Ground Anything Anywhere at Any Granularity.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Ferret: Refer and Ground Anything Anywhere at Any Granularity

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:41.126078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a056f1c-adde-4864-8440-8f745078ba01 · outbound

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

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Convolutions die hard: Open-vocabulary seg- mentation with single frozen convolutional clip

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:41.822743Z

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 1cc26dc8-4858-4a84-acd7-69b225e49105 · outbound

This paper cites Osprey: Pixel un- derstanding with visual instruction tuning.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Osprey: Pixel un- derstanding with visual instruction tuning

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:41.805366Z

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 548302c0-d01d-4a26-9eac-6ec52d771371 · outbound

This paper cites Sigmoid loss for language image pre-training,.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Sigmoid loss for language image pre-training,

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:41.144523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7556df97-c4ee-4b7d-b8ab-f513b2f3bb51 · outbound

This paper cites GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:41.151302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5923443f-74a8-41ea-ae6e-c52518152f71 · outbound

This paper cites ControlVideo: Training-free Controllable Text-to-Video Generation.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model ControlVideo: Training-free Controllable Text-to-Video Generation

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:41.157888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 891d1b46-5fc9-4f41-a6f8-4fb9f8447cdb · outbound

This paper cites Groundhog: Grounding large language models to holistic segmentation.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Groundhog: Grounding large language models to holistic segmentation

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:41.775048Z

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 a43a1024-e009-476b-aede-3d65b8b1cb3a · outbound

This paper cites Psalm: Pixelwise segmentation with large multi-modal model.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Psalm: Pixelwise segmentation with large multi-modal model

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:41.756026Z

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 46b773f9-a729-4c19-962d-315d1de1023b · outbound

This paper cites Rethinking semantic segmen- tation from a sequence-to-sequence perspective with trans- formers.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Rethinking semantic segmen- tation from a sequence-to-sequence perspective with trans- formers

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:41.739593Z

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 6e715acd-3bbc-4c16-88b8-ecfbf0d317ba · outbound

This paper cites Scene parsing through ade20k dataset.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Scene parsing through ade20k dataset

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:41.722980Z

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 cf837357-61af-430d-ac08-29f3e48b1a29 · outbound

This paper cites Seqtr: A simple yet universal network for visual grounding.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model Seqtr: A simple yet universal network for visual grounding

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:41.704525Z

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 25354d67-8d8e-4442-96ce-34acb6d4f0c4 · outbound

This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-12T10:10:41.190681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9380f26d-e32a-4e8c-b96d-46447ed59b62 · outbound

This paper cites User: <IMAGE,MASK> Please segment target region with mask and corre- sponding category.

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model User: <IMAGE,MASK> Please segment target region with mask and corre- sponding category

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:10:41.686647Z

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.

Coverage vector

Reference resolution

Outbound references

Pith citing papers