---
tags:
  - диссер
---
# Gate-Fusion механизмы для мультимодальных CVGL-моделей - Claude

## GeoText-1652 
#Датасеты #CVGL 

1. https://dl.acm.org/doi/10.1007/978-3-031-73247-8_13
2. https://github.com/MultimodalGeo/GeoText-1652
3. https://arxiv.org/html/2412.17007v1
4. https://link.springer.com/chapter/10.1007/978-3-031-73247-8_13
5. https://huggingface.co/datasets/GeoText/GeoText-1652

## Where Am I 
#CVGL 

1. https://arxiv.org/pdf/2212.04074
2. https://arxiv.org/pdf/1703.07815
3. https://arxiv.org/pdf/2303.15676
4. https://github.com/yejy53/CVG-Text
5. https://arxiv.org/abs/2412.17007
6. https://arxiv.org/html/2412.17007
7. https://arxiv.org/pdf/2412.17007

## DEGF-YOLO Quality Aware Gating Unit 2025
#CVGL #gate #YOLO

1. https://arxiv.org/pdf/2405.02591
2. https://www.sciencedirect.com/science/article/abs/pii/S1474034626000881
3. https://pmc.ncbi.nlm.nih.gov/articles/PMC11962121/
4. https://www.mdpi.com/2673-2688/6/7/132
5. https://arxiv.org/html/2506.23252v1
6. https://pmc.ncbi.nlm.nih.gov/articles/PMC12473487/

## Learned Gating residual Connections
#CVGL #gate 

1. https://www.nature.com/articles/s41598-025-11989-6
2. https://www.mdpi.com/2076-3417/15/20/11259
3. https://www.sciencedirect.com/science/article/abs/pii/S0893608025003624
4. https://dl.acm.org/doi/10.1145/3756423.3756555
5. https://www.preprints.org/manuscript/202409.1917/v1
6. https://www.emergentmind.com/topics/early-fusion-methods
7. https://www.emergentmind.com/topics/gated-fusion-mechanism

## Multimodal Teacher-Studen Distillation
#CVGL #дистилляция
[[Knowledge_Distillation]]

1. https://arxiv.org/pdf/2509.00039
2. https://www.sciencedirect.com/science/article/abs/pii/S1566253524005207
3. https://www.ijcai.org/proceedings/2025/0248.pdf
4. https://arxiv.org/pdf/2506.08772
5. https://www.sciencedirect.com/science/article/abs/pii/S1051200424005001

## UC Merced Saturation
#CVGL #Датасеты 

1. https://paperswithcode.com/sota/scene-classification-on-uc-merced-land-use
2. https://www.researchgate.net/figure/UC-Merced-dataset-some-example-images-are-displayed-It-contains-21-scene-categories_fig3_271855526
3. https://arxiv.org/html/2408.16265
4. https://www.researchgate.net/publication/381622097_Classification_of_University_of_California_UC_Merced_Land-Use_Dataset_Remote_Sensing_Images_Using_Pre-Trained_Deep_Learning_Models
5. https://arxiv.org/pdf/1703.00121
6. https://arxiv.org/pdf/1608.05167
7. https://onlinelibrary.wiley.com/doi/abs/10.1002/9781394234271.ch4

## CrossText2Loc method architecture
#CVGL 

1. https://arxiv.org/html/2510.09586v1
2. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12390620/
3. https://arxiv.org/pdf/2401.00421
4. https://voxel51.com/blog/iccv-multimodal-ai
5. https://arxiv.org/pdf/2412.17007
6. https://arxiv.org/pdf/2412.17007
7. https://arxiv.org/html/2504.09925v1
8. https://arxiv.org/html/2504.09925v1

## CVGL Adaptive Fusion Gating 2024-25
#CVGL #gate 

1. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12299452/
2. https://pmc.ncbi.nlm.nih.gov/articles/PMC11207219/
3. https://arxiv.org/pdf/2509.12673
4. https://link.springer.com/chapter/10.1007/978-981-95-5628-1_26
5. https://www.mdpi.com/1424-8220/24/12/3719
6. https://pmc.ncbi.nlm.nih.gov/articles/PMC11548418/
7. https://arxiv.org/html/2510.22582v1
8. https://dl.acm.org/doi/10.1145/3728482.3757381

## Modality Reliability Score Mahalanobis Fusion DL
#CVGL 
[[InfoScore for residual routing]]

1. https://www.sciencedirect.com/science/article/abs/pii/S1566253524004263
2. https://arxiv.org/pdf/2309.05919
3. https://arxiv.org/pdf/2303.13810
4. https://arxiv.org/html/2505.05811
5. https://arxiv.org/html/2309.05919v2
6. https://arxiv.org/pdf/2504.16524

## Multimodal Fusion RS Scene Classification (text, img)
#CVGL #fusion 

1. https://link.springer.com/article/10.1007/s42452-025-06689-9
2. https://arxiv.org/pdf/2503.13814
3. https://www.mdpi.com/2673-2688/7/1/5
4. https://arxiv.org/pdf/2509.23310
5. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11838890/
6. https://arxiv.org/pdf/2412.02531

## Feature Norm Gating MM Fusion NN
#CVGL #fusion #gate #method/gate-fusion 

1. https://www.preprints.org/manuscript/202409.1917/v1
2. https://arxiv.org/pdf/2204.00102
3. https://arxiv.org/pdf/1807.06233
4. https://arxiv.org/pdf/1702.01992
5. https://arxiv.org/pdf/1803.09374
6. https://www.emergentmind.com/topics/gated-fusion-mechanism
7. https://arxiv.org/pdf/2512.04943
8. https://www.emergentmind.com/topics/gated-multimodal-units

## UAV Remote Sensing CLIP Scene Classification benchmark
#CVGL #VLM 

1. https://arxiv.org/pdf/1703.00121
2. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7070946/
3. https://arxiv.org/pdf/2510.24321
4. https://arxiv.org/abs/2510.24321
5. https://arxiv.org/html/2510.24321v1

## Text-Image Teacher Student Distillation (single modality Inference or missing modality)
#CVGL 
[[Knowledge_Distillation]]

1. https://arxiv.org/pdf/2207.01426
2. https://arxiv.org/pdf/2505.21549
3. https://aclanthology.org/2024.emnlp-main.351.pdf
4. https://arxiv.org/pdf/2603.24208
5. https://arxiv.org/pdf/2504.07029
6. https://arxiv.org/pdf/2309.15238
7. https://arxiv.org/pdf/2507.18192
8. https://arxiv.org/pdf/1703.00121
9. https://arxiv.org/pdf/2303.15083
10. https://openreview.net/forum?id=S5coB5kqSD&noteId=hUnKfBwGvh
11. https://arxiv.org/pdf/2512.15311
12. https://openaccess.thecvf.com/content/CVPR2024/html/Huo_C2KD_Bridging_the_Modality_Gap_for_Cross-Modal_Knowledge_Distillation_CVPR_2024_paper.html
13. https://papers.nips.cc/paper_files/paper/2024/file/e34d908241aef40440e61d2a27715424-Paper-Conference.pdf
 missing modality RS distillation
14. https://www.arxiv.org/pdf/2511.11460
15. https://www.ijcai.org/proceedings/2025/
16. https://www.researchgate.net/publication/395685476_DPMamba_Distillation_Prompt_Mamba_for_Multimodal_Remote_Sensing_Image_Classification_with_Missing_Modalities
17. https://arxiv.org/html/2511.11460
18. https://www.ijcai.org/proceedings/2025/0248.pdf

## Entropy-Based Modality Weighted Adaptive Fusion
#CVGL #fusion 

1. https://arxiv.org/pdf/2510.01677
2. https://www.emergentmind.com/topics/adaptive-modality-fusion-modules
3. https://arxiv.org/pdf/2505.15417
4. https://www.emergentmind.com/topics/dynamic-modality-weighting
5. https://www.emergentmind.com/topics/entropy-gated-contrastive-fusion
6. https://jrnl.kai.edu.ua/index.php/PIU/article/view/21098
7. https://www.sciencedirect.com/science/article/abs/pii/S1566253525006530
8. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7513103/
9. https://dl.acm.org/doi/10.1007/978-981-96-0972-7_2

## Learnable Scalar Residual MM Fusion and Gate
#CVGL #fusion #gate 

1. https://www.emergentmind.com/topics/gated-multimodal-units
2. https://arxiv.org/pdf/1907.00135
3. https://link.springer.com/article/10.1007/s40747-025-02023-3
4. https://www.emergentmind.com/topics/gated-fusion-module
5. https://arxiv.org/html/2510.17078v1
6. https://www.emergentmind.com/topics/adaptive-modality-fusion-modules
7. https://www.themoonlight.io/en/review/beyond-simple-fusion-adaptive-gated-fusion-for-robust-multimodal-sentiment-analysis
8. https://arxiv.org/html/2510.01677v1

## Region Level Cross-Modal Matching
#CVGL 

1.  https://arxiv.org/pdf/2603.08491
2. https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/01738.pdf
3. https://arxiv.org/pdf/2510.20291
4. https://arxiv.org/html/2603.08491
5. https://arxiv.org/pdf/2311.12751
6. https://link.springer.com/chapter/10.1007/978-3-031-73247-8_13
7. https://link.springer.com/chapter/10.1007/978-981-95-6123-0_53

## Gated Residual Feature Fusion RS UAV 2024
#CVGL #gate #residual 

1. https://www.tandfonline.com/doi/full/10.1080/01431161.2024.2429784
2. https://www.sciencedirect.com/science/article/abs/pii/S0031320325013858
3. https://arxiv.org/pdf/2304.11422
4. https://www.tandfonline.com/doi/abs/10.1080/2150704X.2024.2305177
5. https://www.tandfonline.com/doi/abs/10.1080/01431161.2024.2425875

## DEGF-YOLO
#CVGL #YOLO 

1. https://arxiv.org/pdf/2506.23252
2. https://pmc.ncbi.nlm.nih.gov/articles/PMC12360555/
3. https://www.mdpi.com/2504-446X/9/11/804
4. https://www.mdpi.com/2072-4292/17/24/3936
5. https://arxiv.org/pdf/2510.10765
6. https://www.mdpi.com/2504-446X/9/7/479

## Feature Quality, Norm, MM VL Fusion Gate
#CVGL #gate #VLM 

1. https://arxiv.org/pdf/2601.10710
2. https://www.sciencedirect.com/science/article/pii/S1566253525011248
3. https://arxiv.org/html/2504.02477v1
4. https://arxiv.org/pdf/2501.08443
5. https://arxiv.org/pdf/2504.09925
6. https://arxiv.org/pdf/2410.17779
7. https://arxiv.org/html/2511.02113v1
8. https://medium.com/@xiaxiami/exploring-feature-fusion-and-matching-in-vision-language-models-3573b6e529b4