Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-07-13T01:03:27.721212Z
Paper Citation Record · LEDGER
As of 7 August 2026, this Paper Citation Record lists 67 of 67 outbound references and 0 inbound Pith citation observations for arXiv:2607.09008.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-07-13T01:03:27.721212Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
67 of 67 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation d8a38870-3797-493b-bbeb-162983dcff0f · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Flamingo: a visual language model for few-shot learning
Reference 1
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d13e7d89-cd13-4c3b-bb41-bca2523dc9c0 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
Reference 2
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2322de0a-0624-4ed2-838f-5b6fc8801c8d · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Khan, and Fahad Shahbaz Khan
Reference 3
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5110977b-83bc-4238-9c92-3f7e7430fce6 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes YOLOv4: Optimal Speed and Accuracy of Object Detection
Reference 4
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a61b1cb2-2eb2-4eb0-ba16-f983abe7b986 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Emerging properties in self-supervised vision transformers
Reference 5
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 996b68e7-2615-42e5-8229-79f898e06de2 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Microsoft COCO Captions: Data Collection and Evaluation Server
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9c8b6d85-92ae-4bf1-900a-4cfc330958c2 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes PaLI: A jointly-scaled multilingual language- image model
Reference 7
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d00a79d0-b91f-4043-8b89-01476a61dbdf · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes YOLO-World: Real- time open-vocabulary object detection
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 784c6c7e-7790-47dc-98ee-dd8095ce60d9 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Open-Vocabulary Object Detection using Pseudo Caption Labels
Reference 9
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9d367007-6b9b-4635-a381-d4270cff1f22 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes The cityscapes dataset for semantic urban scene understand- ing
Reference 10
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bae68df1-83b8-433e-87d2-0c1a49b639b4 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Class-balanced loss based on effective number of samples
Reference 11
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 06b14241-3d0b-4955-831b-df198936504c · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes BERT: Pre-training of deep bidi- rectional transformers for language understanding
Reference 12
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9b1f51df-28a1-470e-a511-1f895a8ddcbd · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Learning to prompt for open- vocabulary object detection with vision-language model
Reference 13
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a755bfc6-df12-4df7-8deb-9b416a64843f · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Cut, paste and learn: Surprisingly easy synthesis for instance detection
Reference 14
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a2d1b15a-d7bd-406a-bbf4-60eda22cc28c · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes PromptDet: Towards open-vocabulary detection using uncurated images
Reference 15
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3c7b3fd9-f071-437f-a555-8acc41454441 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Simple copy-paste is a strong data augmentation method for instance segmentation
Reference 16
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 852ab463-4088-4f6d-9462-baa7a61985b2 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Open-vocabulary object detection via vision and lan- 9 guage knowledge distillation
Reference 17
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1b6abb73-c4b2-4f1e-a8d1-acaf8900f662 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes LVIS: A dataset for large vocabulary instance segmentation
Reference 18
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 78eac4c5-17bd-4fc6-96de-ff3604acb886 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Masked autoencoders are scalable vision learners
Reference 19
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation afac1053-d8ab-4431-8f51-768c82b5299a · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Disen- tangling label distribution for long-tailed visual recog- nition
Reference 20
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4877e3ab-2079-4b1a-8a80-ea349dde6ede · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Unsupervised Prompt Learning for Vision-Language Models
Reference 21
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 13b3d113-b329-4486-9eca-a6ce819f0c01 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes MDETR – modulated detection for end-to-end multi-modal under- standing
Reference 22
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 39cb5d50-cbc4-4339-812a-b20d370a71dd · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes MaPLe: Multi-modal prompt learning
Reference 23
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 51e1d214-9737-4752-bec8-a138ea705bfc · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Grounded language-image pre- training
Reference 24
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation edcddd80-8352-47ed-af94-1fb7f35c4408 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
Reference 25
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation eca558fc-169c-42d8-b903-9a3f0f5bafd2 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Lawrence Zitnick
Reference 26
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dd9b96fb-cb14-4686-974a-2a608fd81d6f · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Focal loss for dense object detection
Reference 27
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bf20bdb2-b07a-485b-aed1-2b6755ebafc5 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Visual instruction tuning
Reference 28
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 420e6937-a05a-41d0-9022-e989a5b74643 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
Reference 29
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 45caed43-a91c-4a46-9f7e-cef67e63673d · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Long-tail learning via logit ad- justment
Reference 30
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4bc5d39e-c307-4b8a-ae9e-438f0652649d · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Simple open- vocabulary object detection
Reference 31
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 24bc332d-16ba-4a59-a2e7-8844ba187985 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Scaling open-vocabulary object detection
Reference 32
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b1fcdddc-ca28-4614-a1a9-66d558aa5f2e · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Imbalance problems in object detection: A re- view.IEEE Transactions on Pattern Analysis and Ma- chine Intelligence, pages 1–1, 2020
Reference 33
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 98c1e5a8-f933-4098-b424-195aa0265c0b · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes GPT-4 technical report
Reference 34
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 39793ec3-826d-4a21-ad58-a94ce4be7726 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Learning transferable visual models from natural language supervision
Reference 35
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7dbd3952-5111-4cbe-8bd1-e94153b1d361 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Aligning and prompting everything all at once for universal visual perception
Reference 36
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3cc1253e-990c-4caa-a3ef-36f34ce6a0be · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Test-time prompt tuning for zero-shot generalization in vision-language models
Reference 37
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 983d7793-9601-4f0e-b8d2-2a6b3c4eb4ab · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Equal- ization loss for long-tailed object recognition
Reference 38
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 22b51d12-11ae-4a4e-9f70-09bf6db4206f · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Equalization loss v2: A new gradient bal- ance approach for long-tailed object detection
Reference 39
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a1950c97-a0a4-4955-a771-ac22b754fb06 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Moondream: A small vision language model
Reference 40
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 48b95d46-a9dc-4858-8741-24f423ec97dd · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Tent: Fully test-time adaptation by entropy minimization
Reference 41
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 721e0868-4bd8-4aa3-802a-d8e3645ba53f · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Seesaw loss for long-tailed instance segmentation
Reference 42
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 08072b10-2a2a-4447-a8a0-e2132c57e693 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes GroupViT: Semantic segmentation emerges from text su- pervision
Reference 43
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b6da45c8-35a1-4885-8de2-73e8687bc2eb · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes End-to-end semi-supervised object detection with soft teacher
Reference 44
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 39efb0a4-b80e-4f99-8375-9ad5ddf7e143 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Improving pseudo labels for open-vocabulary object detection
Reference 45
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 66f5c8a1-031c-4b6d-8abd-f0c393ac2644 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes UniTab: Uni- fying tabular learning at scale
Reference 46
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 26ff197a-012a-4acd-92bd-b4d8a6880300 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Visual- language prompt tuning with knowledge-guided context optimization
Reference 47
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2ce8b913-0bfd-41b4-a936-3805228cf8df · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes CutMix: Regularization strategy to train strong classi- fiers with localizable features
Reference 48
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3e0f31da-da57-4de7-ac15-d60d471b9346 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Open-vocabulary DETR with condi- tional matching
Reference 49
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b6ab8ff8-cd44-49a3-838d-280f7150b7ac · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Unified Vision and Language Prompt Learning
Reference 50
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a2b59379-07e9-4489-9002-69f0db897f57 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Open-vocabulary object detection using captions
Reference 51
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e53bb192-3b6a-4386-99d4-7dfef59dc38e · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Dauphin, and David Lopez-Paz
Reference 52
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 18886383-2b5d-4abb-a251-1e25754983f7 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes GLIPv2: Unifying localization and vision-language un- derstanding
Reference 53
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1c5efbe0-6bac-4900-ae2b-967ca6bd989a · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Real-time Transformer-based Open-Vocabulary Detection with Efficient Fusion Head
Reference 54
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a84fd865-03b7-47d1-aeea-89fd4789f3da · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Re- gionCLIP: Region-based language-image pretraining
Reference 55
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2a963a03-883f-4982-b7be-eaeec8698097 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Conditional prompt learning for vision- language models
Reference 56
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d2657d6f-e39d-4fb1-94ea-bb949bb84597 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Learning to prompt for vision-language mod- els.International Journal of Computer Vision, 130: 2337–2348, 2022
Reference 57
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 42efb28c-514c-400d-924a-d51c04ad94cf · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Detecting twenty- thousand classes using image-level supervision
Reference 58
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 556e3719-ae7a-4acb-a5d4-7e33b07f74e9 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes MiniGPT-4: Enhancing vision- language understanding with advanced large language models
Reference 59
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 21aa748b-e3b9-4057-94dd-21aba2636fee · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Data augmentation remedies include copy-paste [16], Cut- Paste [14], MixUp [52], CutMix [48], and mosaic tiling [4, 8]
Reference 60
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a994cda8-e940-4d52-8dc5-edafcfcf7e4b · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Per-class instance counts in each validation split
Reference 61
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9d3694a6-70d3-4e77-8f54-386af1c7e605 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Detector Inference Settings All detector weights are frozen throughout and no fine- tuning is performed at any stage
Reference 62
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 49b62e83-7c75-41dd-a01e-a5702685c0a8 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Unresolved cited work
Reference 63
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 284de3bd-8397-4603-823a-0749dd230a35 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes We additionally ran CGAP with LLaV A (7B) as an ex- ploratory Phase II refiner for all completed backbone– dataset configurations
Reference 64
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0a06acf6-d83c-42cc-a248-0c042377e4c3 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes moondream (K=15,T 0=CC, strati- fied, three runs)
Reference 65
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3d8846d6-8ea0-416b-9570-da464608a8c7 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes Detection Quality Figure 12 plots refined caption length (words) against minority-class AP@0.5 across all 1,104 CGAP trials, colored by bucket assignment
Reference 66
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 01377427-9604-490a-891d-354dbd5c6985 · outbound
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes The primary metric is AP@0.5 for the designated mi- nority class (bus/COCO, truck/Cityscapes, Bike/Chula Vista)
Reference 67
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
No inbound Pith citation observations are available.