# Chain-of-Talkers (CoTalk): Fast Human Annotation of Dense Image Captions

arXiv: https://arxiv.org/abs/2505.22627 · HTML: https://mlsanity.com/paper/2505.22627/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 28 May 2025.

## Builds on (most cited first, 24 of 24)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models](https://mlsanity.com/paper/2311.06607/) (2023)
- [Perception Encoder: The best visual embeddings are not at the output of the network](https://mlsanity.com/paper/2504.13181/) (2025)
- [Long-CLIP: Unlocking the Long-Text Capability of CLIP](https://mlsanity.com/paper/2403.15378/) (2024)
- [RSGPT: A Remote Sensing Vision Language Model and Benchmark](https://mlsanity.com/paper/2307.15266/) (2023)
- [Exploring Models and Data for Remote Sensing Image Caption Generation](https://mlsanity.com/paper/1712.07835/) (2017)
- [DOCCI: Descriptions of Connected and Contrasting Images](https://mlsanity.com/paper/2404.19753/) (2024)
- [Improving Multimodal Datasets with Image Captioning](https://mlsanity.com/paper/2307.10350/) (2023)
- [Exploring a Fine-Grained Multiscale Method for Cross-Modal Remote Sensing Image Retrieval](https://mlsanity.com/paper/2204.09868/) (2022)
- [ImageInWords: Unlocking Hyper-Detailed Image Descriptions](https://mlsanity.com/paper/2405.02793/) (2024)
- [GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensing](https://mlsanity.com/paper/2501.13925/) (2025)
- [From Pixels to Prose: A Large Dataset of Dense Image Captions](https://mlsanity.com/paper/2406.10328/) (2024)
- [RemoteSAM: Towards Segment Anything for Earth Observation](https://mlsanity.com/paper/2505.18022/) (2025)
- [Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation](https://mlsanity.com/paper/2404.19752/) (2024)
- [FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity](https://mlsanity.com/paper/2411.15411/) (2024)
- [LHRS-Bot-Nova: Improved Multimodal Large Language Model for Remote Sensing Vision-Language Interpretation](https://mlsanity.com/paper/2411.09301/) (2024)
- [ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation](https://mlsanity.com/paper/2412.09754/) (2024)
- [What Makes for Good Image Captions?](https://mlsanity.com/paper/2405.00485/) (2024)
- [GeoPix: Multi-Modal Large Language Model for Pixel-level Image Understanding in Remote Sensing](https://mlsanity.com/paper/2501.06828/) (2025)

## Built on by (most cited first, 1 of 1)

- [DenseAnnotate: Enabling Scalable Dense Caption Collection for Images and 3D Scenes via Spoken Descriptions](https://mlsanity.com/paper/2511.12452/) (2025)

## Abstract (arXiv)

While densely annotated image captions significantly facilitate the learning of robust vision-language alignment, methodologies for systematically optimizing human annotation efforts remain underexplored. We introduce Chain-of-Talkers (CoTalk), an AI-in-the-loop methodology designed to maximize the number of annotated samples and improve their comprehensiveness under fixed budget constraints (e.g., total human annotation time). The framework is built upon two key insights. First, sequential annotation reduces redundant workload compared to conventional parallel annotation, as subsequent annotators only need to annotate the ``residual'' -- the missing visual information that previous annotations have not covered. Second, humans process textual input faster by reading while outputting annotations with much higher throughput via talking; thus a multimodal interface enables optimized efficiency. We evaluate our framework from two aspects: intrinsic evaluations that assess the comprehensiveness of semantic units, obtained by parsing detailed captions into object-attribute trees and analyzing their effective connections; extrinsic evaluation measures the practical usage of the annotated captions in facilitating vision-language alignment. Experiments with eight participants show our Chain-of-Talkers (CoTalk) improves annotation speed (0.42 vs. 0.30 units/sec) and retrieval performance (41.13% vs. 40.52%) over the parallel method.