Text2Traj2Text: Learning-by-Synthesis Framework for Contextual Captioning of Human Movement Trajectories
Not on the map. Why?
Abstract (arXiv)
This paper presents Text2Traj2Text, a novel learning-by-synthesis framework for captioning possible contexts behind shopper's trajectory data in retail stores. Our work will impact various retail applications that need better customer understanding, such as targeted advertising and inventory management. The key idea is leveraging large language models to synthesize a diverse and realistic collection of contextual captions as well as the corresponding movement trajectories on a store map. Despite learned from fully synthesized data, the captioning model can generalize well to trajectories/captions created by real human subjects. Our systematic evaluation confirmed the effectiveness of the proposed framework over competitive approaches in terms of ROUGE and BERT Score metrics.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 26 of its 49 references that are in the map. First posted on arXiv 19 Sep 2024.
Builds on
26 of 49 references.
References · 26
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
- 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
- 2017Dense-Captioning Events in Videoscited by 789
- 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 496
- 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 477
- 2022Multimodal Learning with Transformers: A Surveycited by 399
- 2018All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneouslycited by 364
- 2023Large Language Models are Zero-Shot Rankers for Recommender Systemscited by 307
- 2023Large Language Models are Effective Text Rankers with Pairwise Ranking Promptingcited by 302
14 more
- 2019Human Motion Trajectory Prediction: A Surveycited by 231
- 2018A Comprehensive Survey of Deep Learning for Image Captioningcited by 213
- 2023Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventionscited by 121
- 2023LLMaAA: Making Large Language Models as Active Annotatorscited by 78
- 2017A Survey of Indoor Localization Systems and Technologiescited by 77
- 2023PLACES: Prompting Language Models for Social Conversation Synthesiscited by 72
- 2023Lyfe Agents: Generative agents for low-cost real-time social interactionscited by 49
- 2021Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarizationcited by 46
- 2023Benchmarking Large Language Model Capabilities for Conditional Generationcited by 29
- 2020Pedestrian Models for Autonomous Driving Part II: High-Level Models of Human Behaviorcited by 23
- 2021Ask2Transformers: Zero-Shot Domain labelling with Pre-trained Language Modelscited by 13
- 2016An analytical framework to nowcast well-being using mobile phone datacited by 8
- 2020Understanding Crowd Behaviors in a Social Event by Passive WiFi Sensing and Data Miningcited by 4
- 2020Learning Patterns of Tourist Movement and Photography from Geotagged Photos at Archaeological Heritage Sites in Cuzco, Perucited by 2
Built on by
Citing papers per year: 2025: 1.
1 paper.