pith. sign in

arxiv: 2604.19798 · v1 · submitted 2026-04-10 · 💻 cs.CY · cs.CV· econ.EM

Diagnosing Urban Street Vitality via a Visual-Semantic and Spatiotemporal Framework for Street-Level Economics

Xinxin Zhuo , Mengyuan Niu , Ruizhe Wang , Junyan Yang , Qiao Wang This is my paper

Pith reviewed 2026-05-10 16:51 UTC · model grok-4.3

classification 💻 cs.CY cs.CVecon.EM
keywords street vitalitystreet view imagerybrand hierarchyspatiotemporal heterogeneitylocation-based servicesurban economicsvisual-semantic analysisgeographically weighted regression
0
0 comments X

The pith

A visual-semantic framework shows street vibrancy arises from brand hierarchy interactions with mall externalities across daily time periods.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces a visual-semantic and spatiotemporal framework operationalized as the Street Economic Vitality Index to assess micro-scale street economics. It parses street view images for signboards, glass interfaces, and closures, then uses a dual-stage VLM-LLM pipeline to standardize signage into global brand hierarchies for a spatially smoothed premium index. A temporal lag design with location-based services data captures realized demand and combines with category-weighted Gaussian spillovers to build a three-dimensional diagnostic covering commercial activity, spatial utilization, and physical environment. Experiments with time-lagged geographically weighted regression across eight tidal periods in Nanjing identify quasi-causal heterogeneity where vibrancy depends on hierarchical brand clustering and mall effects, with high-quality interfaces peaking midday and evening while recession produces lagged nighttime repulsion.

Core claim

The framework integrates instance segmentation of streetscape elements, a dual VLM-LLM pipeline for standardizing signage into global brand hierarchies to quantify a brand premium index, and a temporal lag design using LBS data within a category-weighted Gaussian spillover model. This constructs the Street Economic Vitality Index as a three-dimensional system that reveals quasi-causal spatiotemporal heterogeneity in street vibrancy arising from interactions between hierarchical brand clustering and mall-induced externalities, where high-quality interfaces show peak attraction during midday and evening while structural recession produces a lagged nighttime repulsion effect.

What carries the argument

The Street Economic Vitality Index (SEVI), a three-dimensional diagnostic system that integrates visual-semantic parsing of street views, brand hierarchy standardization, and time-lagged spatiotemporal regression to link commercial activity, spatial utilization, and physical environment.

If this is right

  • Hierarchical brand clustering interacts with mall-induced externalities to shape street vibrancy.
  • High-quality interfaces produce peak attraction during midday and evening tidal periods.
  • Structural recession generates a lagged repulsion effect during nighttime periods.
  • The three-dimensional diagnostic system enables evidence-based precision spatial governance.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The framework could be applied to other cities to test whether the brand clustering and mall interaction patterns hold in different retail contexts.
  • Real-time LBS integration might support dynamic interventions that adjust for observed time-of-day effects.
  • The brand standardization component could help map economic diversity patterns across street networks.

Load-bearing premise

The dual-stage VLM-LLM pipeline reliably standardizes signage into global brand hierarchies without significant error, and the temporal lag design using LBS data accurately captures realized demand without selection or measurement bias.

What would settle it

A ground-truth audit of brand classifications from the VLM-LLM pipeline showing high mismatch rates with actual store signage, or a replication of the time-lagged regression finding no consistent time-specific coefficients for brand clustering and interface quality effects.

Figures

Figures reproduced from arXiv: 2604.19798 by Junyan Yang, Mengyuan Niu, Qiao Wang, Ruizhe Wang, Xinxin Zhuo.

Figure 1
Figure 1. Figure 1: Study area. 4.2 Data Acquisition and Processing Framework To capture the fine-grained texture of street life, we implemented a systematic sampling and acquisition workflow ( [PITH_FULL_IMAGE:figures/full_fig_p007_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Analysis framework [PITH_FULL_IMAGE:figures/full_fig_p009_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Spatiotemporal evolution of dynamic crowd intensity (UV) across four tidal periods for both a weekday [PITH_FULL_IMAGE:figures/full_fig_p009_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Training performance of YOLOv5-seg. (1) Stage 1: VLM Extraction (S1). We employ a pre-trained VLM (Qwen2-VL-7B-Instruct) to transcribe textual information and identify commercial logos from the input images. To minimize model hallucination and ensure deterministic outputs, generation hyperparameters were strictly constrained (temperature = 0.0, top_p = 1.0, max_new_tokens = 64.0, and do_sample = False). Th… view at source ↗
Figure 5
Figure 5. Figure 5: The architecture of the VLM-LLM Brand Decoding Pipeline. [PITH_FULL_IMAGE:figures/full_fig_p010_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: The distribution of variables at the sampling-point level. [PITH_FULL_IMAGE:figures/full_fig_p015_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: The distribution of Commercial Activity at the sampling-point level. [PITH_FULL_IMAGE:figures/full_fig_p016_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: The distribution of Spatial Utilization at the sampling-point level. [PITH_FULL_IMAGE:figures/full_fig_p016_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: The distribution of Physical Environment at the sampling-point level. [PITH_FULL_IMAGE:figures/full_fig_p016_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Spearman correlation heatmap identifying the internal coupling of vitality indicators. [PITH_FULL_IMAGE:figures/full_fig_p017_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Principal Component Analysis results. 6.3 Spatial Diagnosis and Heterogeneity Synthesizing the multi-dimensional indicators via the EWM-TOPSIS framework, we generated a spatial distribution map of SEVI to perform a comprehensive diagnosis of Nanjing’s central area ( [PITH_FULL_IMAGE:figures/full_fig_p018_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: The distribution of SEVI. morphologies (𝑋𝑖,𝑡−1) on real-time pedestrian presence (𝑌𝑖,𝑡), stepping beyond purely descriptive co-occurrences. Overall, this lagged GWR model demonstrates robust predictive power, achieving an average Adjusted 𝑅 2 of 0.66 across the observed temporal spectrum. The temporal evolution of the models’ explanatory power (Adjusted 𝑅 2 ) reveals a profound tidal effect dictated by tr… view at source ↗
Figure 13
Figure 13. Figure 13: Spatiotemporal evolution of the Time-Sliced GWR model’s explanatory power (Adjusted [PITH_FULL_IMAGE:figures/full_fig_p020_13.png] view at source ↗
Figure 14
Figure 14. Figure 14: Temporal evolution of local GWR coefficients for Mall Spillover Vitality and Closure Ratio. [PITH_FULL_IMAGE:figures/full_fig_p021_14.png] view at source ↗
read the original abstract

Micro-scale street-level economic assessment is fundamental for precision spatial resource allocation. While Street View Imagery (SVI) advances urban sensing, existing approaches remain semantically superficial and overlook brand hierarchy heterogeneity and structural recession. To address this, we propose a visual-semantic and field-based spatiotemporal framework, operationalized via the Street Economic Vitality Index (SEVI). Our approach integrates physical and semantic streetscape parsing through instance segmentation of signboards, glass interfaces, and storefront closures. A dual-stage VLM-LLM pipeline standardizes signage into global hierarchies to quantify a spatially smoothed brand premium index. To overcome static SVI limitations, we introduce a temporal lag design using Location-Based Services (LBS) data to capture realized demand. Combined with a category-weighted Gaussian spillover model, we construct a three-dimensional diagnostic system covering Commercial Activity, Spatial Utilization, and Physical Environment. Experiments based on time-lagged geographically weighted regression across eight tidal periods in Nanjing reveal quasi-causal spatiotemporal heterogeneity. Street vibrancy arises from interactions between hierarchical brand clustering and mall-induced externalities. High-quality interfaces show peak attraction during midday and evening, while structural recession produces a lagged nighttime repulsion effect. The framework offers evidence-based support for precision spatial governance.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The manuscript proposes a visual-semantic and field-based spatiotemporal framework for micro-scale street-level economic assessment, operationalized through the Street Economic Vitality Index (SEVI). It integrates instance segmentation of street view imagery for signboards, interfaces, and closures; a dual-stage VLM-LLM pipeline to standardize signage into global brand hierarchies and compute a spatially smoothed brand premium index; Location-Based Services data with temporal lags to capture realized demand; and a category-weighted Gaussian spillover model. These elements form a three-dimensional diagnostic system (Commercial Activity, Spatial Utilization, Physical Environment). Experiments apply time-lagged geographically weighted regression across eight tidal periods in Nanjing and claim to reveal quasi-causal spatiotemporal heterogeneity, with street vibrancy arising from hierarchical brand clustering interacting with mall-induced externalities, high-quality interfaces showing peak attraction midday/evening, and structural recession producing lagged nighttime repulsion.

Significance. If the empirical implementation and quasi-causal interpretations hold after addressing identification concerns, the work would advance urban sensing by moving beyond semantically shallow SVI analysis to incorporate brand hierarchy heterogeneity and dynamic demand signals. The integration of computer vision, language models, and spatially explicit regression offers a potentially replicable template for precision spatial governance, with practical value for resource allocation in commercial districts.

major comments (3)
  1. [Abstract / Experiments] Abstract (final paragraph) and implied experiments section: The claim that time-lagged GWR 'reveals quasi-causal spatiotemporal heterogeneity' is not supported by the described methods. GWR estimates spatially varying associations conditional on covariates; temporal lags address precedence but leave endogeneity (e.g., brand location choices correlated with pre-existing vitality), omitted spatial confounders, and LBS selection bias unaddressed. No instrumental variables, fixed effects, falsification tests, or robustness checks are mentioned to justify moving from 'associated with' to 'produces lagged repulsion effect.'
  2. [Abstract / Methods] Abstract (methods description): The dual-stage VLM-LLM pipeline for standardizing signage into global brand hierarchies is presented without any validation metrics, inter-annotator agreement, error rates, or comparison to manual coding. This is load-bearing for the brand premium index and the subsequent category-weighted Gaussian spillover model; without demonstrated reliability, downstream claims about hierarchical clustering effects cannot be assessed.
  3. [Abstract / SEVI framework] Abstract (SEVI construction): The three-dimensional diagnostic system and its integration of the category-weighted Gaussian spillover model lack explicit equations, parameter definitions, or sensitivity analysis. The abstract supplies no data summaries, sample sizes, R^{2} values, or coefficient tables from the Nanjing regressions, preventing evaluation of the reported tidal-period heterogeneity.
minor comments (2)
  1. [Abstract] The abstract would benefit from a concise quantitative summary (e.g., key coefficient ranges or fit statistics) to allow readers to gauge effect magnitudes before the full text.
  2. [Methods] Notation for the brand premium index and spillover weights should be introduced with a small equation or schematic to improve readability.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive and detailed feedback on our manuscript. We address each major comment point by point below, indicating where revisions will be made to improve clarity, accuracy, and completeness.

read point-by-point responses

  1. Referee: [Abstract / Experiments] Abstract (final paragraph) and implied experiments section: The claim that time-lagged GWR 'reveals quasi-causal spatiotemporal heterogeneity' is not supported by the described methods. GWR estimates spatially varying associations conditional on covariates; temporal lags address precedence but leave endogeneity (e.g., brand location choices correlated with pre-existing vitality), omitted spatial confounders, and LBS selection bias unaddressed. No instrumental variables, fixed effects, falsification tests, or robustness checks are mentioned to justify moving from 'associated with' to 'produces lagged repulsion effect.'

    Authors: We acknowledge that the phrasing 'quasi-causal' overstates the inferential capabilities of time-lagged GWR, which identifies spatially varying associations and temporal precedence but does not resolve endogeneity, omitted spatial confounders, or selection biases. In the revised manuscript, we will replace 'quasi-causal spatiotemporal heterogeneity' with 'spatiotemporal associations and heterogeneity' in the abstract and throughout the text. We will add an explicit limitations paragraph in the discussion section acknowledging these identification challenges and outlining potential future extensions (e.g., IV strategies), while retaining the core empirical findings on heterogeneity across tidal periods. revision: yes

  2. Referee: [Abstract / Methods] Abstract (methods description): The dual-stage VLM-LLM pipeline for standardizing signage into global brand hierarchies is presented without any validation metrics, inter-annotator agreement, error rates, or comparison to manual coding. This is load-bearing for the brand premium index and the subsequent category-weighted Gaussian spillover model; without demonstrated reliability, downstream claims about hierarchical clustering effects cannot be assessed.

    Authors: We agree that explicit validation is essential for the brand standardization pipeline, which underpins the brand premium index. While the full methods section describes the dual-stage VLM-LLM process, we will revise to include a new validation subsection reporting inter-annotator agreement (e.g., Cohen's kappa), error rates on a held-out test set, and direct comparisons against manual expert coding. These metrics will be summarized in the abstract and tied to the reliability of downstream hierarchical clustering results. revision: yes

  3. Referee: [Abstract / SEVI framework] Abstract (SEVI construction): The three-dimensional diagnostic system and its integration of the category-weighted Gaussian spillover model lack explicit equations, parameter definitions, or sensitivity analysis. The abstract supplies no data summaries, sample sizes, R^{2} values, or coefficient tables from the Nanjing regressions, preventing evaluation of the reported tidal-period heterogeneity.

    Authors: Abstract length constraints preclude full equations and tables. The complete manuscript already presents the SEVI equations, category-weighted Gaussian spillover model, and parameter definitions in Section 3, with sensitivity analyses in the appendix. We will revise the abstract to incorporate brief parameter definitions, sample sizes (street segments and tidal periods), and key R^{2} summaries. Full coefficient tables and heterogeneity details across the eight periods will be highlighted in the experiments section with references to supplementary materials. revision: partial

Circularity Check

0 steps flagged

No significant circularity; derivation chain remains self-contained

full rationale

The paper constructs SEVI from distinct inputs (SVI instance segmentation, dual-stage VLM-LLM brand hierarchy extraction, LBS temporal lags, and a category-weighted Gaussian spillover model) before applying time-lagged GWR as an explanatory diagnostic across tidal periods. No equation or step equates the reported spatiotemporal heterogeneity or brand/mall interaction effects to the SEVI components by definition or by renaming fitted parameters as independent predictions. The GWR step produces local coefficient surfaces from the assembled index and covariates rather than recovering its own construction inputs tautologically. External data sources and standard spatial regression methods keep the chain non-circular.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only the abstract is available, so specific free parameters, axioms, and invented entities cannot be extracted in detail. The framework introduces SEVI as a composite index whose construction likely depends on fitted parameters in the spillover model and regression, plus assumptions about AI pipeline accuracy and data representativeness.

pith-pipeline@v0.9.0 · 5534 in / 1378 out tokens · 48999 ms · 2026-05-10T16:51:32.891254+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

35 extracted references · 35 canonical work pages · 1 internal anchor

  1. [1]

    Shili Chen, Wei Lang, and Xun Li. 2022. Evaluating urban vitality based on geospatial big data in Xiamen Island, China. Sage Open12, 4 (2022). doi:10.1177/21582440221134519

    work page doi:10.1177/21582440221134519 2022

  2. [2]

    Tingting Chen, Eddie C. M. Hui, Jiemin Wu, Wei Lang, and Xun Li. 2019. Identifying urban spatial structure and urban vibrancy in highly dense cities using georeferenced social media data.Habitat International89 (2019), 102005. doi:10.1016/j.habitatint.2019.102005

    work page doi:10.1016/j.habitatint.2019.102005 2019

  3. [3]

    1987.Life Between Buildings: Using Public Space

    Jan Gehl. 1987.Life Between Buildings: Using Public Space. Van Nostrand Reinhold, New York

    work page 1987

  4. [4]

    Xixuan Hao, Wei Chen, Yibo Yan, Siru Zhong, Kun Wang, Qingsong Wen, and Yuxuan Liang. 2025. UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction. InProceedings of the AAAI Conference on Artificial Intelligence, Vol. 39. 28061–28069

    work page 2025

  5. [5]

    Sanwei He, Zhen Zhang, Shan Yu, Chang Xia, and Chih-Lin Tung. 2024. Investigating the effects of urban morphology on vitality of community life circles using machine learning and geospatial approaches.Applied Geography167 (2024), 103287. doi:10.1016/j.apgeog.2024.103287

    work page doi:10.1016/j.apgeog.2024.103287 2024

  6. [6]

    Yongming Huang, Mingze Chen, Xiamengwei Zhang, Ryosuke Shimoda, and Ruochen Yang. 2025. Multi-Scale Street Vitality Analytics: A Comprehensive Review of Technologies, Data, and Applications.Buildings15, 21 (2025), 3987. doi:10.3390/buildings15213987

    work page doi:10.3390/buildings15213987 2025

  7. [7]

    1981.Multiple Attribute Decision Making: Methods and Applications

    Ching-Lai Hwang and Kwangsun Yoon. 1981.Multiple Attribute Decision Making: Methods and Applications. Springer- Verlag, New York. doi:10.1007/978-3-642-48318-9

    work page doi:10.1007/978-3-642-48318-9 1981

  8. [8]

    1961.The Death and Life of Great American Cities

    Jane Jacobs. 1961.The Death and Life of Great American Cities. Random House, New York

    work page 1961

  9. [9]

    Yinghong Jiang, Yun Han, Mengyang Liu, and Yu Ye. 2022. Street vitality and built environment features: A data- informed approach from fourteen Chinese cities.Sustainable Cities and Society79 (2022), 103724. doi:10.1016/j.scs. 2022.103724

    work page doi:10.1016/j.scs 2022

  10. [10]

    Glenn Jocher, Ayush Chaurasia, Laughing, et al. 2023. Ultralytics YOLOv8. doi:10.5281/zenodo.7841070

    work page doi:10.5281/zenodo.7841070 2023

  11. [11]

    Bon Woo Koo, Subhrajit Guhathakurta, Nisha Botchwey, and Aaron Hipp. 2023. Can good microscale pedestrian streetscapes enhance the benefits of macroscale accessible urban form? An automated audit approach using Google street view images.Landscape and Urban Planning237 (2023), 104816. doi:10.1016/j.landurbplan.2023.104816

    work page doi:10.1016/j.landurbplan.2023.104816 2023

  12. [12]

    Feng Lan, Xiaoqing Gong, Haizhi Da, and Haizhen Wen. 2020. How do population inflow and social infrastructure affect urban vitality? Evidence from Shanghai, China.Cities100 (2020), 102659. doi:10.1016/j.cities.2020.102659

    work page doi:10.1016/j.cities.2020.102659 2020

  13. [13]

    Qian Li, Caihui Cui, Feng Liu, Qirui Wu, Yadi Run, and Zhigang Han. 2022. Multidimensional urban vitality on streets: Spatial patterns and influence factor identification using multisource urban data.ISPRS International Journal of Geo-Information11, 1 (2022), 2. doi:10.3390/ijgi11010002

    work page doi:10.3390/ijgi11010002 2022

  14. [14]

    Yunqin Li, Nobuyoshi Yabuki, and Tomohiro Fukuda. 2022. Exploring the association between street built environment and street vitality using deep learning methods.Sustainable Cities and Society79 (2022), 103656. doi:10.1016/j.scs.2021. 103656

    work page doi:10.1016/j.scs.2021 2022

  15. [15]

    Bojing Liao and Jie Zhu. 2025. Exploring the causal relationship between campus walkability and affective walking experience: Evidence from 7 major tertiary education campuses in China.Journal of Urban Management14, 3 (2025), 657–674. doi:10.1016/j.jum.2025.01.005

    work page doi:10.1016/j.jum.2025.01.005 2025

  16. [16]

    Microsoft

    Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C. Lawrence Zitnick. 2014. Microsoft COCO: Common objects in context. InEuropean Conference on Computer Vision. Springer, 740–755. doi:10.1007/978-3-319-10602-1_48

    work page doi:10.1007/978-3-319-10602-1_48 2014

  17. [17]

    Zhenxiang Ling, Xianxin Meng, Yingbiao Chen, Qinglan Qian, Junyu Kuang, Xianghua Shi, Yifan Yang, Wentao Chen, Zihao Zheng, and Zhifeng Wu. 2025. Unveiling the hidden vitality of block-structured neighborhoods through a multimodal urban perception and ensemble learning framework.International Journal of Digital Earth18, 1 (2025), 2545581. doi:10.1080/1753...

    work page doi:10.1080/17538947.2025.2545581 2025

  18. [18]

    Liu Liu, Alexandra Kudaeva, Marco Cipriano, Fatimeh Al Ghannam, Freya Tan, Gerard de Melo, and Andres Sevtsuk

    work page

  19. [19]

    MINGLE: VLMs for Semantically Complex Region Detection in Urban Scenes.arXiv preprint arXiv:2509.13484 (2025)

    work page internal anchor Pith review arXiv 2025

  20. [20]

    Ying Long and C. C. Huang. 2019. Does block size matter? The impact of urban design on economic vitality for Chinese cities.Environment and Planning B: Urban Analytics and City Science46, 3 (2019), 406–422. doi:10.1177/2399808317715640

    work page doi:10.1177/2399808317715640 2019

  21. [21]

    Ying Long and Lun Liu. 2016. How green are the streets? An analysis for central city of Beijing using Google Street View. Environment and Planning B: Urban Analytics and City Science43, 6 (2016), 1118–1132. doi:10.1177/0265813515600776

    work page doi:10.1177/0265813515600776 2016

  22. [22]

    Vikas Mehta. 2009. Look closely: The hedonic value of walkable streets.Journal of Urban Design14, 2 (2009), 213–241. doi:10.1080/13574800802670929

    work page doi:10.1080/13574800802670929 2009

  23. [23]

    Nanjing Municipal Bureau of Planning and Natural Resources. 2024. Territorial and Spatial Master Plan of Nanjing (2021–2035). https://ghj.nanjing.gov.cn/ghbz/ztgh/202410/t20241024_4992742.html Accessed: 2025-12-22

    work page 2024

  24. [24]

    Ziyu Peng, Weisheng Lu, Hongda An, Xianhua Xia, Yi Zhang, Fan Xue, and Junjie Chen. 2025. Vision language model (VLM)-enabled street view analytics: a systematic literature review.Engineering, Construction and Architectural , Vol. 1, No. 1, Article . Publication date: April 2026. Diagnosing Urban Street Vitality: A Visual-Semantic and Spatiotemporal Frame...

    work page doi:10.1108/ecam-07-2025-1133 2025

  25. [25]

    Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. 2016. You only look once: Unified, real-time object detection. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 779–788. doi:10.1109/CVPR.2016.91

    work page doi:10.1109/cvpr.2016.91 2016

  26. [26]

    Andres Sevtsuk. 2014. Location and agglomeration of retail and food services: The case of Somerville, MA.Urban Studies51, 16 (2014), 3745–3764. doi:10.1177/0042098013516523

    work page doi:10.1177/0042098013516523 2014

  27. [27]

    Kentaro Wada. 2021. Labelme: Image Polygonal Annotation with Python. https://github.com/wkentaro/labelme

    work page 2021

  28. [28]

    Wang and B

    X. Wang and B. Yuen. 2022. The influence of street network configuration on street vitality in Singapore.Journal of Urban Management11, 2 (2022), 202–215. doi:10.1016/j.jum.2022.01.002

    work page doi:10.1016/j.jum.2022.01.002 2022

  29. [29]

    Yuhan Xu and Xiaosu Ma. 2024. Assessing urban street vitality through visual and auditory perception: A case study of historic urban area in Guangzhou, China.International Review for Spatial Planning and Sustainable Development12, 4 (2024), 57–76. doi:10.14246/irspsd.12.4_57

    work page doi:10.14246/irspsd.12.4_57 2024

  30. [30]

    Fiona Fan Yang, Geng Lin, Yubing Lei, Ying Wang, and Zheng Yi. 2024. Understanding urban vitality from the economic and human activities perspective: A case study of Chongqing, China.Chinese Geographical Science34, 1 (2024), 52–66. doi:10.1007/s11769-023-1402-2

    work page doi:10.1007/s11769-023-1402-2 2024

  31. [31]

    Yu Ye, Daniel Richards, Yi Lu, Xiaoqing Song, Yan Zhuang, Wei Zeng, and Teng Zhong. 2019. Measuring daily accessed street greenery: A human-scale approach for informing better urban planning.Landscape and Urban Planning191 (2019), 103434. doi:10.1016/j.landurbplan.2019.103434

    work page doi:10.1016/j.landurbplan.2019.103434 2019

  32. [32]

    Yang Yue, Yan Zhuang, Anthony G. O. Yeh, Jinyu Xie, Chengling Ma, and Qingquan Li. 2017. Measurements of POI-based mixed use and their relationships with neighbourhood vibrancy.International Journal of Geographical Information Science31, 4 (2017), 658–675. doi:10.1080/13658816.2016.1220561

    work page doi:10.1080/13658816.2016.1220561 2017

  33. [33]

    Anqi Zhang, Weifeng Li, Jiayu Wu, Jian Lin, Jianqun Chu, and Chang Xia. 2021. How can the urban landscape affect urban vitality at the street block level? A case study of 15 metropolises in China.Environment and Planning B: Urban Analytics and City Science48, 5 (2021), 1245–1262. doi:10.1177/2399808320924425

    work page doi:10.1177/2399808320924425 2021

  34. [34]

    Fung, Hui Lin, and Carlo Ratti

    Fan Zhang, Bolei Zhou, Liu Liu, Yu Liu, Hong H. Fung, Hui Lin, and Carlo Ratti. 2019. Social sensing from street-level imagery: A case study in learning spatio-temporal urban mobility patterns.ISPRS Journal of Photogrammetry and Remote Sensing153 (2019), 48–58. doi:10.1016/j.isprsjprs.2019.04.016

    work page doi:10.1016/j.isprsjprs.2019.04.016 2019

  35. [35]

    tidal pattern

    Yuxin Zhu, Dazuo Tian, and Feng Yan. 2020. Effectiveness of Entropy Weight Method in Decision-Making.Mathematical Problems in Engineering2020 (2020), 1–5. doi:10.1155/2020/3564835 .1 Robustness Checks Results To validate the structural consistency of the Mall Spillover Vitality (𝑀𝑉𝑖), we performed robustness checks by varying the maximum spatial threshold...

    work page doi:10.1155/2020/3564835 2020