Richard Souvenir
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Richard Souvenir has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Robert Pless
Computer Science George Washington University Washington DC USA
5 shared publications - Albatool Wazzan
Dept of Computer and Information Science, Temple University, Philadelphia, Pennsylvania, USA
4 shared publications - Stephen MacNeil
Temple University, Philadelphia, PA, USA
4 shared publications - Abby Stylianou
Washington University in St. Louis
3 shared publications - Hong Xuan
George Washington University
3 shared publications - Abby Stylianou
Computer Science Saint Louis University Saint Louis USA
2 shared publications
Latest Publications
- Open Access
- 21 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-15
Comparing Intent Communication Modes for Instruction-based Image Editing
Instruction-based image editing tools rely on users to effectively phrase natural language instructions, yet communicating intent clearly can be challenging. We compare two experimental conditions: Baseline, which represents the conventional interaction pattern in which users respond to an agent and, when necessary, provide additional instructions, and Clarification, in which the agent proactively resolves underspecified user requests by posing brief, targeted follow-up questions prior to performing the editing operation. We conducted a between-subjects user study with 60 participants to examine how these modes influence editing outcomes and user behavior across real-world editing tasks. Based on a mixed-methods analysis, both approaches yielded comparable task performance, completion times, and numbers of edits. However, participants in the Baseline condition reported greater ease of communication and a clearer understanding of the operation of the agent. Analysis of open-ended responses and interaction logs revealed recurring patterns, user strategies, and challenges in the editing process. These findings suggest that, rather than resolving ambiguity before execution, interactive systems can support users just as effectively by allowing intent to evolve through feedback and correction.
- 21 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-15
Open AccessComparing Intent Communication Modes for Instruction-based Image Editing
Instruction-based image editing tools rely on users to effectively phrase natural language instructions, yet communicating intent clearly can be challenging. We compare two experimental conditions: Baseline, which represents the conventional interaction pattern in which users respond to an agent and, when necessary, provide additional instructions, and Clarification, in which the agent proactively resolves underspecified user requests by posing brief, targeted follow-up questions prior to performing the editing operation. We conducted a between-subjects user study with 60 participants to examine how these modes influence editing outcomes and user behavior across real-world editing tasks. Based on a mixed-methods analysis, both approaches yielded comparable task performance, completion times, and numbers of edits. However, participants in the Baseline condition reported greater ease of communication and a clearer understanding of the operation of the agent. Analysis of open-ended responses and interaction logs revealed recurring patterns, user strategies, and challenges in the editing process. These findings suggest that, rather than resolving ambiguity before execution, interactive systems can support users just as effectively by allowing intent to evolve through feedback and correction.
- Open Access
- 13 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 270-276
Perspectives of Financially Disadvantaged Science Majors Pursuing a Computing Minor
- 13 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 270-276
Open AccessPerspectives of Financially Disadvantaged Science Majors Pursuing a Computing Minor
- Open Access
- 24 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 672-684
Evaluating the Impact of AI-Generated Visual Explanations on Decision-Making for Image Matching
- 24 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 672-684
Open AccessEvaluating the Impact of AI-Generated Visual Explanations on Decision-Making for Image Matching
- Open Access
Design and Evaluation of Camera-Centric Mobile Crowdsourcing Applications
The data that underlies automated methods in computer vision and machine learning, such as image retrieval and fine-grained recognition, often comes from crowdsourcing. In contexts that rely on the intrinsic motivation of users, we seek to understand how the application design affects a user's willingness to contribute and the quantity and quality of the data they capture. In this project, we designed three versions of a camera-based mobile crowdsourcing application, which varied in the amount of labeling effort requested of the user and conducted a user study to evaluate the trade-off between the level of user-contributed information requested and the quantity and quality of labeled images collected. The results suggest that higher levels of user labeling do not lead to reduced contribution. Users collected and annotated the most images using the application version with the highest requested level of labeling with no decrease in user satisfaction. In preliminary experiments, the additional labeled data supported increased performance on an image retrieval task.
Open AccessDesign and Evaluation of Camera-Centric Mobile Crowdsourcing Applications
The data that underlies automated methods in computer vision and machine learning, such as image retrieval and fine-grained recognition, often comes from crowdsourcing. In contexts that rely on the intrinsic motivation of users, we seek to understand how the application design affects a user's willingness to contribute and the quantity and quality of the data they capture. In this project, we designed three versions of a camera-based mobile crowdsourcing application, which varied in the amount of labeling effort requested of the user and conducted a user study to evaluate the trade-off between the level of user-contributed information requested and the quantity and quality of labeled images collected. The results suggest that higher levels of user labeling do not lead to reduced contribution. Users collected and annotated the most images using the application version with the highest requested level of labeling with no decrease in user satisfaction. In preliminary experiments, the additional labeled data supported increased performance on an image retrieval task.
- Open Access
- 30 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 404-413
Context or Clutter? Efficiently Matching Objects Across Scenes
Annotated images are required for numerous computer vision tasks; however, the annotation process can be time-consuming for crowdworkers and experts. Previous work has investigated novel interaction techniques and task reformulation to speed up this process; however, there remains a gap in optimizing more complex annotation tasks, such as object matching. In this paper, we explore the impact of varying the amount of context provided to annotators. We hypothesize that reducing the context around the object being matched will improve speed without sacrificing the accuracy of the annotation task. To test this hypothesis, we developed a semi-automated annotation pipeline that pre-processes images to adjust the amount of context shown around an object of interest. We conducted two studies (n = 130, n = 10) to assess the effects of context quantitatively and qualitatively. We found that while the accuracy remained the same, the time spent on the task was significantly reduced when there was less context surrounding the object. However, our qualitative findings revealed multiple scenarios in which context served as a means of guiding the object matching task, and many others in which the distinctiveness of the object guided the matching task and additional context was not needed.
- 30 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 404-413
Open AccessContext or Clutter? Efficiently Matching Objects Across Scenes
Annotated images are required for numerous computer vision tasks; however, the annotation process can be time-consuming for crowdworkers and experts. Previous work has investigated novel interaction techniques and task reformulation to speed up this process; however, there remains a gap in optimizing more complex annotation tasks, such as object matching. In this paper, we explore the impact of varying the amount of context provided to annotators. We hypothesize that reducing the context around the object being matched will improve speed without sacrificing the accuracy of the annotation task. To test this hypothesis, we developed a semi-automated annotation pipeline that pre-processes images to adjust the amount of context shown around an object of interest. We conducted two studies (n = 130, n = 10) to assess the effects of context quantitatively and qualitatively. We found that while the accuracy remained the same, the time spent on the task was significantly reduced when there was less context surrounding the object. However, our qualitative findings revealed multiple scenarios in which context served as a means of guiding the object matching task, and many others in which the distinctiveness of the object guided the matching task and additional context was not needed.
- Open Access
- 10 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 291-302
Comparing Traditional and LLM-based Search for Image Geolocation
Web search engines have long served as indispensable tools for information retrieval; user behavior and query formulation strategies have been well studied. The introduction of search engines powered by large language models (LLMs) suggested more conversational search and new types of query strategies. In this paper, we compare traditional and LLM-based search for the task of image geolocation, i.e., determining the location where an image was captured. Our work examines user interactions, with a particular focus on query formulation strategies. In our study, 60 participants were assigned either traditional or LLM-based search engines as assistants for geolocation. Participants using traditional search more accurately predicted the location of the image compared to those using the LLM-based search. Distinct strategies emerged between users depending on the type of assistant. Participants using the LLM-based search issued longer, more natural language queries, but had shorter search sessions. When reformulating their search queries, traditional search participants tended to add more terms to their initial queries, whereas participants using the LLM-based search consistently rephrased their initial queries.
- 10 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 291-302
Open AccessComparing Traditional and LLM-based Search for Image Geolocation
Web search engines have long served as indispensable tools for information retrieval; user behavior and query formulation strategies have been well studied. The introduction of search engines powered by large language models (LLMs) suggested more conversational search and new types of query strategies. In this paper, we compare traditional and LLM-based search for the task of image geolocation, i.e., determining the location where an image was captured. Our work examines user interactions, with a particular focus on query formulation strategies. In our study, 60 participants were assigned either traditional or LLM-based search engines as assistants for geolocation. Participants using traditional search more accurately predicted the location of the image compared to those using the LLM-based search. Distinct strategies emerged between users depending on the type of assistant. Participants using the LLM-based search issued longer, more natural language queries, but had shorter search sessions. When reformulating their search queries, traditional search participants tended to add more terms to their initial queries, whereas participants using the LLM-based search consistently rephrased their initial queries.
- 6 January 2021
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 129 (4) , 977-997
Evaluation of Inpainting and Augmentation for Censored Image Queries
- 6 January 2021
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 129 (4) , 977-997
Evaluation of Inpainting and Augmentation for Censored Image Queries
- Open Access
TraffickCam: Explainable Image Matching For Sex Trafficking Investigations
Investigations of sex trafficking sometimes have access to photographs of victims in hotel rooms. These images directly link victims to places, which can help verify where victims have been trafficked or where traffickers might operate in the future. Current machine learning approaches give promising results in image search to find the matching hotel. This paper explores approaches to make this end-to-end system better support government and law enforcement requirements, including improved performance, visualization approaches that explain what parts of the image led to a match, and infrastructure to support exporting the results of a query.
Open AccessTraffickCam: Explainable Image Matching For Sex Trafficking Investigations
Investigations of sex trafficking sometimes have access to photographs of victims in hotel rooms. These images directly link victims to places, which can help verify where victims have been trafficked or where traffickers might operate in the future. Current machine learning approaches give promising results in image search to find the matching hotel. This paper explores approaches to make this end-to-end system better support government and law enforcement requirements, including improved performance, visualization approaches that explain what parts of the image led to a match, and infrastructure to support exporting the results of a query.
- Open Access
- 17 July 2019
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 33 (01) , 726-733
Hotels-50K: A Global Hotel Recognition Dataset
Recognizing a hotel from an image of a hotel room is important for human trafficking investigations. Images directly link victims to places and can help verify where victims have been trafficked, and where their traffickers might move them or others in the future. Recognizing the hotel from images is challenging because of low image quality, uncommon camera perspectives, large occlusions (often the victim), and the similarity of objects (e.g., furniture, art, bedding) across different hotel rooms. To support efforts towards this hotel recognition task, we have curated a dataset of over 1 million annotated hotel room images from 50,000 hotels. These images include professionally captured photographs from travel websites and crowd-sourced images from a mobile application, which are more similar to the types of images analyzed in real-world investigations. We present a baseline approach based on a standard network architecture and a collection of data-augmentation approaches tuned to this problem domain.
- 17 July 2019
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 33 (01) , 726-733
Open AccessHotels-50K: A Global Hotel Recognition Dataset
Recognizing a hotel from an image of a hotel room is important for human trafficking investigations. Images directly link victims to places and can help verify where victims have been trafficked, and where their traffickers might move them or others in the future. Recognizing the hotel from images is challenging because of low image quality, uncommon camera perspectives, large occlusions (often the victim), and the similarity of objects (e.g., furniture, art, bedding) across different hotel rooms. To support efforts towards this hotel recognition task, we have curated a dataset of over 1 million annotated hotel room images from 50,000 hotels. These images include professionally captured photographs from travel websites and crowd-sourced images from a mobile application, which are more similar to the types of images analyzed in real-world investigations. We present a baseline approach based on a standard network architecture and a collection of data-augmentation approaches tuned to this problem domain.
- Open Access
Hotels-50K: A Global Hotel Recognition Dataset
Recognizing a hotel from an image of a hotel room is important for human trafficking investigations. Images directly link victims to places and can help verify where victims have been trafficked, and where their traffickers might move them or others in the future. Recognizing the hotel from images is challenging because of low image quality, uncommon camera perspectives, large occlusions (often the victim), and the similarity of objects (e.g., furniture, art, bedding) across different hotel rooms. To support efforts towards this hotel recognition task, we have curated a dataset of over 1 million annotated hotel room images from 50,000 hotels. These images include professionally captured photographs from travel websites and crowd-sourced images from a mobile application, which are more similar to the types of images analyzed in real-world investigations. We present a baseline approach based on a standard network architecture and a collection of data-augmentation approaches tuned to this problem domain.
Open AccessHotels-50K: A Global Hotel Recognition Dataset
Recognizing a hotel from an image of a hotel room is important for human trafficking investigations. Images directly link victims to places and can help verify where victims have been trafficked, and where their traffickers might move them or others in the future. Recognizing the hotel from images is challenging because of low image quality, uncommon camera perspectives, large occlusions (often the victim), and the similarity of objects (e.g., furniture, art, bedding) across different hotel rooms. To support efforts towards this hotel recognition task, we have curated a dataset of over 1 million annotated hotel room images from 50,000 hotels. These images include professionally captured photographs from travel websites and crowd-sourced images from a mobile application, which are more similar to the types of images analyzed in real-world investigations. We present a baseline approach based on a standard network architecture and a collection of data-augmentation approaches tuned to this problem domain.