Journaling is a widely adopted technique, known to improve mental health and well-being by enabling reflection on past events. Large amounts of text in digital journaling applications could hinder the reflection process due to information overload. Abstractive summarization can solve this problem by generating short summaries to quickly glance at and reminisce. In this paper, we present an investigation of the utility of large language models in the context of autobiographical text summarization. We study two approaches to adapt a self-supervised learning (SSL) model to the domain of autobiographical text. One model employs transfer learning using our new autobiographical text summary dataset to fine-tune the SSL model. The second model leverages existing news datasets for high-quality text summarization mixed with our autobiographical summary dataset. We conducted mixed methods research to analyze the performance of these two models. Through objective evaluation using ROUGE and BART scores, we find that both these approaches perform significantly better than the SSL model fine-tuned with only high-quality news datasets, showing the importance of domain adaptation and autobiographical text summary dataset for this task. Secondly, through a subjective evaluation on a crowd-sourcing platform, we evaluated the summaries generated from these models on various quality criteria such as grammar, non-redundancy, structure, and coherence. We found that on all criteria, these summaries score >4 out of 5, and the two models show comparable results. We deployed a proof-of-concept web-based journaling application to assess the practical real-world implications of incorporating abstractive summarization in a digital journaling context. We found that the participants showed a high consensus that the summaries generated by the system captured the main idea of their journal entry (80% of the 75 participants gave a Likert scale rating of ≥5.0 out of 7.0, with the overall mean rating of 5.56 ± 1.32) while being factually correct, and they found it to be a useful feature of a journaling application. Finally, we conducted human evaluation studies to compare the quality of the summaries generated from a commercial tool ChatGPT and mixed distribution fine-tuned SSL model, and present insights into these systems in the context of autobiographical abstractive text summarization. We have made our model, dataset, and subjective evaluation questionnaire openly available to the research community.

Corneal Surface Reflections, or reflections on our eye-surface, have been shown as a valid and more socially acceptable source of information for passive lifelogging applications by prior work. However, automatic analysis of corneal surface reflections from a single RGB camera to support passive lifelogging is not extensively investigated in prior work. To address this, we developed a synthetic and self-supervised learning-based two-stage pipeline of deep learning models to detect objects in these reflections. Our prototype only consists a single RGB camera looking into the eye. We collected data from different users in uncontrolled environments using the prototype and trained our system to detect multiple classes of objects present in a typical office environment. We then evaluated our model in partially-controlled and in-the-wild scenarios. In addition, based on the findings from a follow up user study and prior work, we discuss strengths and weaknesses of our system and using corneal surface reflections for passive lifelogging. Finally, we opensource our source codes and trained checkpoints.

Abstract Retrieval Augment Generation (RAG) is a recent advancement in Open-Domain Question Answering (ODQA). RAG has only been trained and explored with a Wikipedia-based external knowledge base and is not optimized for use in other specialized domains such as healthcare and news. In this paper, we evaluate the impact of joint training of the retriever and generator components of RAG for the task of domain adaptation in ODQA. We propose RAG-end2end, an extension to RAG that can adapt to a domain-specific knowledge base by updating all components of the external knowledge base during training. In addition, we introduce an auxiliary training signal to inject more domain-specific knowledge. This auxiliary signal forces RAG-end2end to reconstruct a given sentence by accessing the relevant information from the external knowledge base. Our novel contribution is that, unlike RAG, RAG-end2end does joint training of the retriever and generator for the end QA task and domain adaptation. We evaluate our approach with datasets from three domains: COVID-19, News, and Conversations, and achieve significant performance improvements compared to the original RAG model. Our work has been open-sourced through the HuggingFace Transformers library, attesting to our work’s credibility and technical consistency.

Despite the increasing popularity of VR games, one factor hindering the industry’s rapid growth is motion sickness experienced by the users. Symptoms such as fatigue and nausea severely hamper the user experience. Machine Learning methods could be used to automatically detect motion sickness in VR experiences, but generating the extensive labeled dataset needed is a challenging task. It needs either very time consuming manual labeling by human experts or modification of proprietary VR application source codes for label capturing. To overcome these challenges, we developed a novel data collection tool, VRhook, which can collect data from any VR game without needing access to its source code. This is achieved by dynamic hooking, where we can inject custom code into a game’s run-time memory to record each video frame and its associated transformation matrices. Using this, we can automatically extract various useful labels such as rotation, speed, and acceleration. In addition, VRhook can blend a customized screen overlay on top of game contents to collect self-reported comfort scores. In this paper, we describe the technical development of VRhook, demonstrate its utility with an example, and describe directions for future research.