Understanding Of Intentions Research Articles

Exploring Chinese passenger switching intentions toward airline self-service technology from a push–pull–mooring perspective

PurposeAirline self-service technology (SST) has attracted attention from both the academic and aviation sectors. As the use of SST can reduce airlines’ operating costs, investigating SST usage at airports is particularly important for the aviation sector. The extant literature has explored users’ SST usage intention, but users’ switching intentions from traditional manual counter services to SST is still limited. Therefore, to address this issue, we used the push–pull–mooring (PPM) theoretical framework to develop a research model to explore user switching intention.Design/methodology/approachWe utilized a mixed-methods approach. A qualitative approach (i.e., semistructured interviews) was first employed to recognize and choose the candidate factors. Then, we collected 450 valid responses through an online survey to test the model. The partial least squares method was used for data analysis.FindingsWe found that several push (perceived dissatisfaction and perceived inconvenience), pull (perceived ease of use, perceived usefulness and service process fit), and mooring (personal innovativeness and inertia) factors significantly influence switching intention. Additionally, mooring factors exert contextual effects on the relationships between push and switching intentions and between pull factors and switching intentions.Originality/valueThis study contributes to the literature by further increasing our understanding of user switching intentions regarding SSTs from the PPM perspective and offering guidance for the aviation sector to attract and retain customers.

Practical concepts and intentional understanding: on the lineage of beginning phenomenology

Practical concepts and intentional understanding: on the lineage of beginning phenomenology

User-agnostic adaptation of human locomotion intent: Leveraging Teacher-Student-Learning and ensemble modeling

Wearable robot control in complicated contexts requires an understanding of human locomotion intent and behaviors. However, signals from human–robot interfaces are typically reliant on the user, leading to poor performance of the model trained on training user when applied to new end-point users. This study aims to address this problem by developing a novel Teacher-Student-Learning (TSL) approach using Heterogeneous Ensemble Hypotheses (HEH) to achieve unsupervised user-agnostic adaptation. The motivation behind using the Teacher-Student-Learning architecture is to leverage the diverse features extracted by HEH while maintaining computational efficiency. HEH reduces the difference between labeled training users and unlabeled end-point users by incorporating multiple diverse feature generators to extract a wide range of features, thereby increasing classification accuracy and reducing variance. However, this approach sacrifices efficiency due to the ensemble nature of HEH. To address this trade-off, the knowledge from HEH is distilled into a single network using TSL, ensuring precision and efficiency. The proposed approach is evaluated on two publicly available human locomotion datasets and a 2D moon dataset. Experimental results demonstrate the effectiveness of the proposed method, outperforming all other methods. Tested with three datasets, the proposed method can classify end-point users’ data with an average accuracy of 98.9%, 96.7%, and 96.9% while yielding a low processing time (1 ms). Compared to a benchmark method, the suggested strategy improves the average accuracy by 1.5% and 7.2% for categorizing the target users’ locomotor modes and stabilizes the learning curves. The proposed method represents a significant contribution to the field of human activity recognition and human intent prediction for human–robot interaction systems, enhancing the efficiency and generalization capacity of these systems.

Reframing Communication about Fall Prevention Programs to Increase Older Adults' Intentions to Participate.

Falls and fall-related injuries in community-dwelling older adults are a growing global health concern. Despite effective exercise-based fall prevention programs (FPPs), low enrollment rates persist due to negative connotations associated with falls and aging. This study aimed to investigate whether positive framing in communication leads to a higher intention to participate in an FPP among community-dwelling older adults. We conducted a two-sequence randomized crossover study. We designed two flyers, a standard flyer containing standard terminology regarding FPPs for older adults, and a reframed flyer highlighting fitness and activity by reframing 'fall prevention' as an 'exercise program' and 'old' as 'over 65 years'. With a Mann-Whitney U test, we investigated group differences regarding the intention to participate between the flyers. A sensitivity analysis and subgroup analyses were performed. We conducted qualitative thematic analysis on open-ended answers to gain a deeper understanding of participants' intention to participate. In total, we included 133 participants. Findings indicated a significantly higher intention to participate in the reframed flyer (median = 4; interquartile range = 1-6) compared to the standard flyer (median = 2; interquartile range = 1-4) (p = 0.038). Participants favored more general terms such as 'over 65 years' over 'older adults'. Older adults who were female, not at high fall risk, perceived themselves as not at fall risk, and maintained a positive attitude to aging showed greater receptivity to positively-framed communications in the reframed flyer. Additionally, already being engaged in physical activities and a lack of practical information about the FPP appeared to discourage participation intentions. The results in favor of the reframed flyer provide practical insights for designing and implementing effective (mass-)media campaigns on both (inter)national and local levels, as well as for interacting with this population on an individual basis. Aging-related terminology in promotional materials hinders engagement, underscoring the need for more positive messaging and leaving out terms such as 'older'. Tailored positively framed messages and involving diverse older adults in message development are essential for promoting participation in FPPs across various population subgroups to promote participation in FPPs among community-dwelling older adults.

Psychological factors influencing online booking intentions among resort tourism service users

PurposeThis study examines the psychological factors that directly influence individuals’ intentions to book or arrange reservations through resort hotel websites within the context of the Unified Theory of Acceptance and Use of Technology (UTAUT). Specifically, this study focused on identifying and understanding the key drivers of online purchase intentions, including performance expectancy, effort expectancy, social influence and facilitating conditions within the UTAUT model.Design/methodology/approachThis study used the UTAUT as a theoretical framework. A quantitative research approach was adopted and data were collected through surveys using a five-point Likert scale. The sample consisted of 270 participants, selected through purposive sampling. Data analysis was performed using Smart PLS software.FindingsThe results indicate that performance and effort expectancy significantly influence online purchase intentions. However, social influence did not significantly affect online purchase intention. By contrast, facilitating conditions significantly and positively influence online purchase intention.Practical implicationsThese findings have practical implications for hotel managers and marketers. Emphasizing performance, effort expectations and facilitating conditions can improve customer perceptions of website usefulness and directly increase their intention to book. The limited impact of social influence suggests the need to focus less on social recommendations or endorsements in online marketing efforts and prioritize individual factors and objective information.Originality/valueThis study contributes to the field of technology and tourism by examining the psychological factors that directly influence users’ intention to purchase from resort hotel websites. This extends the understanding of online purchase intentions in the context of resort tourism and highlights the importance of facilitating conditions. This study also partially confirms the applicability of the UTAUT model in this domain and provides insights for future research on online purchase intentions in resort tourism.

Enhancing Chatbot Intelligence Through Narrative Memory Structures

Through the use of narrative memory structures—a cutting-edge technique intended to provide chatbots context awareness and conversational coherence—we sought to improve the intelligence of chatbots. We carefully designed our process with the goal of immediately incorporating narrative data into the chatbot's memory architecture. In order to find narrative patterns, this required evaluating and classifying previous exchanges. The narrative patterns were then saved and used to guide the chatbot's answers. The incorporation of narrative memory structures into the chatbot resulted in a significant improvement in conversational coherence and relevance, as per our study's key findings. Through the use of its narrative memory, which stores earlier encounters, the chatbot shown an impressive capacity to sustain the conversation's flow and provide more contextually relevant replies. In addition, the chatbot demonstrated improved understanding of human intentions, correctly identifying underlying motives and preferences. In addition, comments produced by integrating narrative memory structures were highly customized in addition to being accurate. By utilizing the extensive history of previous exchanges, the chatbot was able to customize replies to each user's unique situation, building a closer relationship and rapport with them. All things considered; our study highlights how narrative memory processes can revolutionize chatbot intelligence. We can improve chatbots' conversational capabilities and enable more meaningful human-computer interactions by giving them the capacity to extract narrative information from previous conversations. This opens the door to a new era of chatbot designs that put the needs of users, contextuality, and empathy first, changing the game for conversational AI in the process.

Sentiment analysis of online reviews of energy-saving products based on transfer learning and LBBA model

With the exacerbation of global climate change and the growing environmental awareness among the general public, the concept of green consumption has gained significant attention across various sectors of society. As a representative example of green consumer products, energy-saving products play a crucial role in the timely realization of dual carbon goals. However, an analysis of online comments regarding energy-saving products reveals that the majority of these products still exhibit shortcomings in terms of efficacy, noise level, cost-effectiveness, and particularly, energy-saving appliances. This study focuses on the user-generated online comments data from the Taobao e-commerce platform for Grade 1 energy-saving refrigerators. By employing text mining techniques, the study aims to extract the essential information and sentiments expressed in the comments, in order to explore the consumption characteristics of Grade 1 energy-saving refrigerators. Moreover, the LBBA (LDA-Bert-BiLSTM-Attention) model is utilized to investigate the consumer topics of interest and emotional features. Initially, the LDA model is adopted to identify the attributes and weights of consumer concerns. Subsequently, the Bert model is pre-trained with the online comment data, and combined with the BiLSTM algorithm and Attention mechanism to predict sentiment categories. Finally, a transfer learning approach is utilized to determine the sentiment inclination of user-generated online comments and to identify the primary driving factors behind each sentiment category. This research employs sentiment analysis on online comments data regarding energy-saving products to uncover consumer sentiment attributes and emotional characteristics. It provides decision-makers with a comprehensive and systematic understanding of public consumption intentions, offering decision support for the efficient operation and management of the energy-saving product market.

Examining the impact of pharmacist professionalism and celebrity endorsers on dietary supplement purchase intention: the moderating role of product knowledge

PurposeThis study aims to explore how consumers’ purchase intentions concerning dietary supplements are affected by two pivotal factors: pharmacist professionalism and celebrity endorser attractiveness. In addition, this study investigates the moderating role of consumers’ awareness of product knowledge about dietary supplements in the relationship between brand trust and purchase intention.Design/methodology/approachThe research data was collected through online questionnaires from a convenience sample of 340 individuals residing in Taiwan. The research model, consisting of four hypotheses, was formulated based on a literature review. The partial least squares structural equation modeling technique was used for data analysis.FindingsThe findings indicate positive effects of both pharmacist professionalism and celebrity endorser attractiveness on dietary supplement brand trust. The results also suggest a significant impact of brand trust on purchase intention. Finally, product knowledge significantly moderates the relationship between brand trust and purchase intention.Practical implicationsThe findings from this study provide valuable insights for marketers, pharmacists and practitioners about the drivers of consumers’ dietary supplement purchase behavior. It will enable marketers to develop better strategies for the dietary supplement market segment.Originality/valueThis paper has made a significant contribution to the understanding of consumer buying intentions toward dietary supplements, addressing a gap in the literature. First, unlike previous research, this study considers both pharmacist professionalism and celebrity endorser attractiveness in the research model, effectively bridging this gap. Furthermore, this study identifies the pivotal role of brand trust as a critical factor in enhancing consumers’ purchase intentions toward dietary supplements, offering valuable insights for dietary supplement companies regarding consumer purchase decision-making.

A Helpful Measure to Measure Help: The Construction and Validation of the Intergroup Giving and Intergroup Acting in Favor of Refugees Scale (IGIAF)

Since 2015, Europe has experienced two important influxes of vulnerable migrants, refugees, and asylum seekers. Despite heterogenous reactions within and across countries, acts of humanitarianism and solidarity have occurred in a diverse range of behaviors. Given the particularities of Intergroup Helping in favor of refugees, a more nuanced understanding of intentions to engage in helping behaviors would enrich theoretical and applied research. We developed and validated a scale of Intergroup Helping in favor of refugees, that covers the two dimensions of help, i.e., Intergroup Giving (alleviating the suffering of others) and Intergroup Acting (addressing injustices and inequalities). Following scale construction practices, we proceeded in three phases. First, we identified and defined our domains of interest, and proceeded to collect representative helping behaviors, using secondary data of semi-structured interviews on volunteers. These behaviors were pre-tested. Then, across two studies, we examined the scale’s reliability, dimensionality, and validity qualities. Study 1 was distributed among a student sample at two time-points. Results yielded robust internal consistency, test-retest reliability, and predictive validity, and displayed preliminary evidence of the bidimensional structure. Study 2 was distributed among a non-student sample and supported the bidimensional structure of the scale. This research demonstrates that Intergroup Helping intentions in favor of refugees can be classified into Intergroup Giving and Intergroup Acting behaviors and offers a predictive tool to investigate these behaviors in an intergroup context.

MBCFNet: A Multimodal Brain–Computer Fusion Network for human intention recognition

Accurate recognition of human intent is crucial for effective human–computer speech interaction. Numerous intent understanding studies were based on speech-to-text transcription, which often overlook the influence of paralinguistic cues (such as speaker’s emotion, attitude, etc.), leading to misunderstandings, especially when identical textual content conveys multiple intents by means of different paralinguistic information. Considering that interaction intent is produced from the human brain, we propose a novel Multimodal Brain–Computer Fusion Network (MBCFNet) to discriminate the different intents carried by the identical textual information, in which the acoustic-textual representation was adapted by brain functional information through a cross-modal transformer. In the output module, a joint multi-task learning method was used to optimize both the primary task of intent recognition and the auxiliary task of emotion recognition of the speaker. To evaluate the model performance, we constructed a multimodal dataset CMSLIU that consists of acoustic, textual, and electroencephalograph (EEG) data of the same Chinese texts with varying intents. Experimental results on the self-constructed dataset indicate that the proposed model achieves state-of-the-art (SOTA) performance compared with other competing models. Ablation experiment results reveal that the model performance declines without information from EEG or audio modality, and also when the auxiliary task of emotion recognition is removed. All these results suggest the effectiveness of the proposed information fusion strategy in spoken language intent recognition and the brain–computer information fusion idea can also be extended to other similar fields.

Stimularea intenţiilor antreprenoriale în contextul şcolar

This article explores the multifaceted concept of entrepreneurial intention within the context of entrepreneurial behavior, grounded in the theory of planned behavior proposed by Ajzen, highlighting the significance of attitude, societal norms, and perceived behavioral control in shaping entrepreneurial intentions. We underscore the necessity of a comprehensive understanding of intention, particularly in the entrepreneurial domain, considering its core components, determinants, and practical implications. We emphasize the crucial role of educational systems in fostering entrepreneurial intentions and propose specific strategies for enhancing entrepreneurial intentions in academic settings, integrating goal setting, positive attitudes, self-efficacy, visualization, implementation intentions, and social support. These educational strategies are presented as essential tools for cultivating the entrepreneurial spirit and capabilities among students, preparing them for future entrepreneurial pursuits. This comprehensive exploration provides valuable insights for educators, policymakers, and aspiring entrepreneurs, highlighting the dynamic interplay between individual intentions, educational frameworks, and the broader economic environment.

Enticing attributes of consumers' purchase intention to use online food delivery applications (OFDAs) in a developing country

PurposeOnline food delivery applications (OFDAs) provide an expedient platform, and consumers’ access to food has been drastically altered, especially during and after the COVID-19 pandemic. This study aimed to completely explore the attributes that influence consumers' purchase intention and how an app's aesthetics can evoke feelings that predict continuous usage intentions for OFDAs. The food industry, especially restaurants, heavily relies on mobile technology to facilitate critical online food delivery during the pandemic crisis.Design/methodology/approachThe data for this study are gathered from 477 food consumers located in the federal capital territory (FCT) of Islamabad, Pakistan, through convenient sampling by developing a self-administrated online survey. SmartPLS is used for structural equation modeling to test the proposed research model and perform bootstrapping and algorithmic analysis.FindingsOur findings revealed that perceived value positively predicted consumers’ purchase intentions. Moreover, perceived value mediates the association of information quality, familiarity, time-saving, usability and reputation with purchase intentions and fear of COVID-19 moderates the relationship between perceived value and purchase intention.Practical implicationsThis research work has significant implications for researchers, web developers, app designers, delivery services, restaurants and other enterprises as it demonstrates the importance of aesthetically pleasing OFDAs in eliciting positive emotions and bolstering consumers’ intentions to continue using the app for efficient food delivery services.Originality/valueThis study expanded the application of the technology acceptance model (TAM) and attention, interest, desire and action (AIDA) by examining consumers’ purchase intentions in the context of OFDAs. Further, the successful utilization of TAM enhanced the understanding of consumer perceptions and behavioral intentions about the usage of OFDAs.

Factors impacting online shopping in India: an empirical approach to extending UTAUT2 with the digital payment mode and attitudes toward technology

PurposeIn keeping with global developments rendering online shopping as an emerging trend among consumers, the present study extends the unified theory of use and acceptance of technology (UTAUT2) comprising the digital payment mode (DPM) as a new driver of online shopping and with the mediation of attitudes toward technology (ATTs) to gauge a better and deeper understanding of behavioral intention (BI).Design/methodology/approachThis study used a survey instrument with snowball sampling from 600 consumers in northern India. Partial least squares structural equation modeling was used to find the association between drivers using UTUAT2, along with DPM and ATTs. The data were divided into a test group (20%) and validated through a training group (80%).FindingsDPM was shown to be directly associated with BI. The mediation of ATTs was also validated through the model. The predictability of the model was 67.5% for the test group (20%) and 69.6% for the training group (80%). The results also indicated that facilitating conditions is a critical driver of BI.Originality/valueThis study enhances the understanding of the roles that DPM and ATTs play in BI during online shopping, suggesting that Indian managers need to adopt DPM as a support service to make online shopping a worthwhile experience.

Do Long Commutes Discourage Fertility Intentions Among Young Public Housing Renters in Guangzhou, China?

There are longstanding international housing policy concerns about the well-being and satisfaction of public housing residents and other low-income households. However, little is known about whether the location of public housing requires such lengthy commutes that it retards their fertility intentions. As a result, this study aims to examine the relationship between long commutes and the fertility intentions of young public housing residents and the underlying mechanism linking them. Based on data from the 2022 Public Housing Survey in Guangzhou, China, the results show that long commutes can weaken the intention to have children among young public housing residents. However, this effect is only found to be significant for the self-employed, part-time workers, and those working in the private sector, not for those working in the public sector. Moreover, the effects turn out to be more pronounced for those who commute by private car and active transportation than those who take public transportation. Finally, this study reveals that residential satisfaction mediates the nexus between long commutes and fertility intentions. This study makes an important step in advancing the scholarly understanding of the differential fertility intentions as a result of the spatial mismatch.

THE APPLICATION OF SOCIAL LEARNING THEORY IN PREDICTING THE ANTECEDENTS OF SOCIAL ENTREPRENEURIAL INTENTION

This study analyzes the influence of self-efficacy, role models, and attitudes toward social entrepreneurship on social entrepreneurial intention. It also examines the moderating role of role models in the relationship between self-efficacy and social entrepreneurial intention. This study uses a structural equation model to test five hypotheses. It relies on primary data collected through questionnaires distributed to 114 students from various Indonesian universities. These respondents, identified through convenience sampling, had all learned social entrepreneurship at their university. This study found that self-efficacy positively affects social entrepreneurial intention; role models also positively influence social entrepreneurial intention and attitude toward social entrepreneurship; and attitude toward social entrepreneurship positively impacts social entrepreneurial intention. Role models do not moderate the relationship between self-efficacy and social entrepreneurial intention. The originality of this research lies in its novel adaptation of social learning theory and social cognitive career theory to understand social entrepreneurial intention. As such, this study adds to the theoretical understanding of social entrepreneurial intention, which has been intensively studied using the theory of planned behavior.

Disease-State Understanding and Experience of Patients Receiving Continuous Intravenous Inotropic Support as Palliative Therapy: A Multicenter Survey.

Background: The use of continuous intravenous inotropic support (CIIS) as palliative therapy in patients with advanced heart failure (HF) has increased over the past decade. CIIS improves New York Heart Association (NYHA) functional class but does not impact survival. Objective: The objective of this study was to examine patients' understanding of the therapeutic intent of CIIS, prognostic awareness, and quality of life with CIIS. Design: We conducted a prospective, cross-sectional, multicenter study of patients with advanced HF receiving CIIS as palliative therapy between 2020 and 2022. Settings/Subjects: An investigator-developed survey instrument was administered to outpatients on CIIS in the United States via telephone. Measurements: Survey data were analyzed using descriptive and inferential statistics. Results: Forty-eight patients, 63% male, 81% African American/Black, with a mean age of 68.9 (standard deviation 12.3) years, participated in this study. The majority of patients responded that they expected CIIS to make them feel better (79%) and increase longevity (75%), but few expected that CIIS would cure their HF (19%). Patients described their overall quality of life on CIIS as not better/worse (19%), somewhat better (46%), and significantly better (35%) and reported high treatment satisfaction (87% were at least somewhat satisfied). Conclusions: In this study, patients report improved quality of life with CIIS as palliative therapy. Patients on CIIS as palliative therapy expected increased survival on CIIS, which is incongruent with current evidence. Further studies on how we can improve care processes so that patients have accurate prognostic and disease-state awareness, and receive goal concordant care, are warranted.

The Impact of the Entrepreneurial Environment on Vietnamese Tourism Students' Entrepreneurial Intention

Purpose: Based on Social and Contextual cognitive theory, this study examines the impact of the entrepreneurial environment on the entrepreneurial intentions of students majoring in tourism in Vietnam. Design/methodology/approach: To standardize the conceptual framework of the study, the author began to use the qualitative research method to build hypotheses, then used the quantitative research method to conduct evaluation and assessment, and calculated the sample of the study with the SPSS software version 25. The study was conducted in the form of online survey research on the sample of 275 undergraduate students of tourism and hospitality management in 7 universities in Vietnam. Findings: The findings show that all six hypotheses of the study are accepted, and they have a positive impact on Vietnamese tourism students' entrepreneurial intention. Among them, the political environment is the most influential. Research limitations/implications: Despite efforts to standardize the conceptual framework, the complexity of the entrepreneurial environment may have led to incomplete consideration of relevant variables. The study primarily examined the impact of the entrepreneurial environment on intentions, not behaviors or outcomes, leaving room for future research to conduct a more comprehensive examination of the entrepreneurial process. These limitations offer opportunities for future research to enhance understanding of the intricate relationship between the entrepreneurial environment and intentions among tourism students in Vietnam. Originality/value: The research contributes to the understanding of entrepreneurial intentions among Vietnamese tourism students and provides practical insights for educators, policymakers, and industry stakeholders. Its focus on the entrepreneurial environment and application of relevant theoretical frameworks position it as a meaningful contribution to the fields of entrepreneurship and tourism education.

The Effectiveness of a Cell Phone eHealth App in Changing Knowledge, Stigmatizing Attitudes, and Intention to Seek Help Associated With Obsessive-Compulsive Disorder: Pilot Questionnaire Study.

Obsessive-compulsive disorder (OCD) is a disabling disorder associated with high interference in people's lives. However, patients with OCD either do not seek help or delay seeking help. Research suggests that this could be explained by poor mental health literacy about the disorder and the associated stigma. This study aims to evaluate the feasibility, acceptability, and preliminary effectiveness of a mental health mobile app, esTOCma, developed to improve knowledge about OCD and its treatment, increase help-seeking intention, and reduce stigmatizing attitudes and social distance associated with OCD. We used preintervention, postintervention, and 3-month follow-up assessments in this single-arm pilot intervention. Overall, 90 participants were recruited from the community using the snowball sampling method. We used esTOCma to defeat the "stigma monster" over the course of 10 missions. The participants completed the sociodemographic information and Obsessive-Compulsive Inventory-Revised at preassessment and an acceptability questionnaire at postassessment. All other measures were completed at the preassessment, postassessment, and 3-month follow-up (ie, the Spanish Mental Illness Stigma Attribution Questionnaire-27, the General Help-Seeking Questionnaire, the Social Distance Scale, and the Mental Health Literacy Questionnaire). Of the 90 participants from the community that were assessed for eligibility, 86% (n=78) were allocated to intervention. Of these 78 participants, 79% (n=62) completed the game and answered the postintervention assessment (completer group). Overall, 69% (43/62) of the participants also completed the 3-month follow-up assessment. The participants completing the study were older (P=.003) and had a higher baseline knowledge of OCD (P=.05). The participants took an average of 13.64 (SD 10.50) days to complete the intervention, including the pre- and postassessments. The participants spent an average of 4.56 (SD 3.33) days completing the 10 missions included in the app. Each mission took a mean of between 2 (SD 3.01) and 9.35 (SD 3.06) minutes. The app was rated as useful or very useful by the vast majority of participants 90% (56/62). Moreover, 90% (56/62) of the participants reported that they had learned or learned a lot, and 98% (61/62) of the participants reported that they would recommend the app to a friend. Repeated measures ANOVA (43/62, 69%) showed that after the intervention participants showed an increased knowledge of mental health and intention to seek help as well as fewer stigmatizing attitudes and less social distance. Preliminary data show that esTOCma is a feasible and acceptable app, and after completing its 10 missions, there is an increase in the understanding of OCD and help-seeking intention along with a decrease in the social stigma and social distance associated with OCD that lasts for at least 3 months. The results support the potential of technology-based interventions to increase the intention to seek help and reduce the stigma associated with OCD. A larger, community-controlled study is also recommended.

AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head

Large language models (LLMs) have exhibited remarkable capabilities across a variety of domains and tasks, challenging our understanding of learning and cognition. Despite the recent success, current LLMs are not capable of processing complex audio information or conducting spoken conversations (like Siri or Alexa). In this work, we propose a multi-modal AI system named AudioGPT, which complements LLMs (i.e., ChatGPT) with 1) foundation models to process complex audio information and solve numerous understanding and generation tasks; and 2) the input/output interface (ASR, TTS) to support spoken dialogue. With an increasing demand to evaluate multi-modal LLMs of human intention understanding and cooperation with foundation models, we outline the principles and processes and test AudioGPT in terms of consistency, capability, and robustness. Experimental results demonstrate the capabilities of AudioGPT in solving 16 AI tasks with speech, music, sound, and talking head understanding and generation in multi-round dialogues, which empower humans to create rich and diverse audio content with unprecedented ease. Code can be found in https://github.com/AIGC-Audio/AudioGPT

Intentional Evolutionary Learning for Untrimmed Videos with Long Tail Distribution

Human intention understanding in untrimmed videos aims to watch a natural video and predict what the person’s intention is. Currently, exploration of predicting human intentions in untrimmed videos is far from enough. On the one hand, untrimmed videos with mixed actions and backgrounds have a significant long-tail distribution with concept drift characteristics. On the other hand, most methods can only perceive instantaneous intentions, but cannot determine the evolution of intentions. To solve the above challenges, we propose a loss based on Instance Confidence and Class Accuracy (ICCA), which aims to alleviate the prediction bias caused by the long-tail distribution with concept drift characteristics in video streams. In addition, we propose an intention-oriented evolutionary learning method to determine the intention evolution pattern (from what action to what action) and the time of evolution (when the action evolves). We conducted extensive experiments on two untrimmed video datasets (THUMOS14 and ActivityNET v1.3), and our method has achieved excellent results compared to SOTA methods. The code and supplementary materials are available at https://github.com/Jennifer123www/UntrimmedVideo.