Multi-Turn Video Question Answering via Hierarchical Attention Context Reinforced Networks

Zhao, Zhou; Zhang, Zhu; Jiang, Xinghua; Cai, Deng

doi:10.1109/tip.2019.2902106

Cited by 31 publications

(6 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This improves customer service operations and improves the user experience while freeing up human agents to handle more complicated requests (Gao et al, 2019). while also providing sellers with new opportunities to showcase their products to a broader audience (Zhao et al, 2017).…”

Section: Review On the Ai-enhanced Online Marketplacesmentioning

confidence: 99%

Exploring the Role of AI-Enhanced Online Marketplaces in Facilitating Economic Growth: An Impact Analysis on Trade Relations between the United States and Sub-Saharan Africa

Anwansedo,

Gbadebo,

Akinwande

2024

RGSA

View full text Add to dashboard Cite

Objective: The integration of artificial intelligence (AI) in the online marketplace represents a turning point in the development of e-commerce and digital trade. This article investigates the transformative potential of AI-enhanced online marketplaces for trade relations between the United States (US) and Sub-Saharan Africa (SSA), with the aim of reviewing the opportunities presented by the AI in enhancing market access, streamlining trade, and driving economic growth. Method: The methodology adopted for this research comprises of expository discussion. We explore theoretical discussion on AI-enhanced online marketplaces and how it has facilitated online marketplaces for trade relations between the United States (US). Results and Discussion: The article finds that there exists a complex mix of opportunities, challenges, and evolving dynamics in the trading landscape between the US and SSA. Furthermore, the rivalry from global powers as well as the geopolitical considerations impact the trade between US and the SSA countries. Implications: The practical and theoretical implications of this research are discussed. The implication of our finding is that by addressing these key areas, stakeholders can navigate the complexities of trade relations effectively and capitalize on opportunities for mutual prosperity and inclusive economic development between the US and SSA in the digital age. Originality/Value: This study contributes to the literature by highlighting how an AI-enhanced online marketplaces can facilitate economic progress by utilizing it for trade relations between the US and SSA economies. The relevance and value of the paper are evidenced by the findings that if both countries leverage on AI-enhance technologies for effective market access, they can unlock their full potential for growth and development. Recommendations: We suggest that stakeholders should leverage on AI technologies by embracing digital transformation, fostering collaboration, prioritizing market research, addressing infrastructure challenges, and ensuring compliance with ethical practices. Future research can explore other areas of emerging technologies, demonstrate the socio-economic implications of AI, and the framework of regulations on AI.

show abstract

Section: Review On the Ai-enhanced Online Marketplacesmentioning

confidence: 99%

Exploring the Role of AI-Enhanced Online Marketplaces in Facilitating Economic Growth: An Impact Analysis on Trade Relations between the United States and Sub-Saharan Africa

Anwansedo,

Gbadebo,

Akinwande

2024

RGSA

View full text Add to dashboard Cite

show abstract

“…Therefore, Yang et al [65] develop a novel set generation model based on RL, which not only captures the correlations between items, but also reduces the dependence on the item order. Zhao et al [75,76] propose to utilize reinforcement learning for video question answering.…”

Section: Drugsmentioning

confidence: 99%

Interaction-aware Drug Package Recommendation via Policy Gradient

Zheng

Wang

et al. 2023

ACM Trans. Inf. Syst.

View full text Add to dashboard Cite

Recent years have witnessed the rapid accumulation of massive electronic medical records (EMRs), which highly support intelligent medical services such as drug recommendation. However, although there are multiple interaction types between drugs, e.g., synergism and antagonism, which can influence the effect of a drug package significantly, prior arts generally neglect the interaction between drugs or consider only a single type of interaction. Moreover, most existing studies generally formulate the problem of package recommendation as getting a personalized scoring function for users, despite the limits of discriminative models to achieve satisfactory performance in practical applications. To this end, in this paper, we propose a novel end-to-end D rug P ackage G eneration (DPG) framework, which develops a new generative model for drug package recommendation with considering the interaction effect within drugs that affected by patient conditions. Specifically, we propose to formulate the drug package generation as a sequence generation process. Along this line, we first initialize the drug interaction graph based on medical records and domain knowledge. Then, we design a novel message passing neural network to capture the drug interaction, as well as a drug package generator based on a recurrent neural network. In detail, a mask layer is utilized to capture the impact of patient condition, and the deep reinforcement learning technique is leveraged to reduce the dependence on the drug order. Finally, extensive experiments on a real-world dataset from a first-rate hospital demonstrate the effectiveness of our DPG framework compared with several competitive baseline methods.

show abstract

“…Jang et al [38], [39] released a large-scale VideoQA dataset named TGIF-QA and proposed a dual-LSTM based method with both spatial and temporal attention. Later on, some hierarchical attention and co-attention based methods [16], [40], [41], [42], [43] are proposed to learn appearance-motion and question-related multi-modal interactions. Le et al [17] proposed hierarchical conditional relation network (HCRN) to construct sophisticated structures for representation and reasoning over videos.…”

Section: Visual Question Answeringmentioning

confidence: 99%

Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering

Liu¹,

Li²,

Li³

2022

Preprint

View full text Add to dashboard Cite

Existing visual question answering methods tend to capture the spurious correlations from visual and linguistic modalities, and fail to discover the true casual mechanism that facilitates reasoning truthfully based on the dominant visual evidence and the correct question intention. Additionally, the existing methods usually ignore the complex event-level understanding in multi-modal settings that requires a strong cognitive capability of causal inference to jointly model cross-modal event temporality, causality, and dynamics. In this work, we focus on event-level visual question answering from a new perspective, i.e., cross-modal causal relational reasoning, by introducing causal intervention methods to mitigate the spurious correlations and discover the true causal structures for the integration of visual and linguistic modalities. Specifically, we propose a novel event-level visual question answering framework named Cross-Modal Causal RelatIonal Reasoning (CMCIR), which consists of three essential components named causality-aware visual-linguistic reasoning module, spatial-temporal transformer, and visual-linguistic feature fusion module, to achieve robust casuality-aware visual-linguistic question answering. To uncover the causal structures for visual and linguistic modalities, the novel Causality-aware Visual-Linguistic Reasoning (CVLR) module is proposed to collaboratively disentangle the visual and linguistic spurious correlations via elaborately designed front-door and back-door causal intervention modules. To discover the fine-grained interactions between linguistic semantics and spatial-temporal representations, we build a novel Spatial-Temporal Transformer (STT) that builds the multi-modal co-occurrence interactions between visual and linguistic content. To adaptively fuse the causality-ware visual and linguistic features, we introduce a Visual-Linguistic Feature Fusion (VLFF) module that leverages the hierarchical linguistic semantic relations as the guidance to learn the global semantic-aware visual-linguistic representations adaptively. Extensive experiments on large-scale event-level urban dataset SUTD-TrafficQA and three benchmark real-world datasets TGIF-QA, MSVD-QA, and MSRVTT-QA demonstrate the effectiveness of our CMCIR for discovering visual-linguistic causal structures and achieving robust event-level visual question answering.

show abstract

Multi-Turn Video Question Answering via Hierarchical Attention Context Reinforced Networks

Cited by 31 publications

References 34 publications

Exploring the Role of AI-Enhanced Online Marketplaces in Facilitating Economic Growth: An Impact Analysis on Trade Relations between the United States and Sub-Saharan Africa

Exploring the Role of AI-Enhanced Online Marketplaces in Facilitating Economic Growth: An Impact Analysis on Trade Relations between the United States and Sub-Saharan Africa

Interaction-aware Drug Package Recommendation via Policy Gradient

Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering

Contact Info

Product

Resources

About