• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.191-204
• /
• 2021

Visual Question Answering (VQA) and image captioning are tasks that require understanding of the features of images and linguistic features of text. Therefore, co-attention may be the key to both tasks, which can connect image and text. In this paper, we propose a model to achieve high performance for VQA by image caption generated using a pretrained standard transformer model based on MSCOCO dataset. Captions unrelated to the question can rather interfere with answering, so some captions similar to the question were selected to use based on a similarity to the question. In addition, stopwords in the caption could not affect or interfere with answering, so the experiment was conducted after removing stopwords. Experiments were conducted on VQA-v2 data to compare the proposed model with the deep modular co-attention network (MCAN) model, which showed good performance by using co-attention between images and text. As a result, the proposed model outperformed the MCAN model.

• 한국정보컨버전스학회:학술대회논문집
• /
• 2008.06a
• /
• pp.53-56
• /
• 2008

This paper reports on the ACQA(Animated agent for Conversational Question Answering) project conducted at LIMSI. The aim is to design an expressive animated conversational agent(ACA) for conducting research along two main lines: 1/ perceptual experiments(eg perception of expressivity and 3D movements in both audio and visual channels): 2/ design of human-computer interfaces requiring head models at different resolutions and the integration of the talking head in virtual scenes. The target application of this expressive ACA is a real-time question and answer speech based system developed at LIMSI(RITEL). The architecture of the system is based on distributed modules exchanging messages through a network protocol. The main components of the system are: RITEL a question and answer system searching raw text, which is able to produce a text(the answer) and attitudinal information; this attitudinal information is then processed for delivering expressive tags; the text is converted into phoneme, viseme, and prosodic descriptions. Audio speech is generated by the LIMSI selection-concatenation text-to-speech engine. Visual speech is using MPEG4 keypoint-based animation, and is rendered in real-time by Virtual Choreographer (VirChor), a GPU-based 3D engine. Finally, visual and audio speech is played in a 3D audio and visual scene. The project also puts a lot of effort for realistic visual and audio 3D rendering. A new model of phoneme-dependant human radiation patterns is included in the speech synthesis system, so that the ACA can move in the virtual scene with realistic 3D visual and audio rendering.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.359-362
• /
• 2020

본 연구에서는 설명 문장 생성을 통한 해석 가능한 시각적 질의응답 모델을 설계하고 학습 방법을 제시한다. 설명 문장은 시각적 질의응답 모델이 응답을 예측하는 데에 필요한 이미지 및 질문 정보와 적절한 논리적인 정보의 조합 및 정답 추론 과정이 함의되어 있을 것으로 기대한다. 설명 문장 생성 과정이 포함된 시각적 질의응답의 기본적인 모델을 기반으로 여러 가지 학습방법을 통해 설명 문장 생성 과정과 응답 예측 과정간의 상호관계를 분석한다. 이러한 상호작용을 적극적으로 활용할 수 있는 보다 개선 시각적 질의응답 모델을 제안한다. 또한 학습한 결과를 바탕으로 설명 문장의 특성을 활용하여 시각적 질의응답 추론 과정을 개선함으로써 시각적 질의응답 모델의 발전 방향을 논의한다. 본 실험을 통해서 응답 예측에 적절한 설명 문장을 제시하는 해석 가능한 시각적 질의응답 모델을 제공한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.749-752
• /
• 2021

오늘날 인공지능(Artificial Intelligence, AI) 분야에서 가장 구현하기 어려운 분야 중 하나는 추론이다. 근래 추론 분야에서 영상과 언어가 결합한 다중 모드(Multi-modal) 환경에서 영상 기반의 질의 응답(Visual Question Answering, VQA) 과업에 대한 AI 모델이 발표됐다. 얼마 지나지 않아 VQA 모델의 성능을 개선한 GVQA(Grounded Visual Question Answering) 모델도 발표됐다. 하지만 아직 GVQA 모델도 완벽한 성능을 내진 못한다. 본 논문에서는 GVQA 모델의 성능 개선을 위해 VCC(Visual Concept Classifier) 모델을 ViT-G(Vision Transformer-Giant)/14로 변경하고, ACP(Answer Cluster Predictor) 모델을 GPT(Generative Pretrained Transformer)-3으로 변경한다. 이와 같은 방법들은 성능을 개선하는 데 큰 도움이 될 수 있다고 사료된다.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.12
• /
• pp.485-496
• /
• 2018

So far, the deep learning, a field of artificial intelligence, has achieved remarkable results in solving problems from unstructured data. However, it is difficult to comprehensively judge situations like humans, and did not reach the level of intelligence that deduced their relations and predicted the next situation. Recently, deep neural networks show that artificial intelligence can possess powerful relational reasoning that is core intellectual ability of human being. In this paper, to analyze and observe the performance of Relation Networks (RN) among the neural networks for relational reasoning, two types of RN-based deep neural network models were constructed and compared with the baseline model. One is a visual question answering RN model using Sort-of-CLEVR and the other is a text-based question answering RN model using bAbI task. In order to maximize the performance of the RN-based model, various performance improvement experiments such as hyper parameters tuning have been proposed and performed. The effectiveness of the proposed performance improvement methods has been verified by applying to the visual QA RN model and the text-based QA RN model, and the new domain model using the dialogue-based LL dataset. As a result of the various experiments, it is found that the initial learning rate is a key factor in determining the performance of the model in both types of RN models. We have observed that the optimal initial learning rate setting found by the proposed random search method can improve the performance of the model up to 99.8%.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.364-366
• /
• 2018

Visual Question Answering(VQA)은 주어진 이미지와 질문에 대해 알맞은 정답을 찾는 기술이다. VQA는 어린이 학습, 인공지능 비서 등 여러 분야에 활용할 수 있는 중요한 기술이다. 그러나 관련된 한국어 데이터를 확보하기 힘든 이유로 한국어를 이용한 연구는 이루어지지 못하고 있다. 본 논문에서는 기존 영어 VQA 데이터를 한글로 번역하여 한국어 VQA 데이터로 사용하며, 이미지 정보와 질문 정보를 적절히 조절할 수 있는 Gate를 한국어 VQA에 적용한다. 실험 결과, 본 논문에서 제안한 모델이 영어 및 한국어 VQA 데이터에서 다른 모델보다 더 좋은 성능을 보였다.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.3
• /
• pp.91-100
• /
• 2020

Unlike the existing Visual Question Answering(VQA) problems, the new Visual Commonsense Reasoning(VCR) problems require deep common sense reasoning for answering questions: recognizing specific relationship between two objects in the image, presenting the rationale of the answer. In this paper, we propose a novel deep neural network model, KG_VCR, for VCR problems. In addition to make use of visual relations and contextual information between objects extracted from input data (images, natural language questions, and response lists), the KG_VCR also utilizes commonsense knowledge embedding extracted from an external knowledge base called ConceptNet. Specifically the proposed model employs a Graph Convolutional Neural Network(GCN) module to obtain commonsense knowledge embedding from the retrieved ConceptNet knowledge graph. By conducting a series of experiments with the VCR benchmark dataset, we show that the proposed KG_VCR model outperforms both the state of the art(SOTA) VQA model and the R2C VCR model.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.468-472
• /
• 2020

시각적 질의응답(Visual Question Answering, VQA)은 주어진 이미지에 연관된 다양한 질문에 대한 올바른 답변을 예측하는 기술이다. 해당 기술은 컴퓨터 비전-자연어 처리 연구분야에서 활발히 연구가 진행되고 있으며, 질문의 의도를 정확히 파악하고, 주어진 이미지에서 관련 단서 정보를 찾는 것이 중요하다. 또한, 서로 이질적인 특성을 지닌 정보(이미지 객체, 객체 위치, 질문)를 통합하는 과정도 중요하다. 본 논문은 질문의 의도에 알맞은 정보를 효율적으로 사용하기 위해 멀티 모달 입력 이미지 객체, 객체 위치, 질문)에 대한 Multi-modal Message Aggregation (MMA) 제안하며 이를 통해 한국어 시각적 질의응답 KVQA에서 다른 모델보다 더 좋은 성능을 확인하였다.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.51 no.5
• /
• pp.44-56
• /
• 2023

This research explores the enhancement of park operation and management by analyzing the changing demands of park users. While traditional methods depended on surveys, there has been a recent shift towards utilizing social media data to understand park usage trends. Notably, most research has focused on text data from social media, overlooking the valuable insights from image data. Addressing this gap, our study introduces a novel method of assessing park usage using social media image data and then applies it to actual city park evaluations. A unique image analysis tool, built on Visual Question Answering (VQA) deep learning technology, was developed. This tool revealed specific city park details such as user demographics, behaviors, and locations. Our findings highlight three main points: (1) The VQA-based image analysis tool's validity was proven by matching its results with traditional text analysis outcomes. (2) VQA deep learning technology offers insights like gender, age, and usage time, which aren't accessible from text analysis alone. (3) Using VQA, we derived operational and management strategies for city parks. In conclusion, our VQA-based method offers significant methodological advancements for future park usage studies.

• Electronics and Telecommunications Trends
• /
• v.38 no.6
• /
• pp.1-11
• /
• 2023

Large language models seem promising for handling reasoning problems, but their underlying solving mechanisms remain unclear. Large language models will establish a new paradigm in artificial intelligence and the society as a whole. However, a major challenge of large language models is the massive resources required for training and operation. To address this issue, researchers are actively exploring compact large language models that retain the capabilities of large language models while notably reducing the model size. These research efforts are mainly focused on improving pretraining, instruction tuning, and alignment. On the other hand, chain-of-thought prompting is a technique aimed at enhancing the reasoning ability of large language models. It provides an answer through a series of intermediate reasoning steps when given a problem. By guiding the model through a multistep problem-solving process, chain-of-thought prompting may improve the model reasoning skills. Mathematical reasoning, which is a fundamental aspect of human intelligence, has played a crucial role in advancing large language models toward human-level performance. As a result, mathematical reasoning is being widely explored in the context of large language models. This type of research extends to various domains such as geometry problem solving, tabular mathematical reasoning, visual question answering, and other areas.