• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.514-517
• /
• 2023

본 연구는 인 컨택스트 러닝 (In-Context Learning)을 오디오-언어 작업에 적용하기 위한 멀티모달 (Multi-Modal) 딥러닝 모델을 다룬다. 해당 모델을 통해 학습 단계에서 오디오와 텍스트의 소통 가능한 형태의 표현 (Representation)을 학습하고 여러가지 오디오-텍스트 작업을 수행할 수 있는 멀티모달 딥러닝 모델을 개발하는 것이 본 연구의 목적이다. 모델은 오디오 인코더와 언어 인코더가 연결된 구조를 가지고 있으며, 언어 모델은 6.7B, 30B 의 파라미터 수를 가진 자동회귀 (Autoregressive) 대형 언어 모델 (Large Language Model)을 사용한다 오디오 인코더는 자기지도학습 (Self-Supervised Learning)을 기반으로 사전학습 된 오디오 특징 추출 모델이다. 언어모델이 상대적으로 대용량이기 언어모델의 파라미터를 고정하고 오디오 인코더의 파라미터만 업데이트하는 프로즌 (Frozen) 방법으로 학습한다. 학습을 위한 과제는 음성인식 (Automatic Speech Recognition)과 요약 (Abstractive Summarization) 이다. 학습을 마친 후 질의응답 (Question Answering) 작업으로 테스트를 진행했다. 그 결과, 정답 문장을 생성하기 위해서는 추가적인 학습이 필요한 것으로 보였으나, 음성인식으로 사전학습 한 모델의 경우 정답과 유사한 키워드를 사용하는 문법적으로 올바른 문장을 생성함을 확인했다.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.278-284
• /
• 2009

Multimodal data to have several modalities such as videos, images, sounds and texts for one contents is increasing. Since this type of data has ill-defined format, it is not easy to represent the crossmodal information for them explicitly. So, we proposed new method to extract and analyze vision-language crossmodal association information using the documentaries video data about the nature. We collected pairs of images and captions from 3 genres of documentaries such as jungle, ocean and universe, and extracted a set of visual words and that of text words from them. We found out that two modal data have semantic association on crossmodal association information from this analysis.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.4
• /
• pp.203-210
• /
• 2017

In this paper, we propose an effective neural network model for image caption generation and model transfer. This model is a kind of multi-modal recurrent neural network models. It consists of five distinct layers: a convolution neural network layer for extracting visual information from images, an embedding layer for converting each word into a low dimensional feature, a recurrent neural network layer for learning caption sentence structure, and a multi-modal layer for combining visual and language information. In this model, the recurrent neural network layer is constructed by LSTM units, which are well known to be effective for learning and transferring sequence patterns. Moreover, this model has a unique structure in which the output of the convolution neural network layer is linked not only to the input of the initial state of the recurrent neural network layer but also to the input of the multimodal layer, in order to make use of visual information extracted from the image at each recurrent step for generating the corresponding textual caption. Through various comparative experiments using open data sets such as Flickr8k, Flickr30k, and MSCOCO, we demonstrated the proposed multimodal recurrent neural network model has high performance in terms of caption accuracy and model transfer effect.

• Electronics and Telecommunications Trends
• /
• v.37 no.1
• /
• pp.1-9
• /
• 2022

With the development of artificial intelligence, many studies have focused on evaluating abnormal situations by using various sensors, as industries try to automate some of the surveillance and security tasks traditionally performed by humans. In particular, mobile robots using multimodal sensors are being used for pilot operations aimed at helping security robots cope with various outdoor situations. Multiagent systems, which combine fixed and mobile systems, can provide more efficient coverage (than that provided by other systems), but network bottlenecks resulting from increased data processing and communication are encountered. In this report, we will examine recent trends in object recognition and abnormal-situation determination in various changing outdoor security robot environments, and describe an outdoor security robot platform that operates as a multiagent equipped with a multimodal sensor.

• Annual Conference of KIPS
• /
• 2010.11a
• /
• pp.1678-1680
• /
• 2010

최근 스마트폰의 보급이 급속도로 이루어지고 있고 전자책 시장이 성장함에 따라 스마트폰을 통해 전자책 등 다양한 교육 서비스를 제공하려는 시도가 활발해지고 있다. 앞으로 가방에 여러 권의 책을 소지하기 보다는 스마트폰이나 전자책 서비스가 가능한 단말기 하나만 들고 다니면서 책을 대체할 것이다. 본 논문에서는 단순한 텍스트기반이 아닌 멀티미디어 디바이스와 각종 센서를 이용함으로써 멀티모달 상호작용을 지원하는 전자책의 개발 방법을 제안한다.

• Annual Conference of KIPS
• /
• 2023.05a
• /
• pp.660-662
• /
• 2023

3차원 포인트 클라우드의 의미적 분할은 환경을 구성하는 물체 단위로 포인트 클라우드를 분할하는 작업으로서, 환경의 3차원적 구성을 이해하고 환경과 상호작용에 필수적인 시각 지능을 요구한다. 본 논문에서는 포인트 클라우드에서 추출하는 3차원 기하학적 특징과 함께 멀티-뷰 영상에서 추출하는 2차원 시각적 특징들도 활용하는 새로운 3차원 포인트 클라우드 의미적 분할 모델 MFNet을 제안한다. 제안 모델은 서로 이질적인 2차원 시각적 특징과 3차원 기하학적 특징의 효과적인 융합을 위해, 새로운 중기 융합 전략과 멀티-모달 교차 주의집중을 이용한다. 본 논문에서는 ScanNetV2 벤치마크 데이터 집합을 이용한 다양한 실험들을 통해, 제안 모델 MFNet의 우수성을 입증한다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.65-71
• /
• 2014

This paper present the multi-modal user distance estimation system using mono camera and mono microphone basically equipped with a mobile device. In case of a distance estimation method using an image, we is estimated a distance of the user through the skin color region extraction step, a noise removal step, the face and eyes region detection step. On the other hand, in case of a distance estimation method using speech, we calculates the absolute difference between the value of the sample of speech input. The largest peak value of the calculated difference value is selected and samples before and after the peak are specified as the ROI(Region of Interest). The samples specified perform FFT(Fast Fourier Transform) and calculate the magnitude of the frequency domain. Magnitude obtained is compared with the distance model to calculate the likelihood. We is estimated user distance by adding with weights in the sorted value. The result of an experiment using the multi-modal method shows more improved measurement value than that of single modality.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.3
• /
• pp.23-29
• /
• 2022

Virtual humans are implemented with dedicated modeling tools like Unity 3D Engine in virtual space (virtual reality, mixed reality, metaverse, etc.). Various human modeling tools have been introduced to implement virtual human-like appearance, voice, expression, and behavior similar to real people, and virtual humans implemented via these tools can communicate with users to some extent. However, most of the virtual humans so far have stayed unimodal using only text or speech. As AI technologies advance, the outdated machine-centered dialogue system is now changing to a human-centered, natural multi-modal system. By using several pre-trained networks, we implemented an emotion-based multi-modal dialogue system, which generates human-like utterances and displays appropriate facial expressions in real-time.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 1998.06a
• /
• pp.1105-1108
• /
• 1998

• Proceedings of the KSPS conference
• /
• 2004.05a
• /
• pp.101-123
• /
• 2004