SPEECH/AUDIO

FastFit: Towards Real-Time Iterative Neural Vocoder by Replacing U-Net Encoder With Multiple STFTs

INTERSPEECH 2023. 08

REINFORCEMENT LEARNING

On the Importance of Feature Decorrelation for Unsupervised Representation Learning in Reinforcement Learning

ICML 2023. 07

COMPUTER VISION

Local 3D Editing via 3D Distillation of CLIP Knowledge

CVPR 2023. 06

COMPUTER VISION

Revisiting the Importance of Amplifying Bias for Debiasing

AAAI 2023. 02

COMPUTER VISION

Efficient Skeleton-Based Action Recognition via Joint-Mapping strategies

WACV 2023. 01

NLP

Normalizing Mutual Information for Robust Adaptive Training for Translation

EMNLP Short Paper 2022. 12

NLP

LittleBird: Efficient Faster & Longer Transformer for Question Answering

EMNLP Long Paper 2022. 12

NLP

APEACH: Attacking Pejorative Expressions with Analysis on Crowd-Generated Hate Speech Evaluation Datasets

Findings of EMNLP 2022. 12

NLP

Persona-Knowledge Dialogue Multi-Context Retrieval and Enhanced Decoding Methods

Customized Chat Grounding Persona and Knowledge Workshop at COLING 2022. 10

SPEECH/AUDIO

Generalizing RNN-Transducer to Out-Domain Audio via Sparse Self-Attention Layers

INTERSPEECH 2022. 09

SPEECH/AUDIO

Automatic Pronunciation Assessment using Self-Supervised Speech Representation Learning

INTERSPEECH 2022. 09

NLP

The Emotion is Not One-hot Encoding: Learning with Grayscale Label for Emotion Recognition in Conversation

INTERSPEECH 2022. 09

SPEECH/AUDIO

JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech

INTERSPEECH 2022. 09

COMPUTER VISION

Proxyless Neural Architecture Adaptation at Once

IEEE Access 2022. 09

COMPUTER VISION

Efficient Two-Stream Network for Online Video Action Segmentation

IEEE Access 2022. 08

COMPUTER VISION

Classification-based Multi-task Learning for Efficient Pose Estimation Network

ICPR 2022. 08

KNOWLEDGE GRAPH

ComDensE : Combined Dense Embedding of Relation-aware and Common Features for Knowledge Graph Completion

ICPR 2022. 08

KNOWLEDGE GRAPH

OASYS: Domain-Agnostic Automated System for Constructing Knowledge Base from Unstructured Text

Mining and Learning on Graphs Workshop at SIGKDD 2022. 08

MACHINE LEARNING

Connecting a Low Loss Subspace for Personalized Federated Learning

SIGKDD Research Track 2022. 08

NLP

Paraphrasing via Ranking Many Candidates

INLG 2022. 07

COMPUTER VISION

A Statistical Manifold Framework for Point Cloud Data

ICML 2022. 07

REINFORCEMENT LEARNING

Towards Validating Long-Term User Feedbacks in Interactive Recommendation Systems

SIGIR (Best Short Paper Honorable Mention) 2022. 07

NLP

CoMPM: Context Modeling with Speaker's Pre-trained Memory Tracking for Emotion Recognition in Conversation

NAACL 2022. 07

COMPUTER VISION

Contrastive Regularization for Semi-Supervised Learning

L3D-IVU Workshop at CVPR 2022. 06

COMPUTER VISION

X-ViT: High Performance Linear Vision Transformer without Softmax

Transformers for Vision Workshop at CVPR 2022. 06

NLP

Vacillating Human Correlation of SacreBLEU in Unprotected Languages

Human Evaluation of NLP Systems Workshop at ACL 2022. 05

NLP

Multimodal Interactions Using Pretrained Unimodal Models for SIMMC 2.0

DSTC10 Wokrshop at AAAI 2022. 02

COMPUTER VISION

Proxyless Neural Architecture Adaptation for Supervised Learning and Self-Supervised Learning

Learning Network Architecture during Training Workshop at AAAI 2022. 02

COMPUTER VISION

SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness

NeurIPS 2021. 12

COMPUTER VISION

Learning Debiased Representation via Disentangled Feature Augmentation

NeurIPS Oral 2021. 12

NLP

Kakao Enterprise’s WMT21 Machine Translation using Terminologies Task Submission

WMT 2021 System Papers 2021. 11

NLP

Capturing Speaker Incorrectness: Speaker-Focused Post-Correction for Abstractive Dialogue Summarization

NewSum workshop, EMNLP 2021. 11

NLP

An Evaluation Dataset and Strategy for Building Robust Multi-turn Response Selection Model

EMNLP 2021. 11

NLP

AligNART: Non-autoregressive Neural Machine Translation by Jointly Learning to Estimate Alignment and Translate

EMNLP 2021. 11

COMPUTER VISION

Distilling Global and Local Logits with Densely Connected Relations

ICCV 2021. 10

SPEECH/AUDIO

Improving End-to-End Contextual Speech Recognition via a Word-Matching Algorithm with Backward Search

IEEE Signal Processing Letters 2021. 10

SPEECH/AUDIO

UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation

INTERSPEECH 2021. 08

NLP

Auxiliary Sequence Labeling Tasks for Disfluency Detection

INTERSPEECH 2021. 08

SPEECH/AUDIO

SE-Conformer: Time-Domain Speech Enhancement using Conformer

INTERSPEECH 2021. 08

NLP

Learning to Walk across Time for Interpretable Temporal Knowledge Graph Completion

SIGKDD Research Track Long Paper 2021. 08

NLP

Adaptive Batch Scheduling for Open-Domain Question Answering

IEEE Access 2021. 08

NLP

Deep Context- and Relation-Aware Learning for Aspect-based Sentiment Analysis

ACL-IJCNLP Main Conference 2021. 08

NLP

OutFlip: Generating Examples for Unknown Intent Detection with Natural Language Attack

ACL-IJCNLP Findings of ACL 2021. 08

COMPUTER VISION

ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision

ICML Long Talk 2021. 07

SPEECH/AUDIO

Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

ICML 2021. 07

SPEECH/AUDIO

U-Convolution Based Residual Echo Suppression With Multiple Encoders

ICASSP 2021. 06

SPEECH/AUDIO

Multitask Learning and Joint Optimization For Transformer-Rnn-Tranducer Speech Recognition

ICASSP 2021. 06

NLP

Korean Erroneous Sentence Classification with Integrated Eojeol Embedding

IEEE Access 2021. 06

COMPUTER VISION

Suppressing Spoof-irrelevant Factors for Domain-agnostic Face Anti-spoofing

IEEE Access 2021. 05

NLP

RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databases

중첩된 SELECT문을 좀 더 정확하게 생성하는 SPC 기법을 적용한 Text-to-SQL 알고리즘 'RYANSQL' 제안

Computational Linguistics 2021. 03

COMPUTER VISION

A Plug-in Method for Representation Factorization in Connectionist Models

딥러닝 모델에서 추출한 임베딩 벡터를 독립 요인으로 분해하는 기법 ‘FDEN’ 제안

IEEE Transactions on Neural Networks and Learning Systems 2021. 02

COMPUTER VISION

Multi-level Distance Regularization for Deep Metric Learning

딥러닝 기반 거리 학습에 적합한 새로운 정규화 기법 ‘MDR’ 제안

AAAI 2021. 02

NLP

Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response Selection

응답 선택에서 대화 맥락에 호응하면서도 의미적 유사도가 높은 문장을 선택하는 기법 'UMS' 제안

AAAI 2021. 02

SPEECH/AUDIO

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

고품질의 음성 오디오를 빠르게 합성하는 TTS 모델 'Hi-Fi GAN' 제안

NeurIPS 2020. 12

SPEECH/AUDIO

Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search

플로우 기반 생성 모델과 동적 프로그래밍을 활용한 TTS 모델 'Glow-TTS' 제안

NeurIPS Oral 2020. 12

NLP

Stable Style Transformer: Delete and Generate Approach with Encoder-Decoder for Text Style Transfer

비병렬 데이터셋을 활용한 새로운 텍스트 스타일 변환 모델 'SST' 제안

INLG 2020. 12

NLP

Reference and Document Aware Semantic Evaluation Methods for Korean Language Summarization

텍스트 요약 모델을 평가하는 새로운 척도 'RDASS' 제안

COLING 2020. 12

COMPUTER VISION

Face Video Retrieval Based on the Deep CNN With RBF Loss

IEEE Transactions on Image Processing 2020. 12

NLP

Sparse and Decorrelated Representations for Stable Zero-shot NMT

강건한 제로샷 번역 모델을 위해 정규화 기법 'SLNI' 도입 제안

EMNLP Findings of ACL 2020. 11

NLP

Revisiting modularized multilingual NMT to meet industrial demands

다국어 번역 모델 아키텍처인 'M2NMT'의 재발견

EMNLP 2020. 11

NLP

AttnIO: Knowledge Graph Exploration with In-and-Out Attention Flow for Knowledge-Grounded Dialogue

대화 맥락에 따른 지식 그래프 경로 탐색 모델 'AttnIO' 제안

EMNLP 2020. 11

SPEECH/AUDIO

Accelerating RNN Transducer Inference via Adaptive Expansion Search

E2E 음성인식의 가속화를 위한 적응적 검색 기법 'AES' 제안

IEEE Signal Processing Letters 2020. 11

COMPUTER VISION

Learning Discriminative Part Features Through Attentions For Effective And Scalable Person Search

한 번의 딥러닝 추론으로 사람 검출과 검색을 한꺼번에 구현하는 기법 제안

ICIP 2020. 10

SPEECH/AUDIO

JDI-T: Jointly trained Duration Informed Transformer for Text-To-Speech without Explicit Alignment

음성합성 모델과 음소-오디오 정렬 모델을 한꺼번에 훈련하는 아키텍처 'JDI-T' 제안

INTERSPEECH 2020. 10

COMPUTER VISION

Diversified Mutual Learning for Deep Metric Learning

여러 모델간 상호학습 방식으로 이미지 검색 성능을 높이는 기법 제안

ECCV workshop on TASK-CV 2020. 09

COMPUTER VISION

BroadFace: Looking at Tens of Thousands of People at Once for Face Recognition

수많은 사람의 얼굴을 효과적으로 학습하는 기법 'BroadFace' 제안

ECCV 2020. 08

COMPUTER VISION

Deep Metric Learning with Multi-Objective Functions

패션 이미지를 효율적으로 검색하는 새로운 거리학습 기법 제안

CVPR workshop on CVFAD 2020. 06

COMPUTER VISION

GroupFace: Learning Latent Groups and Constructing Group-based Representations for Face Recognition

얼굴 인식에 전문화된 새로운 아키텍처 'GroupFace' 제안

CVPR 2020. 06

SPEECH/AUDIO

Affective Latent Representation of Acoustic and Lexical Features for Emotion Recognition

음성의 음향・어휘 특성을 동시에 반영해 사람의 감정을 효과적으로 인식하는 아키텍처 제안

SENSORS 2020. 05

SPEECH/AUDIO

Many-to-Many Voice Conversion using Conditional Cycle-Consistent Adversarial Networks

CycleGAN을 활용해 다자 간의 음성 스타일을 변환하는 기법 제안

ICASSP 2020. 02

COMPUTER VISION

Attentional Feature-Pair Relation Networks for Accurate Face Recognition

ICCV 2019. 10

COMPUTER VISION

BASN: Enriching Feature Representation Using Bipartite Auxiliary Supervision for Face Anti-Spoofing

ICCV Workshop on DFW 2019. 10

NLP

기계 독해를 이용한 웹 기반 오픈 도메인 한국어 질의응답

한글 및 한국어정보처리 학술대회 2019. 10

NLP

한국어 챗봇에서의 오류에 강건한 한국어 문장 분류를 위한 어절 단위 임베딩

한글 및 한국어정보처리 학술대회 2019. 10

NLP

오픈도메인 질의문 자동 분류를 위한 주석 말뭉치 구축 연구

한글 및 한국어정보처리 학술대회 2019. 10

NLP

한국어 질의 응답에서의 화제성을 고려한 딥러닝 기반 정답 유형 분류기

한글 및 한국어정보처리 학술대회 2019. 10

SPEECH/AUDIO

Speech Enhancement Using a Two-Stage Network for an Efficient Boosting Strategy

ICASSP 2019. 05

NLP

DNN-based Emotion Recognition based on Bottleneck Acoustic Features and Lexical Features

ICASSP 2019. 05

COMPUTER VISION

Uncorrelated Feature Encoding for Faster Image Style Transfer

arXiv 2018. 07

COMPUTER VISION

Refining faster-RCNN for accurate object detection

IAPR MVA 2017. 05