Date | Speaker | Title | Source | Year | Area | Paper | Slides |
---|---|---|---|---|---|---|---|
24-11-06 | 김동환 | Learning to Prompt with Text Only Supervision for Vision-Language Models | CVPR Workshop | 2024 | CV | [link] | [link] |
24-10-30 | 이선훈 | HEDNet: A hierarchical encoder-decoder network for 3d object detection in point clouds | NeurIPS | 2024 | CV | [link] | [link] |
24-10-23 | 조경우 | Lost in the Middle: How Language Models Use Long Contexts | TACL | 2024 | NLP | [link] | [link] |
24-10-23 | 김현재 | IFCap: Image-like Retrieval and Frequency-based Entity Filtering for Zero-shot Captioning | arXiv | 2024 | CV | [link] | [link] |
24-10-23 | 안주현 | 2024-2 Engineering Design | - | - | Other | [link] | [link] |
24-10-16 | 김경민 | let’s verify step by step@arXiv’23 | - | - | NLP | [link] | [link] |
24-10-16 | 백영승 | MeaCap: Memory-Augmented Zero-shot Image Captioning | CVPR | 2024 | CV | [link] | [link] |
24-10-09 | 임상훈 | Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation | ACL Findings | 2024 | NLP | [link] | [link] |
24-10-09 | 조수연 | Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer | JMLR | 2020 | NLP | [link] | [link] |
24-10-02 | 김동환 | DECAP: DECODING CLIP LATENTS FOR ZERO-SHOT CAPTIONING VIA TEXT-ONLY TRAINING | ICLR | 2023 | CV | [link] | [link] |
24-10-02 | 이선훈 | SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detection@ | - | - | CV | [link] | [link] |
24-09-25 | 김현우 | SSD: Single Shot MultiBox Detector | ECCV | 2016 | CV | [link] | [link] |
24-09-11 | 김현재 | DMAD: Dual Memory Bank for Real-World Anomaly Detection | arXiv | 2024 | CV | [link] | [link] |
24-09-11 | 조경우 | ListT5: Listwise Reranking with Fusion-in-Decoder Improves Zero-shot Retrieval | ACL | 2024 | NLP | [link] | [link] |
24-09-04 | 김경민 | Emulated Disalignment: Safety Alignment for Large Language Models May Backfire! | ACL | 2024 | NLP | [link] | [link] |
24-08-29 | 백영승 | Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding | CVPR | 2024 | VL | [link] | [link] |
24-08-29 | 임상훈 | Graph Language Models | ACL | 2024 | NLP | [link] | [link] |
24-08-20 | 조수연 | Chain-of-Thought Prompting Elicits Reasoning in Large Language Models@ | - | - | NLP | [link] | [link] |
24-08-20 | 김민석 | ImageNet Classification with Deep Convolutional Neural Networks | NIPS | 2012 | CV | [link] | [link] |
24-08-20 | 안주현 | Tokenization | - | - | NLP | [link] | [link] |
24-08-01 | 이선훈 | FocalFormer3D: Focusing on Hard Instance for 3D Object Detection | ICCV | 2023 | CV | [link] | [link] |
24-07-25 | 김현재 | Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts | CVPR | 2024 | CV | [link] | [link] |
24-07-25 | 김현우 | Faster r-cnn: Towards real-time object detection with region proposal networks | NeurIPS | 2015 | CV | [link] | [link] |
24-07-11 | 조경우 | Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples! | EMNLP Findings | 2023 | NLP | [link] | [link] |
24-07-11 | 김경민 | Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents | NeurIPS | 2023 | NLP | [link] | [link] |
24-07-04 | 백영승 | Towards CLIP-driven Language-free 3D Visual Grounding via 2D-3D Relational Enhancement and Consistency | CVPR | 2024 | VL | [link] | [link] |
24-07-04 | 임상훈 | Direct Preference Optimization: Your Language Model is Secretly a Reward Model | NeurIPS | 2023 | NLP | [link] | [link] |
24-06-18 | 김현재 | ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detection | WACV | 2024 | CV | [link] | [link] |
24-05-28 | 김현우 | 3D Object Detection을 활용한 흡연 구역 이탈 방지 시스템 | - | - | Other | [link] | [link] |
24-05-28 | 조수연 | Attention Is All You Need | NIPS | 2017 | NLP | [link] | [link] |
24-05-28 | 이선훈 | Clustering based point cloud representation learning for 3d analysis | ICCV | 2023 | CV | [link] | [link] |
24-05-21 | 조경우 | PILOT: Legal Case Outcome Prediction with Case Law | NAACL | 2024 | NLP | [link] | [link] |
24-05-21 | 김민석 | Multi-Layer Perceptron | - | - | ML | [link] | [link] |
24-05-21 | 임상훈 | Better & Faster Large Language Models via Multi-token Prediction | arXiv | 2024 | NLP | [link] | [link] |
24-05-07 | 조수연 | BERT: Pre-training Deep Bidirectional Transformers for Language Understanding | NAACL | 2018 | NLP | [link] | [link] |
24-05-07 | 백영승 | Exploiting Contextual Objects and Relations for 3D Visual Grounding | NeurIPS | 2023 | VL | [link] | [link] |
24-05-07 | 김경민 | SELF-RAG: LEARNING TO RETRIEVE, GENERATE, AND CRITIQUE THROUGH SELF-REFLECTION | arXiv | 2023 | NLP | [link] | [link] |
24-04-30 | 이선훈 | Efficient Transformer-based 3D Object Detection with Dynamic Token Halting | ICCV | 2023 | CV | [link] | [link] |
24-04-16 | 김현재 | Deep Semi-Supervised Anomaly Detection | ICLR | 2020 | CV | [link] | [link] |
24-04-16 | 김현우 | Rich feature hierarchies for accurate object detection and semantic segmentation | CVPR | 2014 | CV | [link] | [link] |
24-04-09 | 조경우 | Finetuned Language Models Are Zero-Shot Learners | ICLR | 2022 | NLP | [link] | [link] |
24-04-09 | 임상훈 | GraphText: Graph Reasoning in Text Space | arXiv | 2023 | NLP | [link] | [link] |
24-04-02 | 백영승 | Uni3DETR: Unified 3D Detection Transformer | NeurIPS | 2023 | CV | [link] | [link] |
24-04-02 | 김민석 | Machine Learning - Regression | - | - | ML | [link] | [link] |
24-04-02 | 김경민 | SELF-DISCOVER: Large Language Models Self-Compose Reasoning Structures | arXiv | 2024 | NLP | [link] | [link] |
24-03-26 | 김현우 | GPT-3.5를 이용한 수능 문제 풀이 | - | - | Math | [link] | [link] |
24-03-26 | 이선훈 | Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment | ICCV | 2023 | CV | [link] | [link] |
24-03-26 | 조수연 | Machine learning - basic | - | - | ML | [link] | [link] |
24-03-19 | 김현재 | Soft Augmentation for Image Classification | CVPR | 2023 | CV | [link] | [link] |
24-03-19 | 조경우 | Language Models are Unsupervised Multitask Learners@OpenAI blog | - | - | NLP | [link] | [link] |
24-03-12 | 백영승 | DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Grounding | AAAI | 2023 | VL | [link] | [link] |
24-03-12 | 김경민 | DOLA: DECODING BY CONTRASTING LAYERS IMPROVES FACTUALITY IN LARGE LANGUAGE MODELS | ICLR | 2024 | NLP | [link] | [link] |
24-02-28 | 임상훈 | Tuning Language Models by Proxy | arXiv | 2024 | NLP | [link] | [link] |
24-01-24 | 이선훈 | Clusterformer: Cluster-based Transformer for 3D Object Detection in Point Clouds | ICCV | 2023 | CV | [link] | [link] |
24-01-24 | 김현재 | Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation | CVPR | 2020 | CV | [link] | [link] |
24-01-17 | 조경우 | Distributed Representations of Words and Phrases and their Compositionality | NIPS | 2013 | NLP | [link] | [link] |
24-01-17 | 김경민 | SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling | arXiv | 2023 | NLP | [link] | [link] |
24-01-11 | 백영승 | What does CLIP know about a red circle? Visual prompt engineering for VLMs | ICCV | 2023 | VL | [link] | [link] |
24-01-11 | 임상훈 | The Benefits of Label-Description Training for Zero-Shot Text Classification | EMNLP | 2023 | NLP | [link] | [link] |
23-12-20 | 이선훈 | AdaMixer: A Fast-Converging Query-Based Object Detector | CVPR | 2022 | CV | [link] | [link] |
23-12-14 | 김현재 | ContrastMask: Contrastive Learning to Segment Every Thing | CVPR | 2022 | CV | [link] | [link] |
23-12-07 | 조경우 | Improving Language Understanding by Generative Pre-Training | arXiv | 2018 | NLP | [link] | [link] |
23-11-30 | 김경민 | INSTRUCTION TUNING WITH HUMAN CURRICULUM | arXiv | 2023 | CV | [link] | [link] |
23-11-23 | 백영승 | COT3DREF: CHAIN-OF-THOUGHTS DATA-EFFICIENT 3D VISUAL GROUNDING | arXiv | 2023 | VL | [link] | [link] |
23-11-16 | 김기백 | Asymmetric Loss For Multi-Label Classification | ICCV | 2021 | CV | [link] | [link] |
23-11-16 | 임상훈 | Making Language Models Better Reasoners with Step-Aware Verifier | ACL | 2023 | NLP | [link] | [link] |
23-11-09 | 이선훈 | Sparse r-cnn: End-to-end object detection with learnable proposals | CVPR | 2021 | CV | [link] | [link] |
23-11-09 | 손성빈 | MaPLe: Multi-modal Prompt Learning | CVPR | 2023 | VL | [link] | [link] |
23-11-02 | 김현재 | Best of Both Worlds: Multimodal Contrastive Learning with Tabular and Imaging Data | CVPR | 2023 | CV | [link] | [link] |
23-11-02 | 김동환 | Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations | ACL | 2023 | NLP | [link] | [link] |
23-10-26 | Ratna | SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Model | arXiv | 2023 | NLP | [link] | [link] |
23-10-26 | 김경민 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | arXiv | 2023 | NLP | [link] | [link] |
23-10-19 | 김기백 | VERA: VECTOR-BASED RANDOM MATRIX ADAPTATION | arXiv | 2023 | NLP | [link] | [link] |
23-10-19 | 백영승 | EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding | CVPR | 2023 | VL | [link] | [link] |
23-10-12 | 임상훈 | Instances and Labels: Hierarchy-aware Joint Supervised Contrastive Learning for Hierarchical Multi-Label Text Classification | EMNLP Findings | 2023 | NLP | [link] | [link] |
23-10-12 | 이선훈 | FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxels | arXiv | 2023 | CV | [link] | [link] |
23-09-21 | 손성빈 | MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning | ACL | 2023 | VL | [link] | [link] |
23-09-21 | 김현재 | AnomalyGPT: Detecting Industrial Anomalies using Large Vision-Language Models | arXiv | 2023 | VL | [link] | [link] |
23-09-07 | 김동환 | Faithful Chain-of-Thought Reasoning | arXiv | 2023 | NLP | [link] | [link] |
23-08-31 | 김현우 | Dacon’s Challenge Result | - | - | CV | [link] | [link] |
23-08-31 | Ratna | CQG: A Simple and Effective Controlled Generation Framework for Multi-hop Question Generation | ACL | 2022 | NLP | [link] | [link] |
23-08-31 | 김경민 | SCOTT: Self-Consistent Chain-of-Thought Distillation | ACL | 2023 | NLP | [link] | [link] |
23-08-23 | 백영승 | WildRefer: 3D Object Localization in Large-scale Dynamic Scenes with Multi-modal Visual Data and Natural Language | arXiv | 2023 | VL | [link] | [link] |
23-08-23 | 임상훈 | Enhancing Hierarchical Text Classification through Knowledge Graph Integration | ACL Findings | 2023 | NLP | [link] | [link] |
23-08-16 | 김기백 | ZLPR: A Novel Loss for Multi-label Classification | arXiv | 2022 | NLP | [link] | [link] |
23-08-16 | 김현재 | CutPaste: Self-Supervised Learning for Anomaly Detection and Localization | CVPR | 2021 | CV | [link] | [link] |
23-08-09 | 이선훈 | Model-agnostic meta-learning for fast adaptation of deep networks | ICML | 2017 | CV | [link] | [link] |
23-08-09 | 손성빈 | Transferable Decoding with Visual Entities for Zero-shot Image Captioning | ICCV | 2023 | VL | [link] | [link] |
23-08-02 | 김동환 | Active Retrieval Augmented Generation | arXiv | 2023 | NLP | [link] | [link] |
23-08-02 | Ratna | Educational Multi-Question Generation for Reading Comprehension | ACL | 2022 | NLP | [link] | [link] |
23-07-26 | 김경민 | THE CURSE OF RECURSION: TRAINING ON GENERATED DATA MAKES MODELS FORGET | arXiv | 2023 | DL | [link] | [link] |
23-07-26 | 백영승 | Language-Guided 3D Object Detection in Point Cloud for Autonomous Driving | arXiv | 2023 | VL | [link] | [link] |
23-07-19 | 김기백 | Low-Resource Text Classification: A Parameter-Free Classification Method with Compressors | ACL | 2023 | NLP | [link] | [link] |
23-07-19 | 임상훈 | HiTIN: Hierarchy-aware Tree Isomorphism Network for Hierarchical Text Classification | ACL | 2023 | NLP | [link] | [link] |
23-07-13 | 이선훈 | VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking | CVPR | 2023 | CV | [link] | [link] |
23-07-13 | 손성빈 | Chain of Thought Prompt Tuning for Vision-Language Models | arXiv | 2023 | VL | [link] | [link] |
23-07-05 | 김현재 | Meta Compositional Referring Expression Segmentation | CVPR | 2023 | CV | [link] | [link] |
23-07-05 | 김동환 | Differentiable Instruction Optimization for Cross-Task Generalization | ACL | 2023 | NLP | [link] | [link] |
23-06-21 | 임상훈 | Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes | arXiv | 2023 | NLP | [link] | [link] |
23-06-21 | Ratna | Unsupervised Cross-lingual Representation Learning at Scale | arXiv | 2020 | NLP | [link] | [link] |
23-06-12 | 백영승 | 3D Human Keypoints Estimation from Point Cloud in the Wild without Human Labels | CVPR | 2023 | CV | [link] | [link] |
23-06-12 | 김기백 | InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models | arXiv | 2023 | NLP | [link] | [link] |
23-06-07 | 김경민 | Tree of Thoughts: Deliberate Problem Solving with Large Language Models | arXiv | 2023 | NLP | [link] | [link] |
23-06-07 | 이선훈 | DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets | CVPR | 2023 | CV | [link] | [link] |
23-05-22 | 손성빈 | TransVG: End-to-End Visual Grounding with Transformers | ICCV | 2021 | CV | [link] | [link] |
23-05-22 | 김현재 | CRIS: CLIP-Driven Referring Image Segmentation | CVPR | 2022 | CV | [link] | [link] |
23-05-15 | 김동환 | MEMORIZING TRANSFORMERS | ICLR | 2022 | NLP | [link] | [link] |
23-05-15 | 김경민 | PEER : A Collaborative Language Model | ICLR | 2023 | NLP | [link] | [link] |
23-05-08 | 백영승 | HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Driving | CORL | 2023 | CV | [link] | [link] |
23-05-08 | 김기백 | LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking | MM | 2022 | NLP | [link] | [link] |
23-05-01 | 임상훈 | LoRA: Low-Rank Adaptation of Large Language Models | ICLR | 2022 | NLP | [link] | [link] |
23-05-01 | 이선훈 | ARUBA: An Architecture-Agnostic Balanced Loss for Aerial Object Detection | WACV | 2023 | CV | [link] | [link] |
23-04-26 | 손성빈 | SMALLCAP: Lightweight Image Captioning Prompted with Retrieval Augmentation | CVPR | 2023 | VL | [link] | [link] |
23-04-26 | 김현재 | Rethinking Semantic Segmentation: A Prototype View | CVPR | 2022 | CV | [link] | [link] |
23-04-17 | 김동환 | Meet in the Middle: A New Pre-training Paradigm | arXiv | 2023 | NLP | [link] | [link] |
23-04-10 | 김경민 | DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings | NAACL | 2021 | NLP | [link] | [link] |
23-04-10 | 백영승 | Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving | CVPR | 2022 | CV | [link] | [link] |
23-03-27 | 김기백 | Context-faithful Prompting for Large Language Models | arXiv | 2023 | NLP | [link] | [link] |
23-03-27 | 임상훈 | UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation | arXiv | 2023 | NLP | [link] | [link] |
23-03-22 | 이선훈 | Towards accurate one-stage object detection with ap-loss. | CVPR | 2019 | CV | [link] | [link] |
23-03-13 | 이선훈 | AP losses series | - | - | CV | [link] | [link] |
23-03-13 | 손성빈 | ClipCap: CLIP Prefix for Image Captioning | arXiv | 2021 | VL | [link] | [link] |
23-03-06 | 김경민 | Language Is Not All You Need : Aligning Perception with Language Models | arXiv | 2023 | NLP | [link] | [link] |
23-02-28 | 백영승 | Frustum PointNets for 3D Object Detection from RGB-D Data | CVPR | 2018 | CV | [link] | [link] |
23-02-28 | 백영승 | PointRCNN : 3D Object Proposal Generation and Detection from Point Cloud | CVPR | 2019 | CV | [link] | [link] |
23-02-28 | 김기백 | Embedding Recycling for Language Models | EACL | 2023 | NLP | [link] | [link] |
23-02-22 | 김현재 | Prompt-Matched Semantic Segmentation | arXiv | 2022 | CV | [link] | [link] |
23-02-22 | 임상훈 | Efficient End-to-End Video Question Answering with Pyramidal Multimodal Transformer | AAAI | 2023 | NLP | [link] | [link] |
23-02-16 | 김동환 | HyperPrompt: Prompt-based Task-Conditioning of Transformers | ICML | 2022 | NLP | [link] | [link] |
23-02-16 | 이선훈 | Fully Sparse 3D Object Detection | NeurIPS | 2022 | CV | [link] | [link] |
23-02-08 | 김경민 | Training language models to follow instructions with human feedback | arXiv | 2022 | NLP | [link] | [link] |
23-02-08 | 손성빈 | Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks | ACL | 2021 | NLP | [link] | [link] |
23-02-01 | 김기백 | The Forward-Forward Algorithm: Some Preliminary Investigations | arXiv | 2022 | DL | [link] | [link] |
23-02-01 | 김현재 | Vision Transformer Adapter for Dense Predictions | ICLR | 2023 | CV | [link] | [link] |
23-01-25 | 임상훈 | Non-Autoregressive Neural Machine Translation | ICLR | 2018 | NLP | [link] | [link] |
23-01-25 | 김동환 | Learning to Generate Question by Asking Question: A Primal-Dual Approach with Uncommon Word Generation | EMNLP | 2022 | NLP | [link] | [link] |
23-01-18 | 이선훈 | Contemporary methods of Loss and targeting in the object detection | - | - | CV | [link] | [link] |
23-01-18 | 백영승 | HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection | CVPR | 2020 | CV | [link] | [link] |
23-01-02 | 손성빈 | AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition | NeurIPS | 2022 | CV | [link] | [link] |
23-01-02 | 김경민 | Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Models | EMNLP | 2022 | NLP | [link] | [link] |
22-12-21 | 백영승 | Voxelnet: End-to-End Learning for Point Cloud Based 3D Object Detection | CVPR | 2018 | CV | [link] | [link] |
22-11-23 | 김현재 | Image Segmentation Using Text and Image Prompts | CVPR | 2022 | CV | [link] | [link] |
22-11-23 | 김기백 | HPT: Hierarchy-aware Prompt Tuning for Hierarchical Text Classification | EMNLP | 2022 | NLP | [link] | [link] |
22-11-16 | 임상훈 | CONTRASTIVELY ENFORCING DISTINCTIVENESS FOR MULTI-LABEL CLASSIFICATION | arXiv | 2022 | CV | [link] | [link] |
22-11-09 | 김동환 | ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding | COLING | 2022 | NLP | [link] | [link] |
22-11-09 | 이선훈 | Center-based 3d object detection and tracking | CVPR | 2021 | CV | [link] | [link] |
22-11-02 | 박용준 | AO2-DETR: Arbitrary-Oriented Object Detection Transformer | arXiv | 2022 | CV | [link] | [link] |
22-10-26 | 손성빈 | Unified Contrastive Learning in Image-Text-Label Space | CVPR | 2022 | CV | [link] | [link] |
22-10-26 | 김경민 | ByT5: Towards a token-free future with pre-trained byte-to-byte models | TACL | 2022 | NLP | [link] | [link] |
22-10-19 | 김현재 | Panoptic Segmentation | CVPR | 2019 | CV | [link] | [link] |
22-10-19 | 백영승 | DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection | arXiv | 2022 | CV | [link] | [link] |
22-10-05 | 김기백 | Language Modelling with Pixels | arXiv | 2022 | NLP | [link] | [link] |
22-10-05 | 임상훈 | Improved Text Classification via Contrastive Adversarial Training | AAAI | 2022 | NLP | [link] | [link] |
22-09-28 | 김동환 | COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining | NeurIPS | 2021 | NLP | [link] | [link] |
22-09-22 | 손성빈 | Masked Autoencoders Are Scalable Vision Learners | CVPR | 2022 | CV | [link] | [link] |
22-09-22 | 김경민 | Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks | NeurIPS | 2020 | NLP | [link] | [link] |
22-09-14 | 이선훈 | Dn-detr: Accelerate detr training by introducing query denoising | CVPR | 2022 | CV | [link] | [link] |
22-09-07 | 조성웅 | Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Langauge Processing | arXiv | 2021 | NLP | [link] | [link] |
22-09-07 | 조성웅 | reStructured Pre-training | arXiv | 2022 | NLP | [link] | [link] |
22-08-17 | 백영승 | DAB-DETR: DYNAMIC ANCHOR BOXES ARE BETTER QUERIES FOR DETR | ICLR | 2022 | CV | [link] | [link] |
22-08-10 | 임상훈 | Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classification | ACL | 2022 | NLP | [link] | [link] |
22-08-10 | 김기백 | ML-Decoder: Scalable and Versatile Classification Head | arXiv | 2021 | CV | [link] | [link] |
22-08-03 | 김동환 | Intent Detection and Discovery from User Logs via Deep Semi-Supervised Contrastive Clustering | NAACL | 2022 | NLP | [link] | [link] |
22-08-03 | 김현재 | Pointly-supervised instance segmentation | CVPR | 2022 | CV | [link] | [link] |
22-07-27 | 백영승 | Swin Transformer : Hierachical Vision Transformer using Shifted Windows | CVPR | 2021 | CV | [link] | [link] |
22-07-27 | 손성빈 | Jigsaw Clustering for Unsupervised Visual Representation Learning | CVPR | 2021 | CV | [link] | [link] |
22-07-27 | 조성웅 | Discovering New Intents with Deep Aligned Clustering | AAAI | 2021 | NLP | [link] | [link] |
22-07-20 | 박용준 | Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data | ICCV | 2021 | CV | [link] | [link] |
22-07-20 | 김경민 | SimCSE: Simple Contrastive Learning of Sentence Embeddings | EMNLP | 2021 | NLP | [link] | [link] |
22-07-06 | 이선훈 | Embracing Single Stride 3D Object Detector with Sparse Transformer | CVPR | 2022 | CV | [link] | [link] |
22-07-06 | 임상훈 | Are Prompt-based Models Clueless? | ACL | 2022 | NLP | [link] | [link] |
22-06-15 | 김현재 | Segmenter: Transformer for Semantic Segmentation | ICCV | 2021 | CV | [link] | [link] |
22-06-15 | 김기백 | Using Context-to-Vector with Graph Retrofitting to Improve Word Embeddings | ACL | 2022 | NLP | [link] | [link] |
22-05-25 | 김경민 | BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | NAACL | 2019 | NLP | [link] | [link] |
22-05-11 | 김동환 | QRelScore: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevance | arXiv | 2022 | NLP | [link] | [link] |
22-04-27 | 조성웅 | Asking Questions the Human Way: Scalable Question-Answer Generation from Text Corpus | WWW | 2020 | NLP | [link] | [link] |
22-04-27 | 정준욱 | End-to-End Semi-Supervised Object Detection with Soft Teacher | ICCV | 2021 | CV | [link] | [link] |
22-04-20 | 백영승 | End-to-End Object Detection with Transformers | ECCV | 2020 | CV | [link] | [link] |
22-04-20 | 백영승 | Anchor DETR : Query Design for Transformer-Based Object Detection | AAAI | 2022 | CV | [link] | [link] |
22-04-13 | 박용준 | Style Transfer 연구 요약(part1) | - | - | CV | [link] | [link] |
22-04-06 | 김현재 | Semi-Supervised Classification with Graph Convolutional Networks | - | - | ML | [link] | [link] |
22-04-06 | 김동환 | UNILMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training | ICML | 2020 | NLP | [link] | [link] |
22-03-30 | 손지원 | Supervised Contrastive Learning | NIPS | 2020 | ML | [link] | [link] |
22-03-30 | 김경민 | Plug and Play Language Models: A Simple Approach to Controlled Text Generation | ICLR | 2020 | NLP | [link] | [link] |
22-03-16 | 이선훈 | SDR 연구 집대성 | - | - | CV | [link] | [link] |
22-03-10 | 김기백 | UnClE: Explicitly Leveraging Semantic Similarity to Reduce the Parameters of Word Embeddings | EMNLP | 2021 | NLP | [link] | [link] |
22-02-25 | 임상훈 | Hierarchy-Aware T5 with Path-Adaptive Mask Mechanism for Hierarchical Text Classification | arXiv | 2021 | NLP | [link] | [link] |
22-02-16 | 조성웅 | ERNIE-GEN:An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation | IJCAI | 2020 | NLP | [link] | [link] |
22-02-09 | 이선훈 | Pointnet: Deep learning on point sets for 3d classification and segmentation | CVPR | 2017 | CV | [link] | [link] |
22-02-04 | 박용준 | DEFORMABLE DETR: DEFORMABLE TRANSFORMERS FOR END-TO-END OBJECT DETECTION | ICLR | 2021 | CV | [link] | [link] |
22-02-04 | 조성웅 | How does this interaction affect me? Interpretable attribution for feature interactions | NeurIPS | 2020 | NLP | [link] | [link] |
22-01-19 | 백영승 | Image Style Transfer Using Convolutional Neural Networks | CVPR | 2016 | CV | [link] | [link] |
22-01-19 | 백영승 | Multi-style Generative Network for Real-Time Transfer | - | - | CV | [link] | [link] |
22-01-19 | 김현재 | Mask R-CNN | ICCV | 2017 | CV | [link] | [link] |
22-01-12 | 김기백 | Modeling Fine-Grained Entity Types with Box Embeddings | ACL | 2021 | NLP | [link] | [link] |
22-01-12 | 김동환 | Biomedical Entity Representations with Synonym Marginalization | ACL | 2020 | NLP | [link] | [link] |
22-01-05 | 임상훈 | Hierarchy-aware Label Semantics Matching Network for Hierarchical Text Classification | ACL | 2021 | NLP | [link] | [link] |
21-12-29 | 정준욱 | Learning to Cluster Faces on an Affinity Graph | CVPR | 2019 | CV | [link] | [link] |
21-12-29 | 이선훈 | “Why should i trust you?”:Explaining the predictions of any classifier | KDD | 2016 | ML | [link] | [link] |
21-12-20 | 정준욱 | Linkage Based Face Clustering via Graph Convolution Network | CVPR | 2019 | CV | [link] | [link] |
21-12-20 | 김동환 | Exploring the Role of BERT Token Representations to Explain Sentence Probing Results | EMNLP | 2021 | NLP | [link] | [link] |
21-12-13 | 박용준 | Momentum Contrast for Unsupervised Visual Representation Learning | CVPR | 2020 | CV | [link] | [link] |
21-12-13 | 백영승 | You Only Look Once: Unified, Real-Time Object Detection | CVPR | 2016 | CV | [link] | [link] |
21-12-06 | 김기백 | Exploring the Representation of Word Meanings in Context: A Case Study on Homonymy and Synonymy | ACL | 2021 | NLP | [link] | [link] |
21-12-06 | 김현재 | google's neural machine translation system bridging the gap between human and machine translation | arXiv | 2016 | NLP | [link] | [link] |
21-11-29 | 손성빈 | U-Net: Convolutional Networks for Biomedical Image Segmentation | MICCAI | 2015 | CV | [link] | [link] |
21-11-22 | 손성빈 | A Simple Framework for Contrastive Learning of Visual Representations | ICML | 2020 | CV | [link] | [link] |
21-11-08 | 이선훈 | Learning deep features for discriminative localization | CVPR | 2016 | CV | [link] | [link] |
21-11-08 | 조성웅 | Post-hoc Interpretability for Neural NLP: A survey[Part-1] | arXiv | 2021 | NLP | [link] | [link] |
21-11-01 | 조성웅 | Connecting Attributions and QA Model Behavior on Realistic Counterfactuals | EMNLP | 2021 | NLP | [link] | [link] |
21-11-01 | 박용준 | MLP-Mixer:An all-MLP Architecture for Vision | arXiv | 2021 | CV | [link] | [link] |
21-10-18 | 임상훈 | Transformer Feed-Forward Layers Are Key-Value Memories | EMNLP | 2021 | NLP | [link] | [link] |
21-10-11 | 김동환 | Prefix-Tuning: Optimizing Continuous Prompts for Generation | ACL | 2021 | NLP | [link] | [link] |
21-10-11 | 김기백 | Knowledge Neurons in Pretrained Transformers | arXiv | 2021 | NLP | [link] | [link] |
21-10-04 | 박주찬 | ReDet A Rotation-equivariant Detector for Aerial Object Detection | CVPR | 2021 | CV | [link] | [link] |
21-10-04 | 손성빈 | SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers | arxiv | 2021 | CV | [link] | [link] |
21-09-27 | 정준욱 | MagFace: A Universal Representation for Face Recognition and Quality Assessment | CVPR | 2021 | CV | [link] | [link] |
21-09-27 | 박용준 | Training data-efficient image transformers & distillation through attention | ICML | 2021 | CV | [link] | [link] |
21-09-15 | 이선훈 | MonStereo When Monocular and Stereo Meet | ICRA | 2021 | CV | [link] | [link] |
21-09-01 | 손지원 | Time-Series Representation Learning via Temporal and Contextual Contrasting | IJCAI | 2021 | Other | [link] | [link] |
21-08-25 | 김동환 | TinyBERT: Distilling BERT for Natural Language Understanding | EMNLP | 2020 | NLP | [link] | [link] |
21-08-25 | 손성빈 | Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers | CVPR | 2021 | CV | [link] | [link] |
21-08-18 | 임상훈 | BERT-ATTACK: Adversarial Attack Against BERT Using BERT | EMNLP | 2020 | NLP | [link] | [link] |
21-08-18 | 김기백 | Learning Faithful Representations of Causal Graphs | ACL | 2021 | NLP | [link] | [link] |
21-08-11 | 박주찬 | Unsupervised Monocular Depth Estimation with Left-Right Consistency | CVPR | 2017 | CV | [link] | [link] |
21-08-04 | 정준욱 | 3D Bounding Box Estimation Using Deep Learning and Geometry | CVPR | 2017 | CV | [link] | [link] |
21-08-04 | 이선훈 | DeepCalib: a deep learning approach for automatic intrinsic calibration of wide field-of-view cameras | CVMP | 2018 | CV | [link] | [link] |
21-07-28 | 박용준 | General Multi-label Image Classification with Transformers | CVPR | 2021 | CV | [link] | [link] |
21-07-28 | 김기백 | WARP:Word-level Adversarial ReProgramming | ACL | 2021 | NLP | [link] | [link] |
21-07-21 | 임상훈 | Are Pre-trained Convolutions Better than Pre-trained Transformers? | ACL | 2021 | NLP | [link] | [link] |
21-07-21 | 손성빈 | BEiT: BERT Pre-Training of Image Transformers | arXiv | 2021 | CV | [link] | [link] |
21-07-14 | 김동환 | ALBERT: A Lite BERT for Self-supervised Learning of Language Representations | ICLR | 2020 | NLP | [link] | [link] |
21-07-14 | 박주찬 | Scale-aware Automatic Augmentation for Object Detection | CVPR | 2021 | CV | [link] | [link] |
21-07-07 | 정준욱 | Realtime multi-person 2d pose estimation using part affinity fields | CVPR | 2017 | CV | [link] | [link] |
21-07-07 | 임상훈 | Feature Projection for Improved Text Classification | ACL | 2020 | NLP | [link] | [link] |
21-06-23 | 박용준 | Philosophy of artificial intelligence | - | - | Other | [link] | [link] |
21-06-23 | 이선훈 | 0. 3D 컴퓨터비전(카메라 기초) | - | - | CV | [link] | [link] |
21-06-23 | 박용준 | SSD:Single Shot Multibox Detector | ECCV | 2016 | CV | [link] | [link] |
21-06-16 | 조성웅 | Pre-Training Transformers as Energy-Based Cloze Models | EMNLP | 2020 | NLP | [link] | [link] |
21-06-16 | 손성빈 | Swin Transformer: Hierarchical Vision Transformer using Shifted Windows | arXiv | 2021 | CV | [link] | [link] |
21-06-09 | 김동환 | ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators | ICLR | 2020 | NLP | [link] | [link] |
21-06-09 | 임상훈 | Pay Attention to MLPs | arXiv | 2021 | DL | [link] | [link] |
21-06-02 | 조성웅 | Retrospective Reader for Machine Reading Comprehension | AAAI | 2021 | NLP | [link] | [link] |
21-06-02 | 박주찬 | Learning from Noisy Anchors for One-stage Object Detection | CVPR | 2020 | CV | [link] | [link] |
21-05-26 | 이선훈 | 함수의 극한과 연속 | - | - | Math | [link] | [link] |
21-05-26 | 김동환 | Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward | ACL | 2020 | NLP | [link] | [link] |
21-05-19 | 김기백 | Large Memory Layers with Product keys | NeurIPS | 2019 | NLP | [link] | [link] |
21-05-12 | 정준욱 | Face Recognition A to Z | - | - | CV | [link] | [link] |
21-05-12 | 손성빈 | End-to-End Object Detection with Transformers | ECCV | 2020 | CV | [link] | [link] |
21-05-05 | 김기백 | Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context | ACL | 2019 | NLP | [link] | [link] |
21-05-05 | 조성웅 | Neural Approaches to Conversational AI | Foundations and Trends in Information Retrieval | 2019 | NLP | [link] | [link] |
21-04-28 | 이선훈 | tensorflow-intro | - | - | Math | [link] | [link] |
21-04-28 | 조성웅 | DSTC9 track1: workshop papers | AAAI workshops | 2021 | NLP | [link] | [link] |
21-04-21 | 정준욱 | VinVL: Revisiting Visual Representations in Vision-Language Models | arXiv | 2021 | NLP, CV | [link] | [link] |
21-04-07 | 손성빈 | An Image is Worth 16 x 16 Words: Transformers For Image Recognition at Scale | ICLR | 2021 | CV | [link] | [link] |
21-04-07 | 임상훈 | When Attention Meets Fast Recurrence Training Language Models with Reduce Compute | arXiv | 2021 | NLP | [link] | [link] |
21-03-31 | 박주찬 | Feature Selective Anchor-Free Module for Single-Shot Object Detection | CVPR | 2019 | CV | [link] | [link] |
21-03-31 | 김동환 | Domain Aware Neural Dialog System | arXiv | 2017 | NLP | [link] | [link] |
21-03-24 | 이선훈 | 논리와 증명 | - | - | Math | [link] | [link] |
21-03-24 | 정준욱 | Circle Loss: A Unified Perspective of Pair Similarity Optimization | CVPR | 2020 | CV | [link] | [link] |
21-03-17 | 박용준 | You Only Look Once : Unified, Real-Time Object Detection | CVPR | 2016 | CV | [link] | [link] |
21-03-17 | 김기백 | Simple Recurrent Units for Highly Parallelizable Recurrence | EMNLP | 2018 | NLP | [link] | [link] |
21-03-10 | 손성빈 | RepPoints: Points Set Representation for Object Detection | ICCV | 2019 | CV | [link] | [link] |
21-03-03 | 임상훈 | Language Models with Transformers | arXiv | 2019 | NLP | [link] | [link] |
21-02-24 | 박주찬 | Multiple Anchor Learning for Visual Object Detection | CVPR | 2020 | CV | [link] | [link] |
21-02-17 | 정준욱 | Improved Deep Metric Learning with Multi-class N-pair Loss Objective | NIPS | 2016 | CV | [link] | [link] |
21-02-17 | 박용준 | Image Style Transfer Using Convolutional Neural Networks | CVPR | 2016 | CV | [link] | [link] |
21-02-03 | 손성빈 | Analysis of Anchor-based and Anchor-free Detection | - | - | CV | [link] | [link] |
21-02-03 | 김기백 | Deep contextualized word representations | NAACL | 2018 | NLP | [link] | [link] |
21-01-27 | 이선훈 | COVID-19 Control by Computer Vision Approaches: A Survey | IEEE ACCESS | 2020 | CV | [link] | [link] |
21-01-27 | 임상훈 | Hierarchy-Aware Global Model for Hierarchical Text Classification | ACL | 2020 | NLP | [link] | [link] |
21-01-27 | 김동환 | BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | NAACL | 2018 | NLP | [link] | [link] |
21-01-20 | 정준욱 | YOLOv4:Optimal Speed and Accuracy of Object Detection | arXiv | 2020 | CV | [link] | [link] |
21-01-20 | 박주찬 | Dynamic Anchor Learning for Arbitrary-Oriented Object Detection | arXiv | 2020 | CV | [link] | [link] |
21-01-08 | 박용준 | SmokeNet Satellite Smoke Scene Detection Using Convolutional Neural Network with Spatial and Channel-Wise Attention | Sensors | 2019 | CV | [link] | [link] |
21-01-05 | 이선훈 | Vision‐based garbage dumping action detection for real‐world surveillance platform | ETRI Journal | 2019 | CV | [link] | [link] |
20-12-30 | 김동환 | Attention is All you Need | NIPS | 2017 | NLP | [link] | [link] |
20-12-30 | 손성빈 | Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection | CVPR | 2020 | CV | [link] | [link] |
20-12-16 | 임상훈 | Graph Transformer Networks | NeurIPS | 2019 | ML | [link] | [link] |
20-12-16 | 김기백 | Graph Attention Networks | ICLR | 2018 | ML | [link] | [link] |
20-12-09 | 박주찬 | Align Deep Features for Oriented Object Detection | arXiv | 2020 | CV | [link] | [link] |
20-11-18 | 김기백 | Neural Machine Translation by Jointly Learning to Align and Translate | ICLR | 2015 | NLP | [link] | [link] |
20-11-17 | 이선훈 | Data augmentation using learned transformations for one-shot medical image segmentation | CVPR | 2019 | CV | [link] | [link] |
20-11-11 | 조성웅 | PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization | ICML | 2020 | NLP | [link] | [link] |
20-11-11 | 정준욱 | PROGRESSIVE GROWING OF GANS FOR IMPROVED QUALITY, STABILITY, AND VARIATION | ICLR | 2018 | CV | [link] | [link] |
20-10-28 | 이선훈 | NVIDIA Jetson TX2 architecture | - | - | Other | [link] | [link] |
20-10-28 | 박용준 | Progressive Growing of GANs for Improved Quality, Stability, and Variation | arXiv | 2018 | CV | [link] | [link] |
20-10-21 | 손성빈 | GLAMpoints: Greedily Learned Accurate Match points | ICCV | 2019 | CV | [link] | [link] |
20-10-21 | 김기백 | Attention Is All You Need | NIPS | 2017 | NLP | [link] | [link] |
20-10-14 | 임상훈 | A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine Translation | ACL | 2020 | NLP | [link] | [link] |
20-09-23 | 김동환 | LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection | ICML | 2016 | NLP | [link] | [link] |
20-09-23 | 이선훈 | Transformer Network for Trajectory Forecasting | arXiv | 2020 | CV | [link] | [link] |
20-09-16 | 정준욱 | A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data | AAAI | 2019 | ML | [link] | [link] |
20-09-16 | 박주찬 | Deep Learning for 3D Point Clouds: A Survey | TPAMI | 2020 | CV | [link] | [link] |
20-08-25 | 손성빈 | Rf-net: An end-to-end image matching network based on receptive field | CVPR | 2019 | CV | [link] | [link] |
20-08-25 | 조성웅 | Non-Autoregressive Dialog State Tracking | ICLR | 2020 | NLP | [link] | [link] |
20-08-17 | 이선훈 | Neural Data Server: A Large-Scale Search Engine for Transfer Learning Data | CVPR | 2020 | CV, Other | [link] | [link] |
20-08-17 | 손지원 | Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward | ACL | 2020 | NLP | [link] | [link] |
20-08-11 | 손지원 | Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewards | ACL | 2019 | NLP | [link] | [link] |
20-07-29 | 임상훈 | Deep Learning for Extreme Multi-label Text Classification | SIGIR | 2017 | NLP | [link] | [link] |
20-07-29 | 정준욱 | Unsupervised Representation Learning By Predicting Image Rotations | ICLR | 2018 | CV | [link] | [link] |
20-07-14 | 손성빈 | You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization | arXiv | 2019 | CV | [link] | [link] |
20-07-14 | 박주찬 | SlowFast Networks for Video Recognition | ICCV | 2019 | CV | [link] | [link] |
20-07-07 | 조성웅 | Few-shot Natural Language Generation for Task-Oriented Dialog | arXiv | 2020 | NLP | [link] | [link] |
20-06-16 | 이선훈 | Temporal Segment Networks for Action Recognition in Videos | TPAMI | 2018 | CV | [link] | [link] |
20-06-16 | 이선훈 | Two-Stream Convolutional Networks for Action Recognition in Videos | NIPS | 2014 | CV | [link] | [link] |
20-06-09 | 임상훈 | Representation Learning on Network - Tutorial | WWW | 2018 | DL | [link] | [link] |
20-06-09 | 이선훈 | G-TAD: Sub-Graph Localization for Temporal Action Detection | CVPR | 2020 | CV | [link] | [link] |
20-06-02 | 정준욱 | Improved Training of Wasserstein GANs | NIPS | 2017 | CV | [link] | [link] |
20-06-02 | 박주찬 | Gliding vertex on the horizontal bounding box for multi-oriented object detection | TPAMI | 2020 | CV | [link] | [link] |
20-05-26 | 손지원 | Domain aware Abstractive Text Summarization for Medical Document | BIBM | 2018 | NLP | [link] | [link] |
20-05-20 | 손성빈 | ResNeSt:Split-Attention Networks | arXiv | 2020 | CV | [link] | [link] |
20-05-20 | 이선훈 | Striking the Right Balance with Uncertainty | CVPR | 2019 | CV | [link] | [link] |
20-05-14 | 임상훈 | LARGE BATCH OPTIMIZATION FOR DEEP LEARNING: TRAINING BERT IN 76 MINUTES | ICLR | 2020 | NLP, CV | [link] | [link] |
20-05-07 | 조성웅 | Deep Learning for Dialogue Systems | COLLING | 2018 | NLP | [link] | [link] |
20-05-04 | 이선훈 | What Uncertainty Do We Need in Bayesian Deep Learning for Computer Vision | NIPS | 2017 | CV | [link] | [link] |
20-04-29 | 박주찬 | Deformable Convolutional Networks | ICCV | 2017 | CV | [link] | [link] |
20-04-29 | 이선훈 | Dropout as a bayesian approximation: Representing model uncertainty in deep learning | JMLR | 2016 | DL | [link] | [link] |
20-04-15 | 박주찬 | Learning to Reweight Examples for Robust Deep Learning | ICML | 2018 | CV | [link] | [link] |
20-04-15 | 손성빈 | ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices | CVPR | 2018 | CV | [link] | [link] |
20-04-08 | 이선훈 | Gaussian Process Regression | - | - | Other | [link] | [link] |
20-04-08 | 손지원 | Word Embedding-Based Biomedical Text Summarization | IRICT | 2019 | NLP | [link] | [link] |
20-04-01 | 정준욱 | Progressive Growing of GANs for Improved Quality, Stability, and Variation | ICLR | 2018 | CV | [link] | [link] |
20-03-25 | 조성웅 | ELECTRA: PRE-TRAINING TEXT ENCODERS AS DISCRIMINATORS RATHER THAN GENERATORS | ICLR | 2020 | NLP | [link] | [link] |
20-03-17 | 임상훈 | Concept Pointer Network for Abstractive Summarization | EMNLP | 2019 | NLP | [link] | [link] |
20-03-04 | 정준욱 | Libra R-CNN: Towards Balanced Learning for Object Detection | CVPR | 2019 | CV | [link] | [link] |
20-03-04 | 손지원 | Sequence Level Training with Recurrent Neural Networks | ICLR | 2016 | NLP | [link] | [link] |
20-02-26 | 손성빈 | R-FCN: Object Detection via Region-based Fully Convolutional Networks | NNIPS | 2016 | CV | [link] | [link] |
20-02-26 | 이선훈 | Learning roi transformer for oriented object detection in aerial image | CVPR | 2019 | CV | [link] | [link] |
20-02-18 | 박주찬 | Faster R-CNN : Towards Real-Time Object Detection with Region Proposal Networks | NIPS | 2015 | CV | [link] | [link] |
20-02-12 | 임상훈 | Large-Scale Hierarchical Text Classification with Recursively Regularized Deep Graph-CNN | WWW | 2018 | NLP | [link] | [link] |
20-02-05 | 이선훈 | Biomedical Image Segmentation via Representative Annotation | AAAI | 2019 | CV | [link] | [link] |
20-02-05 | 조성웅 | Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer | arXiv | 2019 | NLP | [link] | [link] |
20-01-29 | 정준욱 | Unsupervised Representation Learning With Deep Convolutional Generative Adversarial Networks | ICLR | 2016 | CV | [link] | [link] |
20-01-22 | 손성빈 | Focal Loss for Dense Object Detection | ICCV | 2017 | CV | [link] | [link] |
20-01-22 | 조성웅 | The Natural Language Decathlon Multitask Learning as Question Answering | arXiv | 2018 | NLP | [link] | [link] |
20-01-15 | 손지원 | Better Rewards Yield Better Summaries: Learning to Summarise Without References | EMNLP | 2019 | NLP | [link] | [link] |
20-01-15 | 정준욱 | VarGFaceNet: An Efficient Variable Group Convolutional Neural Network for Lightweight Face Recognition | CVPR | 2019 | CV | [link] | [link] |
20-01-08 | 이선훈 | Data augmentation using learned transformations for one-shot medical image segmentation | CVPR | 2019 | CV | [link] | [link] |
20-01-08 | 박주찬 | EfficientDet : Scalable and Efficient Object Detection | arXiv | 2019 | CV | [link] | [link] |
19-12-05 | 손지원 | Sentence-BERT:Sentence Embeddings using Siamese BERT-Networks | EMNLP | 2019 | NLP | [link] | [link] |
19-12-05 | 임상훈 | Hierarchical Attention Networks for Document Classification | NAACL | 2016 | NLP | [link] | [link] |
19-12-03 | 정준욱 | Novel Weight Initialization | - | - | DL | [link] | [link] |
19-11-28 | 임상훈 | Graph Learning Network: A Structure Learning Algorithm | ICML Workshop | 2019 | DL | [link] | [link] |
19-11-26 | 박주찬 | Arbitrary-Oriented Scene Text Detection via Rotation proposals | IEEE TMM | 2018 | CV | [link] | [link] |
19-11-26 | 손성빈 | You Only Look Twice: Rapid Multi Scale Object Detection in Satellite Imagery | arXiv | 2018 | CV | [link] | [link] |
19-11-21 | 임상훈 | Inductive Representation Learning on Large Graphs | NIPS | 2017 | NLP | [link] | [link] |
19-11-21 | 정준욱 | Learning Deep Features for Discriminative Localization | CVPR | 2016 | CV | [link] | [link] |
19-11-21 | 이선훈 | MobileNetV2: Inverted Residuals and Linear Bottleneck | CVPR | 2018 | CV | [link] | [link] |
19-11-19 | 손지원 | Extracting UMLS Concepts from Medical Text Using General and Domain-Specific Deep Learning Models | LOUHI | 2019 | CV | [link] | [link] |
19-11-14 | 이선훈 | H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes | IEEE TRANSACTIONS ON MEDICAL IMAGING | 2018 | CV, NLP | [link] | [link] |
19-11-12 | 손지원 | Deep contextualized embeddings for quantifying the informative content in biomedical text summarization | CMPB | 2020 | CV | [link] | [link] |
19-11-12 | 정준욱 | EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks | ICML | 2019 | CV | [link] | [link] |
19-11-07 | 조성웅 | Sentimet Classification using Document Embeddings trained with Cosine Similarity | ACL | 2019 | NLP | [link] | [link] |
19-11-05 | 임상훈 | Graph Convolutional Networks for Text Classification | AAAI | 2019 | NLP | [link] | [link] |
19-11-03 | 이선훈 | Densely Connected Convolutional Networks | CVPR | 2017 | CV | [link] | [link] |
19-10-31 | 정준욱 | AdaCos Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations | CVPR | 2018 | CV | [link] | [link] |
19-10-31 | 손지원 | Deep Reinforced Model for Abstractive Summarization | ICLR | 2018 | NLP | [link] | [link] |
19-10-22 | 박주찬 | Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network | CVPR | 2017 | CV | [link] | [link] |
19-10-15 | 손지원 | MASS: Masked Sequence to Sequence Pre-training for Language Generation | ICML | 2019 | NLP | [link] | [link] |
19-10-15 | 손성빈 | ASSD : Attentive Single Shot Multibox Detector | Computer Vision and Image Understanding | 2019 | CV | [link] | [link] |
19-10-10 | 임상훈 | ALBERT: A Lite BERT for Self-supervised Learning of Language Representations | ICLR | 2020 | NLP | [link] | [link] |
19-10-08 | 손지원 | U-Net: Convolutional Networks for Biomedical Image Segmentation | MICCAI | 2015 | CV | [link] | [link] |
19-10-04 | 이선훈 | minimum description length | - | - | Math | [link] | [link] |
19-10-04 | 임상훈 | Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context | ACL | 2019 | NLP | [link] | [link] |
19-10-04 | 조성웅 | Searching for MobileNetV3 | arxiv | 2019 | CV | [link] | [link] |
19-09-19 | 손지원 | Searching for Effective Neural Extractive Summarization: What Works and What's Nexts | ACL | 2019 | CV, NLP | [link] | [link] |
19-09-19 | 정준욱 | Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition | ECCV | 2018 | CV | [link] | [link] |
19-09-10 | 손지원 | Text Summarization with Pretrained Encoders | EMNLP | 2019 | NLP | [link] | [link] |
19-09-10 | 박주찬 | Fully Convolutional Networks for Semantic Segmentation | CVPR | 2015 | CV | [link] | [link] |
19-09-10 | 임상훈 | XLNet: Generalized Autoregressive Pretraining for Language Understanding | arxiv | 2019 | NLP | [link] | [link] |
19-08-29 | 정준욱 | Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition | ECCV | 2018 | CV | [link] | [link] |
19-08-29 | 조성웅 | MobileNetV2 Inverted Residuals and Linear Bottlenecks | CVPR | 2018 | CV | [link] | [link] |
19-08-15 | 손지원 | Fine-tune BERT for Extractive Summarization | arXiv | 2019 | NLP | [link] | [link] |
19-08-15 | 정준욱 | SSD Single Shot MultiBox Detector | ECCV | 2016 | CV | [link] | [link] |
19-08-08 | 이선훈 | BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | NAACL | 2019 | NLP | [link] | [link] |
19-08-08 | 임상훈 | Attention Augmented Convolutional Networks | arXiv | 2019 | CV | [link] | [link] |
19-08-08 | 손성빈 | You Only Look Once : Unified, Real-Time Object Detection | CVPR | 2016 | CV | [link] | [link] |
19-07-25 | 박주찬 | Fully Convolutional Networks for Semantic Segmentation | CVPR | 2015 | CV | [link] | [link] |
19-07-18 | 손성빈 | 운전자 안정성 향상을 위한 Generative Adversarial Network 기반의 야간도로 영상 변환 시스템 | 방송공학회논문지 | 2018 | CV | [link] | [link] |
19-07-18 | 손지원 | Get To The Point: Summarization with Pointer-Generator Networks | ACL | 2017 | NLP | [link] | [link] |
19-07-10 | 조성웅 | Convolutional Neural Networks for Sentence Classification | EMNLP | 2014 | NLP | [link] | [link] |
19-07-09 | 이선훈 | Attention Is All You Need | NIPS | 2017 | NLP | [link] | [link] |
19-07-04 | 임상훈 | Character-aware neural language models | AAAI | 2016 | NLP | [link] | [link] |
19-07-04 | 박주찬 | 한국어 자모 단위 기반의 Convolution Neural Network를 이용한 텍스트 분류 | 한국정보과학회 학술발표논문집 | 2017 | NLP | [link] | [link] |
19-06-27 | 손지원 | A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents | NAACL | 2018 | NLP | [link] | [link] |
19-06-27 | 조성웅 | Eyemotion: Classifying Facial Expressions in VR Using Eye-Tracking Cameras | WACV | 2019 | CV | [link] | [link] |
19-05-28 | 조성웅 | 한글 및 한국어 정보처리 학술대회 논문집 논문 조사 발표 | - | - | NLP | [link] | [link] |
19-05-14 | 손지원 | SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition | arXiv | 2019 | DL | [link] | [link] |
19-04-16 | 손지원 | 한글 및 한국어 정보처리 학술대회 논문집 논문 조사 발표 | - | - | NLP | [link] | [link] |
19-04-09 | 손지원 | Ranking Sentences for Extractive Summarization with Reinforcement Learning | NAACL-HLT | 2018 | NLP | [link] | [link] |
19-04-09 | 정준욱 | Non-local Neural Networks | CVPR | 2018 | CV | [link] | [link] |
Date | Speaker | Title | Source | Year | Area | Paper | Slides |