Lab. Seminars
| Date | Person | Title |
|---|---|---|
| 2024.08.16 | Mingi | Deep Online Fused Video Stabilization (CVPR'21) |
| 2024.08.16 | Juyeap | RecDiffusion: Rectangling for Image Stitching with Diffusion Models (CVPR'24) |
| 2024.08.16 | Yeongju | Traceable Federated Continual Learning (CVPR'24) |
| 2024.08.08 | Jiwon | Adding Conditional Control to Text-to-Image Diffusion Models (ICCV'23) |
| 2024.08.01 | Hanshuo | YOLOv3: An Incremental Improvement |
| 2024.08.01 | Saad | EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Camera (MICCAI'24) |
| 2024.07.25 | Juyeob | GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis (CVPR'24) |
| 2024.07.25 | Jungmin | Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model (CVPR'24) |
| 2024.07.25 | Kangsan | Zero-1-to-3: Zero-shot On Image to 3D Object (ICCV'23) |
| 2024.07.18 | Jaehyuk | DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis (CVPR'24) |
| 2024.07.18 | Yejin | COLMAP-FREE 3D Gaussian splatting (CVPR'24) |
| 2024.07.10 | Mingi | FreGS: 3D Gaussian Splatting with Progressive Frequency Regularization (CVPR'24) |
| 2024.07.10 | Sumin | 3D Gaussian Splatting for Real-Time Radial Field Rendering (SIGGRAPH'23) |
| 2024.06.26 | Jiwon, Yeongju | CVPR 2024 visit reports |
| 2024.06.04 | Yejin | CROSSFIRE_camera Relocalization On self_supervised features from an Implicit Representation (ICCV'23) |
| 2024.05.28 | Yeongju | ACCURATE RETRAINING-FREE PRUNING FOR PRETRAINED ENCODER-BASED LANGUAGE MODELS (ICLR'24) |
| 2024.05.28 | Kangsan | Self-supervised Super-plane for Neural 3D Reconstruction (CVPR'23) |
| 2024.05.21 | Jungmin | The Fully Convolutional Transformer for Medical Image Segmentation (WACV'23) |
| 2024.05.16 | Saad | Self-Supervised Monocular Depth and Ego-Motion Estimation in Endoscopy: Appearance Flow to the Rescue (MIA'22) |
| 2024.05.07 | Jiwon | Generative Modeling by Estimating Gradients of the Data Distribution (NeurIPS'19) |
| 2024.05.07 | Jaehyuk | Instant Neural Graphics Primitives with a Multiresolution Hash encoding (SIGGRAPH'22) |
| 2024.04.30 | Yejin | DFNet_Enhanve Absolute Pose Regression with Direct Feature Matching (ECCV'22) |
| 2024.04.15 | Mingi | direct-posenet absolute pose regression with photometric consistency (3DV'21) |
| 2024.04.15 | Taewoo | SoildNet: Soiling Degradation Detection in Autonomous Driving (NeurIPS'19 Workshop) |
| 2024.04.08 | Yeongju | DepGraph: Towards Any Structural Pruning (CVPR'23) |
| 2024.04.01 | Kangsan | Neural 3D Scene Reconstruction with the Manhattan-world Assumption (CVPR'22) |
| 2024.03.25 | Saad | Self-Supervised Lightweight Depth Estimation in Endoscopy Combining CNN and Transformer (TMI'24) |
| 2024.03.25 | Jungmin | One-step Diffusion with Distribution Matching Distillation (CVPR'24) |
| 2024.03.07 | Jiwon | On Distillation of Guided Diffusion Models (CVPR'23) |
| 2024.03.07 | Jaehyuk | Neural RGB-D Surface Reconstruction (CVPR'22) |
| 2024.02.28 | Sumin | ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe (arXiv'24) |
| 2024.02.28 | Mingi | Autoregressive Visual Tracking (CVPR'23) |
| 2024.02.14 | Yeongju | Stair Fall Warning System for Wheelchair Users (IEIES2023) |
| 2024.02.14 | Taewoo | Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR'22) |
| 2024.01.30 | Kangsan | FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency (CVPR'23) |
| 2024.01.16 | Jungmin | AdaViT: Adaptive Vision Transformers for Efficient Image Recognition (CVPR'22) |
| 2024.01.16 | Donghyeon | WACV 2024 Visit Report |
| 2024.01.09 | Saad | EndoSLAM Dataset and An Unsupervised Monocular Visual Odometry and Depth Estimation Approach for Endoscopic Videos: Endo-SfMLearner (MIA'21) |
| 2024.01.09 | Jaehyuk | Tri-MipRF: Tri-Mip Representation for Efficient Anti-aliasing Neural Radiance Fields (ICCV'23) |
| 2024.01.03 | Soomin | Vision transformer with Deformable Attraction (CVPR'22) |
| 2023.12.26 | Taewoo | Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentation (NeurIPS'23) |
| 2023.12.26 | Jiwon | Token Merging: Your ViT But Faster (ICLR'23) |
| 2023.12.19 | Minahil | Learning Tracking Representations via Dual-Branch Fully Transformer Networks (ICCVw'21) |
| 2023.12.07 | Eunho | Research Progress, Transformer backbones |
| 2023.11.24 | Kangsan | SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fields (CVPR'23) |
| 2023.11.24 | Saad | Investigating keypoint descriptors for camera relocalization in endoscopy surgery (IJCARS'23) |
| 2023.11.14 | Donghyeon | Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations (ICLR'22) |
| 2023.11.10 | Soomin | Recent VOT papers |
| 2023.10.20 | Eunho, Minahil, Taewoo | ICCV 2023 Visit Report |
| 2023.10.13 | Jaehyuk | IFSeg : Image-free Semantic Segmentation via Vision-Language Model (CVPR'23) |
| 2023.10.06 | Saad | Learning 2D–3D Correspondences To Solve The Blind Perspective-n-Point Problem (CVPR'20) |
| 2023.09.26 | Jiwon | High-fidelity 3D Human Digitization from Single 2K Resolution Images (CVPR'23) |
| 2023.09.26 | Taewoo | HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness (ICCV'23) |
| 2023.09.19 | Jungi | The Majority Can Help the Minority: Context-rich Minority Oversampling for Long-tailed Classification (CVPR'22) |
| 2023.09.05 | Eunsoo | OMNI3D: A Large Benchmark and Model for 3D Object Detection in the Wild (CVPR'23) |
| 2023.09.05 | Donghyeon | Research progress, pruning from scratch via shared pruning module and nuclear norm-based regularization |
| 2023.08.29 | Minahil | Visual Prompt Multi-Modal Tracking (ViPT) (CVPR'23) |
| 2023.08.22 | Dayoung | UNICOM: Universal and Compact Representation Learning for Image Retrieval (ICLR'23) |
| 2023.08.22 | Saad | Fast image-based localization using direct 2D-to-3D matching (ICCV'11) |
| 2023.08.17 | Minho | TensoRF: Tensorial Radiance Fields (ECCV'22) |
| 2023.08.17 | Jungmin | DR2: Diffusion-based Robust Degradation Remover for Blind Face Restoration (CVPR'23) |
| 2023.08.11 | Kangsan | SA3D: Segment Anything in 3D with NeRFs (NeurIPS'23) |
| 2023.08.01 | Seokmin | Multi-Scale Dense Networks for Resource Efficient Image Classification (ICLR'18) |
| 2023.08.01 | Jaehyuk | Bert : Pre-Training of Deep Bidirectional Transformers for Language Understanding (arXiv'18) |
| 2023.07.10 | Jiwon | PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360 (CVPR'23) |
| 2023.07.10 | Jungi | DDIM: Denoising Diffusion Implicit models (ICLR'21) |
| 2023.07.10 | Minahil | RGBT Tracking by Trident Fusion Network (TCSVT) |
| 2023.07.04 | Soomin, Donghyeon | CVPR 2023 Visit Report |
| 2023.07.04 | Suhyeon | Relational Knowledge Distillation (CVPR'19) |
| 2023.06.29 | Kangsan | SUN-RGB D:A RGB-D Scene Understanding Benchmark Suite (CVPR'15) |
| 2023.06.29 | Taewoo | Random Erasing Data Augmentation (AAAI'20) |
| 2023.06.29 | Eunsoo | FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection (ICCVw'21) |
| 2023.06.20 | Minho | PeRFception: Perception using Radiance Fields (NeurIPS'22) |
| 2023.06.01 | Eunho | Research progress, Image Restogration |
| 2023.06.01 | Jaehyuk | Show and Tell : A Neural Image Caption Generator (CVPR'15) |
| 2023.06.01 | Jungmin | High-Resolution Image Synthesis with Latent Diffusion Models (CVPR'22) |
| 2023.05.25 | Seokmin | Taming Transformers for High-Resolution Image Synthesis (CVPR'21) |
| 2023.05.25 | Jiwon | Joint Camera Intrinsic and LiDAR-Camera Extrinsic Calibration (ICRA'23) |
| 2023.05.09 | Saad | Reconstructing Sinus Anatomy from Endoscopic Video - Towards a Radiation-free Approach for Quantitative longitudinal Assessment (MICCAI'20) |
| 2023.05.09 | Dayoung | Training Vision Transformers for Image Retrieval (arXiv'21) |
| 2023.05.09 | Suhyeon | Knowledge Distillation : A Good Teacher Is Patient and Consistent (CVPR'22) |
| 2023.05.02 | Jungi | TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation (ICCV'21) |
| 2023.04.25 | Minahil | Generalized Relation Modeling for Transformer Tracking (CVPR'23) |
| 2023.04.11 | Donghyeon | Research progress, Optimal hyper parameters for EPI |
| 2023.04.04 | Minho | Research progress, Tomato pose estimation using the relationship between tomato and sepal |
| 2023.04.04 | Kangsan | Multimodal Token Fusion for Vision Transformers (CVPR'22) |
| 2023.03.21 | Eunsoo | CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows (CVPR'22) |
| 2023.03.14 | Dayoung | Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing (AAAI'19) |
| 2023.03.14 | Jaehyuk | What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis (ICCV'19) |
| 2023.03.07 | Eunho | Research progress,Decomformer: Decompose self-attention of Transformer for efficient image restoration |
| 2023.02.28 | Seokmin | An Image is Worth 16x16 Words : transformers for image recognition at scale (ICLR'21) |
| 2023.02.28 | Saad | Whole Stomach 3D Reconstruction and Frame Localization From Monocular Endoscope Video (IEEE JTEHM'19) |
| 2023.02.21 | Donghyeon | Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization (IJCAI'20) |
| 2023.02.21 | Minahil | Multi-Adapter RGBT Tracking (CVPRw'19) |
| 2023.02.14 | Suhyeon | Explaining Knowledge Distillation by Quantifying the Knowledge (CVPR'20) |
| 2023.02.14 | Jiwon | Few-shot image generation via cross-domain correspondence (CVPR'21) |
| 2023.01.31 | Eunsoo | VIDT: An Efficient and effective fully transformer-based object detector (ICLR'22) |
| 2023.01.25 | Minho | Depth-supervised NeRF: Fewer Views and Faster Training for Free (CVPR'22) |
| 2023.01.17 | Eunho | RED: Looking for Redundancies for Data-Free Structured Compression of Deep Neural Networks (NeurIPS'21) |
| 2023.01.17 | Saad | RNNSLAM: Reconstructing the 3D colon to visualize missing regions during a colonoscopy (MIA'21) |
| 2023.01.17 | Jungmin | Probabilistic Normal Distributions Transform Representation for Accurate 3D Point Cloud Registration (IROS'17) |
| 2023.01.10 | Minahil | AiATrack: Attention in Attention for Transformer Visual Tracking (ECCV'22) |
| 2023.01.10 | Kangsan | Point-Voxel CNN for Efficient 3D Deep Learning (NeurIPS'19) |
| 2023.01.10 | Dayoung | Scalable Recognition with a Vocabulary Tree (CVPR'06) |
| 2023.01.03 | Jungi | You Only Cut Once: Boosting Data Augmentation with a Single Cut (ICML'22) |
| 2023.01.03 | Seokmin | Denoising Diffusion Probabilistic Models (NeurIPS'20) |
| 2023.01.03 | Donghyeon | When to Prune? A Policy Towards Early Structural Pruning (CVPR'22) |
| 2022.12.28 | Minho | BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotations (CVPR'22) |
| 2022.12.28 | Eunsoo | Focal Length and Object Pose Estimation via Render and Compare (CVPR'22) |
| 2022.12.20 | Soomin | Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework (ECCV'22) |
| 2022.11.15 | Dayoung | Deep convolutional features for image retrieval (ESwA'21) |
| 2022.11.15 | Jaehyuk | Reading Text in the Wild with Convolutional Nerual Networks (IJCV'16) |
| 2022.11.01 | Saad | SAGE: SLAM with Appearance and Geometry Prior for Endoscopy (ICRA'22) |
| 2022.11.01 | Soohyun | Decoupled Knowledge Distillation (CVPR'22) |
| 2022.10.11 | Chung-Gi | Efficient Object Embedding for Spliced Image Retrieval (CVPR'21) |
| 2022.10.04 | Minahil | SwinTrack: A Simple and Strong Baseline for Transformer Tracking (Neurips'22) |
| 2022.10.04 | Jiwon | InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs (TPAMI'22) |
| 2022.09.22 | Eunho | All-In-One Image Restoration for Unknown Corruption (CVPR'22) |
| 2022.09.22 | Dong Hyeon | Revisiting Random Channel Pruning for Neural Network Compression (CVPR'22) |
| 2022.09.13 | Soohyun | Improved Knowledge Distillation via Teacher Assistant (AAAI'20) |
| 2022.09.13 | Eunsoo | Reconstruct Locally, Localize Globally: A Model Free Method for Object Pose Estimation (CVPR'20) |
| 2022.08.31 | Minho | InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering (CVPR'22) |
| 2022.08.31 | Dayoung | Combination of Multiple Global Descriptors for Image Retrieval (arXiv'19) |
| 2022.08.31 | Jungi | population Based Augmentation : Efficient Learning of Augmentation Policy Schedules (ICML'19) |
| 2022.08.31 | Seokmin | Image to Image Translation part 1 (Pix2Pix, CycleGAN, MUNIT, DRIT, FUNIT) |
| 2022.08.24 | Jiwon | Analyzing and Improving the Image Quality of StyleGAN (CVPR'20) |
| 2022.08.16 | Chung-Gi | Video Instance Segmentation using Inter-Frame Communication Transformers (NeurIPS'21) |
| 2022.08.16 | Seokmin | Image to Image Translation part 1 (Pix2Pix, CycleGAN, MUNIT, DRIT, FUNIT) |
| 2022.08.09 | Minahil | Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking (CVPR'21) |
| 2022.08.09 | Seokmin | Particular object retrieval with integral max-pooling of CNN activations (ICLR'16) |
| 2022.08.02 | Dayoung | Particular object retrieval with integral max-pooling of CNN activations (ICLR'16) |
| 2022.08.02 | Eunsoo | Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction Without Convolutions (ICCV'21) |
| 2022.08.02 | Soohyun | Knowledge Distillation with the Reused Teacher Classifier (CVPR'22) |
| 2022.07.25 | Minho | 3D Common Corruptions and Data Augmentation (CVPR'22) |
| 2022.07.25 | Jungi | AutoAugment: Learning Augmentation Policies from Data (CVPR'19) |
| 2022.07.20 | Eunho | Simple Baseline for Image Restoration (ECCV'22) |
| 2022.07.07 | Jiwon | StarGAN v2: Diverse Image Synthesis for Multiple Domains (CVPR'20) |
| 2022.07.07 | Chung-Gi | End-to-End Multi-Person Pose Estimation with Transformers (CVPR'22) |
| 2022.06.30 | Dong Hyeon | Neuron Merging Compensating for Pruned Neurons (NeurIPS'20) |
| 2022.06.30 | Minahil | Transformer-based Dual Relation Graph for Multi-label Image Recognition (ICCV'21) |
| 2022.05.31 | Eunho | Transformer in vision tasks. |
| 2022.05.31 | Seokmin | SinGAN: Learning a Generative Model from a Single Natural Image (ICCV'19) |
| 2022.05.24 | Eunsoo | Cylindrical Convolution Networks for Joint Object Detection and Viewpoint Estimation (CVPR'20) |
| 2022.05.24 | Soomin | MixFormer: End-to-End Tracking with Iterative Mixed Attention (CVPR'22) |
| 2022.05.17 | Hogeol | Stereo Visual Inertial LiDAR Simultaneous Localization and Mapping (IROS'19) |
| 2022.05.10 | Minho | TransPose: Keypoint Localization via Transformer (ICCV'21) |
| 2022.05.03 | Dayoung | Contextual similarity aggregation with self attention for visual re ranking (NIPS'21) |
| 2022.04.12 | Donghyeon | Network Pruning via Performance Maximization (CVPR'21) |
| 2022.04.12 | Seokmin | StarGAN v2: Diverse Image Synthesis for Multiple Domains (CVPR'20) |
| 2022.04.05 | Sanghyeop | Semantic Histogram Based Graph Matching for Real-Time Multi-Robot Global Localization in Large Scale Environment (RA-L'21) |
| 2022.04.05 | Chung-Gi | Pose Recognition With Cascade Transformers (CVPR'21) |
| 2022.03.29 | Soohyun | CondLaneNet: A Top-To-Down Lane Detection Framework Based on Conditional Convolution (ICCV'21) |
| 2022.03.29 | Junbeom | Path Planning for Autonomous Mobile Robots: A Review (MDPI Sensors'21) |
| 2022.03.22 | Eunho | Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (ICCV'21) |
| 2022.03.22 | Minahil | Query2Label: A Simple Transformer Way to Multi-Label Classification (arXiv'21) |
| 2022.03.17 | Eunsoo | Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation (arXiv'21) |
| 2022.03.17 | Jiwon | Few-Shot Adversarial Learning of Realistic Neural Talking Head Models (ICCV'19) |
| 2022.03.10 | Minho | SSimple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation (CVPR'21) |
| 2022.03.10 | Junki | Self6D: Self-Supervised Monocular 6D Object Pose Estimation (ECCV'20) |
| 2022.03.03 | Dayoung | Striking the Right Balance With Uncertainty (CVPR'19) |
| 2022.02.22 | Chung-Gi | HOTR: End-to-End Human-Object Interaction Detection with Transformers (CVPR'21) |
| 2022.02.22 | Hogeol | SurfelMeshing: Online Surfel-Based Mesh Reconstruction (TPAMI'19) |
| 2022.02.08 | Sanghyeop | Deep ChArUco: Dark ChArUco Marker Pose Estimation (CVPR'19) |
| 2022.02.08 | Eunsoo | Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild (ECCV'20) |
| 2022.01.19 | Soomin | Transformer Tracking (CVPR'21) |
| 2022.01.19 | Eunho | NBNet: Noise Basis Learning for Image Denoising with Subspace Projection (CVPR'21) |
| 2022.01.11 | Dayoung | Class-Balanced Loss Based on Effective Number of Samples (CVPR'19) |
| 2022.01.11 | Donghyeon | DHP: Differentiable Meta Pruning via Hypernetworks (ECCV'20) |
| 2022.01.11 | Chung-Gi | Deformable DETR: DEformable TRansformers for end-to-end object detection (ICLR'21) |
| 2022.01.05 | Sanghyeop | Superline: A Robust Line Segment Feature for visual SLAM (IROS'21) |
| 2022.01.05 | Seokmin | StyleCLIP Text-Driven Manipulation of StyleGAN Imagery (arXiv'21) |
| 2021.12.21 | Minahil | Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification (CVPR'17) |
| 2021.12.15 | Eunsoo | Few-shot Learning via Embedding Adaptation With Set-to-Set Functions |
| 2021.11.23 | Hogeol | SP-SLAM : Surfel-Point Simultaneous Localization And Mapping (TMECH'21) |
| 2021.11.23 | Sanghyeop | DOT: Dynamic Object Tracking for Visual SLAM (ICRA'21) |
| 2021.11.16 | Minahil | GM-MLIC Graph Matching based Multi-Label Image Classification (IJCAI'21) |
| 2021.11.09 | Minho | Efficient and Robust Orientation Estimation of Strawberries for Fruit Picking Applications (ICRA'21) |
| 2021.11.09 | Soomin | SORT (Simple Online and Realtime Tracking) (ICIP'16) |
| 2021.11.09 | Eunho | Uformer : A General U-Shaped Transformer for Image Restoration (arXiv'21) |
| 2021.11.02 | Chung-Gi | Training data-efficient image transformers & distillation through attention(DeiT) (ICML'21) |
| 2021.10.26 | Sanghyeop | Exploiting Semantic and Public Prior Information in MonoSLAM (IROS'20) |
| 2021.10.07 | Minahil | A Shared Multi-Attention Framework for Multi-Label Zero-Shot Learning (CVPR'20) |
| 2021.10.07 | Dayoung | 3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training (AAAI'20) |
| 2021.09.29 | Eunho | Enhanced Dual Adversarial Network for Real Image Noise Removal and Generation using Edge Loss Function (ICCAS'21) |
| 2021.09.29 | Donghyeon | MetaDistiller: Network Self-Boosting via Meta-Learned Top-Down Distillation (ECCV'20) |
| 2021.09.07 | Chung-Gi | End-to-End Object Detection with Transformers (ECCV'20) |
| 2021.09.07 | Seokmin | Unpaired image-to-image translation using Cycle-Consistent Adversarial Network (ICCV'17) |
| 2021.08.31 | Eunsoo | Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection (CVPR'21) |
| 2021.08.25 | Minahil | General Multi-label Image Classification with Transformers (CVPR'21) |
| 2021.08.19 | Eunho | Progressive Growing of GANs for Improved Quality, Stability, And Variation (ICLR'18) |
| 2021.08.13 | Sanghyeop | Monocular Camera Localization in Prior LIDAR Maps with 2D-3D Line Correspondences (IROS'20) |
| 2021.08.13 | Dong Hyeon | Designing Network Design Spaces (CVPR'20) |
| 2021.08.13 | Hogeol | Robust 3D-SLAM with Tight RGB-D-Inertial Fusion (Chinese Control Conference'19) |
| 2021.07.28 | Minahil | Orderless Recurrent Models for Multi-label Classification (CVPR'20) |
| 2021.07.28 | Seokmin | Playing Atari with Deep Reinforcement Learning (NIPS workship'13) |
| 2021.07.20 | Eunho | You Only Look Once (YOLO) (CVPR'16, CVPR'17, arXiv'18) |
| 2021.07.13 | Chung-Gi | An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (ICLR'21) |
| 2021.07.13 | Minho | Fruit Localization and Environment Perception for Strawberry Harvesting Robots (IEEE Access'19) |
| 2021.07.06 | Minahil | Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition (ICCV'19) |
| 2021.07.06 | Dong Hyeon | Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields (CVPR'17) |
| 2021.06.28 | Sanghyeop | DeepFusion:Real-Time Dense 3D Reconstruction for Monocular SLAM using Single-View Depth and Gradient Predictions (ICRA'19) |
| 2021.06.28 | Hogeol | BAD SLAM : Bundle Adjusted Direct RGB-D SLAM (CVPR'19) |
| 2021.06.22 | Eunho | MetaPruning:Meta Learning for Automatic Neural Network Channel Pruning (ICCV'19) |
| 2021.06.16 | Chung-Gi | BERT & GPT ( Pre-trained Model in NLP) |
| 2021.05.25 | Sanghyeop | GEN-SLAM: Generative Modeling for Monocular Simultaneous Localization and Mapping (ICRA'19) |
| 2021.05.18 | Minahil | Fast Graph Convolution Network Based Multi-Label Image Recognition via Cross-modal Fusion (CIKM'20) |
| 2021.05.18 | Hogeol | FAST ICP-SLAM for a Bi-steerable Mobile Robot in large environments (ICAR'15) |
| 2021.05.11 | Eunho | DMCP: Differentiable Markov Channel Pruning for Neural Networks (CVPR'20) |
| 2021.05.11 | Junhyuk | End-to-End Object Detection with Transformers (ECCV'20) |
| 2021.05.03 | Junhyung | Infrared small target detection |
| 2021.04.27 | Yunseok | License Plate Detection and Recognition in Unconstrained Scenarios (ECCV'18) |
| 2021.04.27 | Chung-Gi | Attention Is All You Need (NIPS'17) |
| 2021.04.06 | Junki | CosyPose: Consistent multi-view multi-object 6D pose estimation (ECCV'20) |
| 2021.04.06 | Sanghyeop | SaD-SLAM: A Visual Based on Semantic and Depth Information (IROS'20) |
| 2021.03.30 | Hogeol | Lightweight 3D Localization and Mapping for Solid-State LiDAR (RA-L'21) |
| 2021.03.30 | Minahil | Large-scale multi-label classification using unknown streaming images (PR'20) |
| 2021.03.16 | Soomin | Robust Lane Detection from Continuous Driving Scenes Using Deep Neural Networks (IEEE TVT'20) |
| 2021.03.16 | Eunho | Multi-Stage Progressive Image Restoration (CVPR'21) |
| 2021.03.09 | Junhyuk | Generative Adversarial Nets (NIPS'14) |
| 2021.03.09 | Sanghyeop | Loosely-Coupled Semi-Direct Monocular SLAM (RA-L'19) |
| 2021.02.23 | Heejae | Learning Spatiotemporal Features with 3D Convolutional Networks (ICCV'15) |
| 2021.02.23 | Minahil | Multi-Label Image Classification by Feature Attention Network (IEEE Access'20) |
| 2021.02.17 | Yunseok | Automatic Vehicle License Plate Recognition Using Optimal K-Means With Convolutional Neural Network for Intelligent Transportation Systems (IEEE Access'20) |
| 2021.02.17 | Hogeol | Intensity Scan Context: Coding Intensity and Geometry Relations for Loop Closure Detection (ICRA'20) |
| 2021.02.17 | Eunho | Channel Pruning via Automatic Structure Search (IJCAI'20) |
| 2021.02.04 | Sanghyeop | CNN-SVO: Improving the Mapping in Semi-Direct Visual Odometry Using Single-Image Depth Prediction (ICRA'19) |
| 2021.01.27 | Junki | Deep Fitting Degree Scoring Network for Monocular 3D Object Detection (CVPR'19) |
| 2021.01.27 | Minahil | Visual Attention Consistency under Image Transforms for Multi-Label Image Classification (CVPR'19) |
| 2021.01.20 | Eunho | Real image denoising with feature attention (ICCV'19) |
| 2021.01.14 | Sanghyeop | Robust Stereo Visual Inertial Odometry for Fast Autonomous Flight (RA-L'18) |
| 2021.01.14 | Hansu | Fully-Convolutional Siamese Networks for Object Tracking (ECCVw'16) |
| 2021.01.14 | Junhyuk | NetVLAD: CNN architecture for weakly supervised place recognition (CVPR'16) |
| 2021.01.14 | Hogeol | A Portable 3D LIDAR-based System for Long-term and Wide-area People Behavior Measurement (IJARS'19) |
| 2021.01.06 | Junki | Fast Single Shot Detection and Pose Estimation (3DV'16) |
| 2021.01.06 | Minahil | Visual Attention in Multi-Label Image Classification (CVPRw'19) |
| 2020.12.29 | Eunho | Toward Convolutional Blind Denoising of Real Photographs (CVPR'19) |
| 2020.12.29 | Soomin | Ultra Fast Structure-aware Deep Lane Detection (ECCV'20) |
| 2020.12.23 | Sanghyeop | CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction (CVPR'17) |
| 2020.12.23 | Hogeol | LOAM: Lidar Odometry and Mapping in Real-time (RSS'14) |
| 2020.11.25 | Minahil | Learning a Deep ConvNet for Multi-label Classification with Partial Labels Layout (CVPR'19) |
| 2020.11.25 | Junhyuk | Spherical-Model-Based SLAM on Full-View Images for Indoor Environments (Applied Sciences, 2018) |
| 2020.11.18 | Heejae | AON : Towards Arbitrarily-Oriented Text Recognition (CVPR'18) |
| 2020.11.18 | Eunho | Towards Efficient Model Compression via Learned Global Ranking (CVPR'20) |
| 2020.11.11 | Sanghyeop | DeepLens: Shallow Depth of Field from A Single Image (SIGGRAPH ASIA'18) |
| 2020.11.04 | Junki | Hand Gesture Recognition with 3D Convolutional Neural Networks (CVPR'15) |
| 2020.11.04 | Minahil | Multi-Label classification with Label Graph Superimposing (AAAI'20) |
| 2020.10.28 | Eunho | Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation (ICCV'19) |
| 2020.10.14 | Hogeol | Parallel Tracking and Mapping for Small AR Workspaces (ISMAR'07) |
| 2020.09.28 | Sanghyeop | VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator (TRO'18) (part 2) |
| 2020.09.23 | Minahil | Multi-label image recognition with graph convolutional networks (CVPR'19) |
| 2020.09.16 | Eunho | DARTS: Differentiable Architecture Search (ICLR'19) |
| 2020.09.09 | Junhyuk | ORB-SLAM: A Versatile and Accurate Monocular SLAM System (TRO'15) |
| 2020.09.02 | Minahil | CNN-RNN: A Unified Framework for Multi-label Image Classification (CVPR'16) |
| 2020.08.26 | Hogeol | Tangent Convolutions for Dense Prediction in 3D (CVPR'18) |
| 2020.08.19 | Sanghyeop | VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator (TRO'18) | 2020.08.11 | Heejae | Shape Robust Text Detection with Progressive Scale Expansion Network (CVPR'19) | 2020.08.11 | Minahil | Fixing the train-test Resolution discrepancy (NeurIPS'19) | 2020.08.11 | Eunho | AutoPrune: Automatic Network Pruning by Regularizing Auxiliary Parameters (NeurIPS'19) | 2020.07.30 | Hogeol | Mask R-CNN (ICCV'17) | 2020.07.30 | Junhyuk | Visual Odometry (CVPR'04) | 2020.07.22 | Minhyuk | FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19) | 2020.07.22 | Sanghyeop | Robust High Accuracy Visual-Inertial-Laser SLAM System (IROS'19) | 2020.07.15 | Eunho | Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration (CVPR'19) | 2020.07.15 | Minahil | EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (ICML'19) | 2020.02.12 | Eunho | Cross-stitch Networks for Multi-task Learning (CVPR'16) | 2020.02.12 | Heejae | Reading Text in the Wild with Convolutional Neural Networks (IJCV'15) | 2020.02.12 | Minhyuk | CADP: A Novel Dataset for CCTV Traffic Camera based Accident Analysis (AVSS'18) | 2020.02.12 | Duwan | DCT-Based Iris Recognition (TPAMI'07) | 2020.02.05 | Sanghyeop | Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints (CVPR'18) | 2020.01.29 | Eunho | Ene-to-End Multi-Task Leanring with Attention (CVPR'19) | 2020.01.29 | Minjun & Duwan | Efficient Iris Recognition by Chracterizing Key Local Variations (TIP'04) | 2020.01.29 | Minhyuk | Real-world Anomaly Detection in Surveillance Videos (CVPR'18) | 2020.01.15 | Eunho | Deep Compression: Compressing deep neural networks with pruning, trained quantization and huffman coding (ICLR'16) | 2020.01.15 | Heejae | Textboxes: A fast text detector with a single deep neural network (AAAI'17) | 2019.12.30 | Sanghyeop | MegaDepth:Learning Single-Vide Depth Prediction from Internet Photos (CVPR'18) | 2019.12.30 | Eunho | Deep Elastic Networks with Model Selection for Multi-Task Learning (ICCV'19) |