Hyeongmin Lee

13 Followers

deep learning pr12 tensorflow kr mvp seminar computer vision paper review optical flow video frame interpolation machine learning video deep neural network #pr12 nerf video compression gan image compression unmasking mathematics video feature image captioning version control github git tsne dimension reduction data science word2vec tracking cotracker clip4clip clip model compression ddpm diffusion deep image compression hyperprior view synthesis light field networks information threory information technology entropy compression motion estimation convolutional neural network #deep learning signal prcessing natural language processing

Activity
About

Hyeongmin Lee

Presentations

Word 2 Vec Algorithm

Data Visualization and t-SNE

Git command

[Paper Review] Image captioning with semantic attention

GAN with Mathematics

[Paper Review] Unmasking the abnormal events in video

[Paper Review] A spatio -Temporal Descriptor Based on 3D -Gradients

[Paper Review] Video Frame Interpolation via Adaptive Convolution

[Paper Review] A Middlebury Benchmark & Context-Aware Synthesis for Video Frame Interpolation

[Paper Review] Temporal Generative Adversarial Nets with Singular Value Clipping

Latest Frame interpolation Algorithms

[PR12] Making Convolutional Networks Shift-Invariant Again

PR-214: FlowNet: Learning Optical Flow with Convolutional Networks

PR-228: Geonet: Unsupervised learning of dense depth, optical flow and camera pose

PR-240: Modulating Image Restoration with Continual Levels viaAdaptive Feature Modification Layers

PR-252: Making Convolutional Networks Shift-Invariant Again

Pr266

PR-278: RAFT: Recurrent All-Pairs Field Transforms for Optical Flow

PR-302: NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis

PR-315: Taming Transformers for High-Resolution Image Synthesis

PR-328: End-to-End OptimizedImage Compression

PR-340: DVC: An End-to-end Deep Video Compression Framework

PR-365: Fast object detection in compressed video

PR-376: Softmax Splatting for Video Frame Interpolation

PR-386: Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering

PR-395: Variational Image Compression with a Scale Hyperprior

PR-409: Denoising Diffusion Probabilistic Models

PR-420: Scalable Model Compression by Entropy Penalized Reparameterization

PR-430: CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval

PR-455: CoTracker: It is Better to Track Together