Thread by @stephenwithavee

...a bit more #PapersThatMakeYouGoHmmm this week! (cs.CV just caught my attention.)

A-NeRF: Surface-free Human 3D Pose Refinement via Neural Rendering

sciencewise.info/bookmarks/2102…

Adversarial Segmentation Loss for Sketch Colorization

sciencewise.info/bookmarks/2102…

SWAGAN: A Style-based Wavelet-driven Generative Model

sciencewise.info/bookmarks/2102…

L-SNet: from Region Localization to Scale Invariant Medical Image Segmentation

sciencewise.info/bookmarks/2102…

Explainability in CNN Models By Means of Z-Scores

sciencewise.info/bookmarks/2102…

Corner Cases for Visual Perception in Automated Driving: Some Guidance on Detection Approaches

sciencewise.info/bookmarks/2102…

UAV Localization Using Autoencoded Satellite Images

sciencewise.info/bookmarks/2102…

Deep Iteration Assisted by Multi-level Obey-pixel Network Discriminator (DIAMOND) for Medical Image Recovery

sciencewise.info/bookmarks/2102…

Automated Video Labelling: Identifying Faces by Corroborative Evidence

sciencewise.info/bookmarks/2102…

Training Vision Transformers for Image Retrieval

sciencewise.info/bookmarks/2102…

Exploiting Depth Information for Wildlife Monitoring

sciencewise.info/bookmarks/2102…

Application of Yolo on Mask Detection Task

sciencewise.info/bookmarks/2102…

Regional Attention with Architecture-Rebuilt 3D Network for RGB-D Gesture Recognition

sciencewise.info/bookmarks/2102…

H3D: Benchmark on Semantic Segmentation of High-Resolution 3D Point Clouds and textured Meshes from UAV LiDAR and Multi-View-Stereo

sciencewise.info/bookmarks/2102…

Culture-inspired Multi-modal Color Palette Generation and Colorization: A Chinese Youth Subculture Case

sciencewise.info/bookmarks/2102…

Sequential vessel segmentation via deep channel attention network

sciencewise.info/bookmarks/2102…

Deep learning architectural designs for super-resolution of noisy images

sciencewise.info/bookmarks/2102…

VINS: Visual Search for Mobile User Interface Design

sciencewise.info/bookmarks/2102…

D2A U-Net: Automatic Segmentation of COVID-19 Lesions from CT Slices with Dilated Convolution and Dual Attention Mechanism

sciencewise.info/bookmarks/2102…

SG2Caps: Revisiting Scene Graphs for Image Captioning

sciencewise.info/bookmarks/2102…

How Unique Is a Face: An Investigative Study

sciencewise.info/bookmarks/2102…

Dynamic Neural Networks: A Survey

sciencewise.info/bookmarks/2102…

Diverse Single Image Generation with Controllable Global Structure though Self-Attention

sciencewise.info/bookmarks/2102…

Referring Segmentation in Images and Videos with Cross-Modal Self-Attention Network

sciencewise.info/bookmarks/2102…

Visual Search at Alibaba

sciencewise.info/bookmarks/2102…

Virtual ID Discovery from E-commerce Media at Alibaba: Exploiting Richness of User Click Behavior for Visual Search Relevance

sciencewise.info/bookmarks/2102…

Large Scale Long-tailed Product Recognition System at Alibaba

sciencewise.info/bookmarks/2102…

End-to-end Generative Zero-shot Learning via Few-shot Learning

sciencewise.info/bookmarks/2102…

Soccer Event Detection Using Deep Learning

sciencewise.info/bookmarks/2102…

TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation

sciencewise.info/bookmarks/2102…

Towards Accurate RGB-D Saliency Detection with Complementary Attention and Adaptive Integration

sciencewise.info/bookmarks/2102…

An Efficient Framework for Zero-Shot Sketch-Based Image Retrieval

sciencewise.info/bookmarks/2102…

Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch

sciencewise.info/bookmarks/2102…

One-shot Face Reenactment Using Appearance Adaptive Normalization

sciencewise.info/bookmarks/2102…

Iconographic Image Captioning for Artworks

sciencewise.info/bookmarks/2102…

Machine Learning Methods for Histopathological Image Analysis: A Review

sciencewise.info/bookmarks/2102…

DPointNet: A Density-Oriented PointNet for 3D Object Detection in Point Clouds

sciencewise.info/bookmarks/2102…

Adversarial Imaging Pipelines

sciencewise.info/bookmarks/2102…

CMS-LSTM: Context-Embedding and Multi-Scale Spatiotemporal-Expression LSTM for Video Prediction

sciencewise.info/bookmarks/2102…

Sill-Net: Feature Augmentation with Separated Illumination Representation

sciencewise.info/bookmarks/2102…

MOTS R-CNN: Cosine-margin-triplet loss for multi-object tracking

sciencewise.info/bookmarks/2102…

IC Networks: Remodeling the Basic Unit for Convolutional Neural Networks

sciencewise.info/bookmarks/2102…

Switching Variational Auto-Encoders for Noise-Agnostic Audio-visual Speech Enhancement

sciencewise.info/bookmarks/2102…

Unsupervised Novel View Synthesis from a Single Image

sciencewise.info/bookmarks/2102…

Applications of Machine Learning in Document Digitisation

sciencewise.info/bookmarks/2102…

CharacterGAN: Few-Shot Keypoint Character Animation and Reposing

sciencewise.info/bookmarks/2102…

Real-World Super-Resolution of Face-Images from Surveillance Cameras

sciencewise.info/bookmarks/2102…

Bidirectional Multi-scale Attention Networks for Semantic Segmentation of Oblique UAV Imagery

sciencewise.info/bookmarks/2102…

Instance and Panoptic Segmentation Using Conditional Convolutions

sciencewise.info/bookmarks/2102…

Commonsense Knowledge Aware Concept Selection For Diverse and Informative Visual Storytelling

sciencewise.info/bookmarks/2102…

Automated Rip Current Detection with Region based Convolutional Neural Networks

sciencewise.info/bookmarks/2102…

Learning the Update Operator for 2D/3D Image Registration

sciencewise.info/bookmarks/2102…

A Collaborative Visual SLAM Framework for Service Robots

sciencewise.info/bookmarks/2102…

@threadreaderapp unroll