Survey on improving efficiency of computer vision recogntion using deep learning Efficient Visual Recognition with Deep Neural Networks:...

Efficiently identify people in image in one stage without separate detection step Efficient Person Search: An Anchor-Free Approach arXiv...

Answer question about an image using text in scene to find external knowledge External Knowledge Augmented Text Visual Question Answering...

Camera looking at blank wall can determine number of people and activity What You Can Learn by Staring at a Blank Wall arXiv paper...

Super-resolution video using non-neighboring frames without frame alignment Memory-Augmented Non-Local Attention for Video...

More accurate action recognition in videos by using the identities of people Identity-aware Graph Memory Network for Action Detection...

Restore image by removing artifacts superimposed in an unknown manner Blind Image Decomposition arXiv paper abstract...

Real-time YOLOP detects traffic object, drivable area, and road lane YOLOP: You Only Look Once for Panoptic Driving Perception arXiv...

Find location of image anomalies using neural net trained on simulated anomalies DRÆM -- A discriminatively trained reconstruction...

Better 3D reconstruction without exact model match by using database of patches Patch2CAD: Patchwise Embedding Learning for In-the-Wild...

Improve thermal IR images using neural net to model physics and influence of scene Thermal Image Processing via Physics-Inspired Deep...

Detect anomaly in video by reconstructing motion and frame predicting A Hybrid Video Anomaly Detection Framework via Memory-Augmented...

Segmentation system marks unknown objects which are then incrementally learned Deep Metric Learning for Open World Semantic Segmentation...

Segment humans in image after self-supervised training on multiple views Self-supervised Human Detection and Segmentation via Multi-view...

Segmenting objects in images with transformers SOTR: Segmenting Objects with Transformers arXiv paper abstract...

Dense depth in crowded dynamic scenes using sparse depth and monocular color images DnD: Dense Depth Estimation in Crowded Dynamic Indoor...

Get segmented bird's-eye view of a scene from one frontal image Bird's-Eye-View Panoptic Segmentation Using Monocular Frontal View Images...

Building detection in high-resolution satellite images Continental-Scale Building Detection from High Resolution Satellite Imagery arXiv...

Remove haze in a single image by using three components From Synthetic to Real: Image Dehazing Collaborating with Unlabeled Real Data...

Get depth in videos where the objects and the camera move Consistent Depth of Moving Objects in Video arXiv paper abstract...