Survey of the robustness of computer vision models to image corruptions
Track multiple people and their gaze direction using many edge TPU and pose for privacy with Kwon
Segment objects in videos using pyramid architecture and improved dataset with PAOT
Detect small 3D objects quickly and accurately using dynamic spatial pruning with DSPDet3D
Segment object using one example without training using target-guided attention with PerSAM
Retrieve images using complex text descriptions by Neural Divide-and-Conquer Reasoning with NDCR
Real-time segmentation using improved K-Net architecture with RT-K-Net
Real-time incremental learning of scene light field with novel model and multiple agent with NSLF-OL
Get 3D shape of object by neural reconstruction enhanced with depth from multiple views with CVRecon
Segment dark images by using RAW image data reducing feature noise with LIS
Get 3D shape of object using material and lighting estimates and physics rendering with Neural-PBIR
Survey of video captioning using deep learning
Survey of unsupervised segmentation in new domains for autonomous driving
Get editable 3D objects and new view from monocular RGB-D video by separate models with factorednerf
Survey of radar-camera fusion for object detection and segmentation in autonomous driving
Survey of vision segmentation using transformers
Segment objects which are adjacent or overlap by examining the surrounding region with Su
Real-time object detector RT-DETR beats YOLO in accuracy and speed by efficient multi-scaling
Indoor 3D scene reconstruction using flat surface prior but unknown frame with Popovic
Get 3D shape of object from one image using similar objects from CLIP with ShapeClipper