Boost neural network performance with circular kernels instead of square ones Integrating Circle Kernels into Convolutional Neural...

Transformer handles images, video, point clouds, and audio to understand world Perceiver: General Perception with Iterative Attention...

Object detect, segment, and pose using one tracking framework Do Different Tracking Tasks Require Different Appearance Models? arXiv...

Get absolute distance of object in image regardless of type Representation Based Regression for Object Distance Estimation arXiv paper...

Action recognition by turning videos into an image mosaic An Image Classifier Can Suffice Video Understanding arXiv paper abstract...

Efficiently detect 3D objects in 2D range image with graph convolution kernels To the Point: Efficient 3D Object Detection in the Range...

Getting 3D shapes from a single image Shelf-Supervised Mesh Prediction in the Wild arXiv paper abstract https://arxiv.org/abs/2102.06195...

Quickly identify object in many camera views using tree of neural nets Low-Power Multi-Camera Object Re-Identification using Hierarchical...

Answering questions about an image using outside knowledge KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain...

Get hand interactions in 3D in real-time from monocular video RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB...

Learning by comparing images improved by understanding objects Unsupervised Object-Level Representation Learning from Scene Images arXiv...

Finding prominent objects in images without manual labeled training Large-Scale Unsupervised Object Discovery arXiv paper abstract...

Training with modified data like using 10 times more data How to train your ViT? Data, Augmentation, and Regularization in Vision...

Get 3D pose and shape of people from monocular images THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers arXiv paper abtract...

Survey of continual learning for image classification Online Continual Learning in Image Classification: An Empirical Survey arXiv paper...

Counting new objects in image using only a few examples Learning To Count Everything arXiv paper abstract https://arxiv.org/abs/2104.0839...

Transformer for super-resolution video Video Super-Resolution Transformer arXiv paper abstract https://arxiv.org/abs/2106.06847 arXiv PDF...

Faster segmentation of objects in video with new affinity formula Faster segmentation of objects in video with new affinity formula arXiv...

Real-time 3D face mesh from one camera on phones Real-time Facial Surface Geometry from Monocular Video on Mobile GPUs arXiv paper...

Improved segmentation of objects and regions in images without object proposals Hierarchical Lovász Embeddings for Proposal-free Panoptic...