Answer question about an image using structured information graph with SA-VQA SA-VQA: Structured Alignment of Visual and Semantic...

Detect people in top-view, fish-eye images with ARPD ARPD: Anchor-free Rotation-aware People Detection using Topview Fisheye Camera arXiv...

Count objects of any type in an image with only a few examples Iterative Correlation-based Feature Refinement for Few-shot Counting arXiv...

Put partial 3D point clouds into standard orientation with self-supervised ConDor ConDor: Self-Supervised Canonicalization of 3D Pose for...

Real-time 3D object detection on low CPU headsets Realtime 3D Object Detection for Headsets arXiv paper abstract...

Survey of methods to determine camera position A Critical Analysis of Image-based Camera Pose Estimation Techniques arXiv paper abstract...

Survey of transformers for video Video Transformers: A Survey arXiv paper abstract https://arxiv.org/abs/2201.05991v1 arXiv PDF paper...

Improve pedestrian detection by using general object detector with Cascade RCNN Pedestrian Detection: Domain Generalization, CNNs,...

Enhance dim images better and simpler using imperfectly aligned images with CIDN Enhancing Low-Light Images in Real World via Cross-Image...

Better depth and motion from thermal images by improving self-supervised learning Maximizing Self-supervision from Thermal Image for...

Identify better the events and participants in an image with CLIP-Event CLIP-Event: Connecting Text and Images with Event Structures...

Detect known and also unknown objects which are later labeled and added without forgetting Revisiting Open World Object Detection arXiv...

Get eye gaze direction using low-cost camera with edge device Resolving Camera Position for a Practical Application of Gaze Estimation on...

Crop an image based on user text description Repurposing Existing Deep Networks for Caption and Aesthetic-Guided Image Cropping arXiv...

Train object detector on image data without box annotation with Detic Detecting Twenty-thousand Classes using Image-level Supervision...

Recognizing the place shown in an image of a scene despite distracting factors with TransVPR TransVPR: Transformer-based place...

Improved segmenting of objects in a video that are mentioned in a text query with ReferFormer Language as Queries for Referring Video...

Faster restoration of a single non-uniformly blurred image by using local and global data Adaptive Single Image Deblurring arXiv paper...

Survey of vision for locating where an image is captured or where objects are located in an image Visual and Object Geo-localization: A...

Identify regions in road image mentioned in sentence Grounding Linguistic Commands to Navigable Regions arXiv paper abstract...