SOTAVerified
Home/Computer Vision

Computer Vision

1,775 tasks · View all areas

Papers in this area

Showing 110 of 10 papers

TitleStatusHype
ProxyFusion: Face Feature Aggregation Through Sparse ExpertsCode0
NeuroXAI: Adaptive, robust, explainable surrogate framework for determination of channel importance in EEG applicationCode1
DeepCS-TRD, a Deep Learning-based Cross-Section Tree Ring DetectorCode0
Efficient Deployment of Spiking Neural Networks on SpiNNaker2 for DVS Gesture Recognition Using Neuromorphic Intermediate RepresentationCode0
Visual-Language Model Knowledge Distillation Method for Image Quality Assessment0
SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction0
Long-Short Distance Graph Neural Networks and Improved Curriculum Learning for Emotion Recognition in ConversationCode0
Language Integration in Fine-Tuning Multimodal Large Language Models for Image-Based Regression0
Smart fault detection in satellite electrical power system0
NoHumansRequired: Autonomous High-Quality Image Editing Triplet Mining0
Show:102550
TaskPapersResults
Heart Segmentation300
Lung Nodule Segmentation300
Multimodal Activity Recognition300
Self-supervised Skeleton-based Action Recognition300
Video Matting

Image credit: [https://arxiv.org/pdf/2012.07810v1.pdf](https…

300
Video Synchronization300
3D Object Retrieval

Source: [He et al](https://arxiv.org/pdf/1803.06189v1.pdf)

290
Age Classification290
Anatomical Landmark Detection290
Classifier calibration

Confidence calibration – the problem of predicting probabili…

290
Domain Adaptive Person Re-Identification290
Facial Editing

Image source: [Stitch it in Time: GAN-Based Facial Editing o…

290
Foveation290
Outdoor Localization290
Radar Object Detection

The radar object detection (ROD) task aims to classify and l…

290
Real-time Instance Segmentation

Similar to its parent task, instance segmentation, but with …

290
Vessel Detection290
Video Emotion Recognition290
Video Saliency Prediction290
Weakly-supervised 3D Human Pose Estimation

This task targets at 3D Human Pose Estimation with fewer 3D …

290
Zero-shot Image Retrieval290
Cloth-Changing Person Re-Identification280
Depth Map Super-Resolution

Depth map super-resolution is the task of upsampling depth i…

280
Dichotomous Image Segmentation

Currently, existing image segmentation tasks mainly focus on…

280
LV Segmentation280
Snow Removal280
Split-MNIST280
Supervised Video Summarization

Supervised video summarization rely on datasets with human-l…

280
Synthetic Image Detection

Identify if the image is real or generated/manipulated by an…

280
Unsupervised Few-Shot Image Classification

In contrast to (supervised) few-shot image classification, o…

280
3D Place Recognition

Pointcloud-based place recognition and retrieval

270
Classification Of Hyperspectral Images270
Depth And Camera Motion270
Emotion Cause Extraction270
Segmentation Of Remote Sensing Imagery270
3D dense captioning

Dense captioning in 3D point clouds is an emerging vision-an…

260
3D Face Alignment260
Egocentric Activity Recognition260
Image Retargeting260
Indoor Scene Synthesis260
Interest Point Detection260
NavSim

Data-Driven Non-Reactive Autonomous Vehicle Benchmark. Evalu…

260
Point Cloud Pre-training

Point cloud data represents 3D shapes as a set of discrete p…

260
Reference-based Super-Resolution

Reference-based Super-Resolution aims to recover high-resolu…

260
Video MME260
Connectivity Estimation250
Face Morphing Attack Detection250
Feature Upsampling

Deep features are a cornerstone of computer vision research,…

250
Garment Reconstruction250
Left Ventricle Segmentation250