SOTAVerified

Scene Understanding

Scene understanding involves interpreting the visual information of a scene, including objects, their spatial relationships, and the overall layout. It goes beyond simple object recognition by considering the context and how objects relate to each other and the environment.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1551–1600 of 1723 papers

TitleStatusHype
A Minimalist Approach to Type-Agnostic Detection of Quadrics in Point Clouds—0
Trajectory-based Scene Understanding using Dirichlet Process Mixture Model—0
General-Purpose Deep Point Cloud Feature ExtractorCode0
Indoor Scene Understanding in 2.5/3D for Autonomous Agents: A Survey—0
Learning Scene Gist with Convolutional Neural Networks to Improve Object Recognition—0
Structured Label Inference for Visual UnderstandingCode0
Scenarios: A New Representation for Complex Scene Understanding—0
Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning AbstractionsCode0
Recognizing Material Properties from Images—0
Depth Not Needed - An Evaluation of RGB-D Feature Encodings for Off-Road Scene Understanding by Convolutional Neural Network—0
Object segmentation in depth maps with one user click and a synthetically trained fully convolutional network—0
Boundary Seeking GANs—0
Spatial As Deep: Spatial CNN for Traffic Scene UnderstandingCode0
Self-Supervised Relative Depth Learning for Urban Scene Understanding—0
Why my photos look sideways or upside down? Detecting Canonical Orientation of Images using Convolutional Neural Networks—0
Feature discovery and visualization of robot mission data using convolutional autoencoders and Bayesian nonparametric topic models—0
Small Drone Field Experiment: Data Collection & Processing—0
Grounded Objects and Interactions for Video Captioning—0
Natural Language Guided Visual Relationship Detection—0
HyKo: A Spectral Dataset for Scene Understanding—0
ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic SegmentationCode0
SceneNet RGB-D: Can 5M Synthetic Images Beat Generic ImageNet Pre-Training on Indoor Segmentation?—0
Semantic Line Detection and Its ApplicationsCode1
The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes—0
Dense RGB-D semantic mapping with Pixel-Voxel neural network—0
Hierarchical Scene Parsing by Weakly Supervised Learning with Image Descriptions—0
J-MOD^2: Joint Monocular Obstacle Detection and Depth Estimation—0
Matterport3D: Learning from RGB-D Data in Indoor EnvironmentsCode0
Direction-Aware Semi-Dense SLAM—0
Automatic Ground Truths: Projected Image Annotations for Omnidirectional Vision—0
Reasoning with shapes: profiting cognitive susceptibilities to infer linear mapping transformations between shapes—0
Semantic Foggy Scene Understanding with Synthetic Data—0
3D Pose Regression using Convolutional Neural Networks—0
Deep Scene Text Detection with Connected Component Proposals—0
BlitzNet: A Real-Time Deep Network for Scene UnderstandingCode0
Fast Scene Understanding for Autonomous DrivingCode0
Semantic Augmented Reality Environment with Material-Aware Physical Interactions—0
Dual-Glance Model for Deciphering Social RelationshipsCode0
Scene Graph Generation from Objects, Phrases and Region CaptionsCode0
Relationship Proposal Networks—0
Weakly Supervised Affordance DetectionCode0
Neural Scene De-Rendering—0
Deep Video Deblurring for Hand-Held CamerasCode0
Segmentation Guided Attention Networks for Visual Question Answering—0
LinkNet: Exploiting Encoder Representations for Efficient Semantic SegmentationCode1
Efficient ConvNet for Real-time Semantic SegmentationCode0
Dilated Residual NetworksCode0
Towards seamless multi-view scene analysis from satellite to street-level—0
Classification of Aerial Photogrammetric 3D Point Clouds—0
DepthCut: Improved Depth Edge Estimation Using Multiple Unreliable Channels—0
Show:102550
← PrevPage 32 of 35Next →
All datasetsSemantic Scene Understanding Challenge (passive actuation & ground-truth localisation)ADE20K valSemantic Scene Understanding Challenge (active actuation & ground-truth localisation)

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ACRV BaselineOMQ0.44—Unverified
2Team VGAI (TCS Research)OMQ0.37—Unverified
3Demo_semantic_SLAMOMQ0.11—Unverified
#ModelMetricClaimedVerifiedStatus
1CPN(ResNet-101)Mean IoU46.3—Unverified
#ModelMetricClaimedVerifiedStatus
1ACRV BaselineOMQ0.35—Unverified