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 1351–1375 of 1723 papers

TitleStatusHype
MLM: A Benchmark Dataset for Multitask Learning with Multiple Languages and ModalitiesCode0
DAWN: Vehicle Detection in Adverse Weather Nature Dataset—0
Factor Graph based 3D Multi-Object Tracking in Point Clouds—0
Global Context Aware Convolutions for 3D Point Cloud Understanding—0
Leveraging Acoustic Images for Effective Self-Supervised Audio Representation LearningCode0
OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets—0
Synthetic and Real Inputs for Tool Segmentation in Robotic Surgery—0
JUMPS: Joints Upsampling Method for Pose Sequences—0
Analogical Image Translation for Fog Generation—0
Exploiting the ConvLSTM: Human Action Recognition using Raw Depth Video-Based Recurrent Neural Networks—0
MVLidarNet: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Views—0
From Real to Synthetic and Back: Synthesizing Training Data for Multi-Person Scene Understanding—0
Where Does It End? - Reasoning About Hidden Surfaces by Object Intersection ConstraintsCode0
SpSequenceNet: Semantic Segmentation Network on 4D Point Clouds—0
Peek-a-Boo: Occlusion Reasoning in Indoor Scenes With Plane Representations—0
FroDO: From Detections to 3D Objects—0
Taskology: Utilizing Task Relations at Scale—0
SUPER: A Novel Lane Detection System—0
FroDO: From Detections to 3D Objects—0
Where Does It End? -- Reasoning About Hidden Surfaces by Object Intersection ConstraintsCode0
Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions—0
MNEW: Multi-domain Neighborhood Embedding and Weighting for Sparse Point Clouds Segmentation—0
ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings—0
One-Shot GAN Generated Fake Face Detection—0
High-Accuracy Facial Depth Models derived from 3D Synthetic Data—0
Show:102550
← PrevPage 55 of 69Next →
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