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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 1641–1650 of 1723 papers

Title	Date	Tasks	Status
False Negative Reduction in Video Instance Segmentation using Uncertainty Estimates	Jun 28, 2021	Depth EstimationInstance Segmentation	CodeCode Available
3D Semantic Segmentation of Modular Furniture using rjMCMC	May 15, 2017	3D Semantic Segmentationfurniture segmentation	CodeCode Available
Uncertainty-aware LiDAR Panoptic Segmentation	Oct 10, 2022	Autonomous DrivingPanoptic Segmentation	CodeCode Available
Facing the Void: Overcoming Missing Data in Multi-View Imagery	May 21, 2022	Classificationimage-classification	CodeCode Available
COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images	Jan 26, 2016	DiversityGeneral Classification	CodeCode Available
CNN-based Lidar Point Cloud De-Noising in Adverse Weather	Dec 9, 2019	Autonomous VehiclesScene Understanding	CodeCode Available
AdaptVision: Dynamic Input Scaling in MLLMs for Versatile Scene Understanding	Aug 30, 2024	Language ModellingLarge Language Model	CodeCode Available
An efficient solution for semantic segmentation: ShuffleNet V2 with atrous separable convolutions	Feb 20, 2019	Autonomous DrivingScene Understanding	CodeCode Available
SCIM: Simultaneous Clustering, Inference, and Mapping for Open-World Semantic Scene Understanding	Jun 21, 2022	ClusteringObject Discovery	CodeCode Available
Extremely Fine-Grained Visual Classification over Resembling Glyphs in the Wild	Aug 25, 2024	Contrastive LearningFine-Grained Image Classification	CodeCode Available

Show:10 25 50

← PrevPage 165 of 173Next →

All datasets Semantic Scene Understanding Challenge (passive actuation & ground-truth localisation)ADE20K val Semantic Scene Understanding Challenge (active actuation & ground-truth localisation)

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	ACRV Baseline	OMQ	0.44	—	Unverified
2	Team VGAI (TCS Research)	OMQ	0.37	—	Unverified
3	Demo_semantic_SLAM	OMQ	0.11	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CPN(ResNet-101)	Mean IoU	46.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ACRV Baseline	OMQ	0.35	—	Unverified