SOTAVerified

Multi-Object Tracking and Segmentation

Multiple object tracking and segmentation requires detecting, tracking, and segmenting objects belonging to a set of given classes.

(Image and definition credit: Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation, NeurIPS 2021, Spotlight )

Papers

Showing 1120 of 28 papers

TitleStatusHype
Continuous Copy-Paste for One-Stage Multi-Object Tracking and SegmentationCode1
D2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in VideosCode1
BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in VideoCode1
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask LearningCode1
Multi-Object Tracking and Segmentation via Neural Message PassingCode1
Online Multi-Object Tracking and Segmentation with GMPHD Filter and Mask-based Affinity FusionCode1
Weakly Supervised Multi-Object Tracking and Segmentation0
CML-MOTS: Collaborative Multi-task Learning for Multi-Object Tracking and Segmentation0
Deep Learning Techniques for Video Instance Segmentation: A Survey0
DG-Labeler and DGL-MOTS Dataset: Boost the Autonomous Driving Perception0
Show:102550
← PrevPage 2 of 3Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1UNINEXT-HmMOTSA35.7Unverified
2UnicornmMOTSA29.6Unverified
#ModelMetricClaimedVerifiedStatus
1EagerMOTAssA73.75Unverified