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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 21–28 of 28 papers

TitleStatusHype
Learning Multi-Object Tracking and Segmentation from Automatic Annotations—0
MeNToS: Tracklets Association with a Space-Time Memory Network—0
MOTS: Multi-Object Tracking and Segmentation—0
MOTS R-CNN: Cosine-margin-triplet loss for multi-object tracking—0
Multi-Object Tracking and Segmentation with a Space-Time Memory Network—0
ReMOTS: Self-Supervised Refining Multi-Object Tracking and Segmentation—0
Temporal-Enhanced Multimodal Transformer for Referring Multi-Object Tracking and Segmentation—0
Track Targets by Dense Spatio-Temporal Position Encoding—0
Show:102550
← PrevPage 3 of 3Next →
All datasetsBDD100K valKITTI MOTS

Benchmark Results

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