REVIEW 4 cited by
MOTRv3: Release-Fetch Supervision for End-to-End Multi-Object Tracking
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Although end-to-end multi-object trackers like MOTR enjoy the merits of simplicity, they suffer from the conflict between detection and association seriously, resulting in unsatisfactory convergence dynamics. While MOTRv2 partly addresses this problem, it demands an additional detection network for assistance. In this work, we serve as the first to reveal that this conflict arises from the unfair label assignment between detect queries and track queries during training, where these detect queries recognize targets and track queries associate them. Based on this observation, we propose MOTRv3, which balances the label assignment process using the developed release-fetch supervision strategy. In this strategy, labels are first released for detection and gradually fetched back for association. Besides, another two strategies named pseudo label distillation and track group denoising are designed to further improve the supervision for detection and association. Without the assistance of an extra detection network during inference, MOTRv3 achieves impressive performance across diverse benchmarks, e.g., MOT17, DanceTrack.
Forward citations
Cited by 4 Pith papers
-
To New Beginnings: A Survey of Unified Perception in Autonomous Vehicle Software
A taxonomy that classifies unified perception methods in autonomous driving into Early, Late, and Full Unified Perception based on task integration, tracking formulation, and representation flow.
-
Disentangling Instance and Scene Contexts for 3D Semantic Scene Completion
A dual-stream BEV architecture that separates instance and scene class queries achieves state-of-the-art mIoU of 17.35 on SemanticKITTI and 20.55 on SSCBench-KITTI-360.
-
USVTrack: USV-Based 4D Radar-Camera Tracking Dataset for Autonomous Driving in Inland Waterways
A new USV dataset combining 4D radar, camera, GPS, and IMU data for tracking boats, ships, and vessels on inland waterways, together with a radar-camera matching method that consistently improves two-stage trackers.
-
A Framework for Multi-View Multiple Object Tracking using Single-View Multi-Object Trackers on Fish Data
A YOLOv8-ByteTrack pipeline plus stereo triangulation can produce 3D fish tracks for some underwater video pairs, but the claimed multi-view accuracy improvement is not demonstrated.
Discussion (0). Sign in to comment.