Research map / Detection and segmentation / Tracking
Dual-Path Temporal Decoder for End-to-End Multi-Object Tracking
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a dual-path temporal decoder for end-to-end transformer-based multi-object tracking to better preserve object identities across frames under occlusion and appearance change.
Problem
End-to-end transformer-based MOT methods struggle to maintain consistent object identities across frames, especially under occlusions, appearance changes, or detection failures.
Approach
A dual-path temporal decoder that explicitly separates temporal modeling paths to improve identity preservation within an end-to-end transformer tracker (abstract only; details unavailable).
Closest papers by meaning
- DeconfuseTrack: Dealing with Confusion for Multi-Object Tracking (CVPR 2024 · similarity 0.87)
- Revisiting motion information for RGB-Event tracking with MOT philosophy (NeurIPS 2024 · similarity 0.87)
- DiffusionTrack: Diffusion Model for Multi-Object Tracking (AAAI 2024 · similarity 0.87)
- OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer (ICLR 2025 · similarity 0.87)
- ADA-Track: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Association (CVPR 2024 · similarity 0.87)
- More Than Meets the Eye: Enhancing Multi-Object Tracking Even with Prolonged Occlusions (ICML 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.