Referring Multi-Object Tracking with Diverse Dynamic Expressions

arXiv:2406.05039 · cs.CV, cs.CL · Submitted 2024-06-07 · Read on arXiv

cs.CV, cs.CL

Submitted: 2024-06-07

Updated: 2026-10-16

Code: https://github.com/zyn213/TempRMOT

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Core — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes

Sources

• Talk2Car: Taking Control of Your Self-Driving Car
• Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video
• MLS-Track: Multilevel Semantic Interaction in RMOT
• ReferGPT: Towards Zero-Shot Referring Multi-Object Tracking
• NuGrounding: A Multi-View 3D Visual Grounding Framework in Autonomous Driving
• RefAV: Towards Planning-Centric Scenario Mining
• Tell Me What to Track: Infusing Robust Language Guidance for Enhanced Referring Multi-Object Tracking
• Deformable DETR: Deformable Transformers for End-to-End Object Detection
• MOT16: A Benchmark for Multi-Object Tracking
• MOT20: A benchmark for multi object tracking in crowded scenes
• BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View
• TransTrack: Multiple Object Tracking with Transformer
• RoBERTa: A Robustly Optimized BERT Pretraining Approach

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models