GateMOT: Q-Gated Attention for Dense Object Tracking
cs.CV
Submitted: 2026-04-29
Updated: 2026-11-02
Terminology
Sources
- BoT-SORT: Robust Associations Multi-Pedestrian Tracking
- Refined Gate: A Simple and Effective Gating Mechanism for Recurrent Units
- Rethinking Attention with Performers
- FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
- MOT20: A benchmark for multi object tracking in crowded scenes
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- YOLOX: Exceeding YOLO Series in 2021
- SIoU Loss: More Powerful Learning for Bounding Box Regression
- FeatureSORT: Essential Features for Effective Tracking
- TrackSSM: A General Motion Predictor by State-Space Model
- LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing
- MELT: Improve Composed Image Retrieval via the Modification Frequentation-Rarity Balance Network
- Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking
- TransTrack: Multiple Object Tracking with Transformer
- Linformer: Self-Attention with Linear Complexity
- AB3DMOT: A Baseline for 3D Multi-Object Tracking and New Evaluation Metrics
- STABLE: Efficient Hybrid Nearest Neighbor Search via Magnitude-Uniformity and Cardinality-Robustness
- Motion-Aware Transformer for Multi-Object Tracking
- MVP: Winning Solution to SMP Challenge 2025 Video Track
- HINT: Composed Image Retrieval with Dual-path Compositional Contextualized Network
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs