LoRATv2: Enabling Low-Cost Temporal Modeling in One-Stream Trackers

NeurIPSSpotlight2025

Authors: Liting Lin, Heng Fan, Zhipeng Zhang, Yuqing Huang, Yaowei Wang, Yong Xu, Haibin Ling
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

Transformer-based algorithms, such as LoRAT, have significantly enhanced object-tracking performance…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

transformer

← All NeurIPS 2025 Spotlight papers · Browse the whole archive