Challenge-Aware RGBT Tracking

ECCV 2020  ·  Chenglong Li, Lei Liu, Andong Lu, Qing Ji, Jin Tang ·

RGB and thermal source data suffer from both shared and specific challenges, and how to explore and exploit them plays a critical role to represent the target appearance in RGBT tracking. In this paper, we propose a novel challenge-aware neural network to handle the modality-shared challenges (e.g., fast motion, scale variation and occlusion) and the modality-specific ones (e.g., illumination variation and thermal crossover) for RGBT tracking. In particular, we design several parameter-shared branches in each layer to model the target appearance under the modality-shared challenges, and several parameterindependent branches under the modality-specific ones. Based on the observation that the modality-specific cues of different modalities usually contains the complementary advantages, we propose a guidance module to transfer discriminative features from one modality to another one, which could enhance the discriminative ability of some weak modality. Moreover, all branches are aggregated together in an adaptive manner and parallel embedded in the backbone network to efficiently form more discriminative target representations. These challenge-aware branches are able to model the target appearance under certain challenges so that the target representations can be learnt by a few parameters even in the situation of insufficient training data. From the experimental results we will show that our method operates at a real-time speed while performing well against the state-of-the-art methods on three benchmark datasets.

PDF Abstract ECCV 2020 PDF ECCV 2020 Abstract
No code implementations yet. Submit your code now

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Rgb-T Tracking GTOT CAT Precision 88.9 # 6
Success 71.7 # 7
Rgb-T Tracking LasHeR CAT Precision 45.0 # 16
Success 31.4 # 16
Rgb-T Tracking RGBT210 CAT Precision 79.2 # 6
Success 53.3 # 8

Methods


No methods listed for this paper. Add relevant methods here