Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Single-Model and Any-Modality for Video Object Tracking

About

In the realm of video object tracking, auxiliary modalities such as depth, thermal, or event data have emerged as valuable assets to complement the RGB trackers. In practice, most existing RGB trackers learn a single set of parameters to use them across datasets and applications. However, a similar single-model unification for multi-modality tracking presents several challenges. These challenges stem from the inherent heterogeneity of inputs -- each with modality-specific representations, the scarcity of multi-modal datasets, and the absence of all the modalities at all times. In this work, we introduce Un-Track, a Unified Tracker of a single set of parameters for any modality. To handle any modality, our method learns their common latent space through low-rank factorization and reconstruction techniques. More importantly, we use only the RGB-X pairs to learn the common latent space. This unique shared representation seamlessly binds all modalities together, enabling effective unification and accommodating any missing modality, all within a single transformer-based architecture. Our Un-Track achieves +8.1 absolute F-score gain, on the DepthTrack dataset, by introducing only +2.14 (over 21.50) GFLOPs with +6.6M (over 93M) parameters, through a simple yet efficient prompting strategy. Extensive comparisons on five benchmark datasets with different modalities show that Un-Track surpasses both SOTA unified trackers and modality-specific counterparts, validating our effectiveness and practicality. The source code is publicly available at https://github.com/Zongwei97/UnTrack.

Zongwei Wu, Jilai Zheng, Xiangxuan Ren, Florin-Alexandru Vasluianu, Chao Ma, Danda Pani Paudel, Luc Van Gool, Radu Timofte• 2023

Related benchmarks

TaskDatasetResultRank
RGB-T TrackingLasHeR (test)
PR66.7
244
RGB-T TrackingRGBT234 (test)
Precision Rate84.2
189
RGB-D Object TrackingVOT-RGBD 2022 (public challenge)
EAO72.1
167
RGB-D Object TrackingDepthTrack (test)
Precision61.3
145
RGB-T TrackingRGBT234
Precision84.2
98
RGBT TrackingRGBT234
PR84.2
65
Object TrackingVisEvent (test)
PR76.3
63
RGBT TrackingLasHeR
PR66.7
55
RGBT TrackingRGBT 234
Precision Rate84.2
53
Object TrackingCOESOT (test)
SR67.9
50
Showing 10 of 23 rows

Other info

Code

Follow for update