Towards Real-World Visual Tracking with Temporal Contexts

TL;DR

This paper introduces TCTrack++, a novel visual tracking framework that effectively exploits temporal contexts through attention-based convolution and adaptive transformers, significantly improving real-world tracking performance.

Contribution

It proposes a two-level framework with temporal context exploitation via attention-based convolution and adaptive transformers, addressing real-world tracking challenges.

Findings

Outperforms state-of-the-art trackers on 8 benchmarks.

Demonstrates robustness in real-world conditions.

Enhances tracking accuracy with temporal context integration.

Abstract

Visual tracking has made significant improvements in the past few decades. Most existing state-of-the-art trackers 1) merely aim for performance in ideal conditions while overlooking the real-world conditions; 2) adopt the tracking-by-detection paradigm, neglecting rich temporal contexts; 3) only integrate the temporal information into the template, where temporal contexts among consecutive frames are far from being fully utilized. To handle those problems, we propose a two-level framework (TCTrack) that can exploit temporal contexts efficiently. Based on it, we propose a stronger version for real-world visual tracking, i.e., TCTrack++. It boils down to two levels: features and similarity maps. Specifically, for feature extraction, we propose an attention-based temporally adaptive convolution to enhance the spatial features using temporal information, which is achieved by dynamically calibrating the convolution weights. For similarity map refinement, we introduce an adaptive temporal transformer to encode the temporal knowledge efficiently and decode it for the accurate refinement of the similarity map. To further improve the performance, we additionally introduce a curriculum learning strategy. Also, we adopt online evaluation to measure performance in real-world conditions. Exhaustive experiments on 8 wellknown benchmarks demonstrate the superiority of TCTrack++. Real-world tests directly verify that TCTrack++ can be readily used in real-world applications.