Learning regression and verification networks for long-term visual tracking

TL;DR

This paper introduces a novel long-term visual tracking framework utilizing deep regression and verification networks, capable of accurately detecting object presence, estimating bounding boxes, and re-detecting objects after disappearance.

Contribution

The work presents a new long-term tracking approach combining regression and verification networks with online adaptation, improving detection and re-detection capabilities in practical scenarios.

Findings

Achieves top performance on VOT2018 long-term challenge.

Attains state-of-the-art results on OxUvA long-term dataset.

Effectively handles object absence and reappearance in tracking.

Abstract

Compared with short-term tracking, the long-term tracking task requires determining the tracked object is present or absent, and then estimating the accurate bounding box if present or conducting image-wide re-detection if absent. Until now, few attempts have been done although this task is much closer to designing practical tracking systems. In this work, we propose a novel long-term tracking framework based on deep regression and verification networks. The offline-trained regression model is designed using the object-aware feature fusion and region proposal networks to generate a series of candidates and estimate their similarity scores effectively. The verification network evaluates these candidates to output the optimal one as the tracked object with its classification score, which is online updated to adapt to the appearance variations based on newly reliable observations. The similarity and classification scores are combined to obtain a final confidence value, based on which our tracker can determine the absence of the target accurately and conduct image-wide re-detection to capture the target successfully when it reappears. Extensive experiments show that our tracker achieves the best performance on the VOT2018 long-term challenge and state-of-the-art results on the OxUvA long-term dataset.