Target Transformed Regression for Accurate Tracking
Accurate tracking is still a challenging task due to appearance variations, pose and view changes, and geometric deformations of target in videos. Recent anchor-free trackers provide an efficient regression mechanism but fail to produce precise bounding box estimation. To address these issues, this paper repurposes a Transformer-alike regression branch, termed as Target Transformed Regression (TREG), for accurate anchor-free tracking. The core to our TREG is to model pair-wise relation between elements in target template and search region, and use the resulted target enhanced visual representation for accurate bounding box regression. This target contextualized representation is able to enhance the target relevant information to help precisely locate the box boundaries, and deal with the object deformation to some extent due to its local and dense matching mechanism. In addition, we devise a simple online template update mechanism to select reliable templates, increasing the robustness for appearance variations and geometric deformations of target in time. Experimental results on visual tracking benchmarks including VOT2018, VOT2019, OTB100, GOT10k, NFS, UAV123, LaSOT and TrackingNet demonstrate that TREG obtains the state-of-the-art performance, achieving a success rate of 0.640 on LaSOT, while running at around 30 FPS. The code and models will be made available at https://github.com/MCG-NJU/TREG.
Code (1)
Tasks
regressionVisual Object TrackingVisual TrackingSimilar Papers 제목 키워드 기반
Probabilistic Regression for Visual Tracking
Visual tracking is fundamentally the problem of regressing the state of the target in each video frame. While significant progress has been achieved, trackers are still prone to failures and inaccuracies. It is therefore…
Object TrackingregressionVisual TrackingLearning regression and verification networks for long-term visual tracking
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 …
General ClassificationObjectRegion Proposalregression+1Learning Localization-aware Target Confidence for Siamese Visual Tracking
Siamese tracking paradigm has achieved great success, providing effective appearance discrimination and size estimation by the classification and regression. While such a paradigm typically optimizes the classification a…
ClassificationregressionVisual TrackingCapsuleRRT: Relationships-Aware Regression Tracking via Capsules
Regression tracking has gained more and more attention thanks to its easy-to-implement characteristics, while existing regression trackers rarely consider the relationships between the object parts and the complete o…
image-classificationImage ClassificationKnowledge DistillationObject+1Two stages for visual object tracking
Siamese-based trackers have achived promising performance on visual object tracking tasks. Most existing Siamese-based trackers contain two separate branches for tracking, including classification branch and bounding box…
Image SegmentationObjectObject TrackingSegmentation+4