Visual tracking via weakly supervised learning from multiple imperfect oracles

Zhong, Bineng; Yao, Hongxun; Chen, Sheng; Ji, Rongrong; Yuan, Xin; Liu, Shaohui; Gao, Wen

doi:10.1016/j.patcog.2013.10.002

Cited by 69 publications

(9 citation statements)

References 48 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The tracker based on trackingby-detection treats object location as a classification problem, in which the decision boundary is implemented by the online learning classifier. In order to solve the drift problem in the tracking process, Zhong et al [49] proposed a probabilistic method in a new type of weakly supervised learning scenario to judge the position of the object and the accuracy of each tracker. And online evaluation and heuristic training are used to make tracking faster and more effective.…”

Section: A Tracking Frameworkmentioning

confidence: 99%

Triplet Network Template for Siamese Trackers

2021

View full text Add to dashboard Cite

Siamese network based trackers describe object tracking as a similarity matching problem and these trackers achieve state-of-the-art performance on multiple benchmarks. However, due to the nonupdate of the appearance template and the change of the object appearance, the tracking drift problem often occurs, especially in the background clutter scene. Effective appearance template update methods can improve tracker performance, but most trackers use simple linear interpolation to update the template or do not update the initial template at all. Through experiments, we find that the channel response of the search region with the adjacent frame appearance template is often better than that with the initial frame appearance template. So we add the results of the previous frame prediction as a new template branch to the Siamese network to form a Triplet network. We applied the Triplet network to the SiamFC and SiamCAR, called TripFC and TripCAR. We tested on four challenging benchmarks (GOT-10K, OTB2013, OTB2015, UAV123). The experiments show that our method is powerful and effective, it can be easily embedded into the Siamese trackers. TripFC has a good effect on solving the problem of tracking drift. If necessary we can publish the code to facilitate research in this area.

show abstract

Section: A Tracking Frameworkmentioning

confidence: 99%

Triplet Network Template for Siamese Trackers

2021

View full text Add to dashboard Cite

show abstract

“…Recently, a variety of low-rank subspaces and sparse representations based tracking methods have been proposed [ 42 – 47 ] for cell/object tracking due to their robustness to occlusion and image noises. Zhong et al [ 48 ] propose a weakly supervised learning-based tracking method, in which multiple complementary trackers are effectively fused to achieve robust tracking results. Zhou et al [ 49 ] propose a similarity fusion-based tracking method, in which multiple features and context structure of unlabeled data are effectively utilized.…”

Section: Related Workmentioning

confidence: 99%

Robust Individual-Cell/Object Tracking via PCANet Deep Network in Biomedicine and Computer Vision

Zhong

Pan

Wang

et al. 2016

BioMed Research International

Self Cite

View full text Add to dashboard Cite

Tracking individual-cell/object over time is important in understanding drug treatment effects on cancer cells and video surveillance. A fundamental problem of individual-cell/object tracking is to simultaneously address the cell/object appearance variations caused by intrinsic and extrinsic factors. In this paper, inspired by the architecture of deep learning, we propose a robust feature learning method for constructing discriminative appearance models without large-scale pretraining. Specifically, in the initial frames, an unsupervised method is firstly used to learn the abstract feature of a target by exploiting both classic principal component analysis (PCA) algorithms with recent deep learning representation architectures. We use learned PCA eigenvectors as filters and develop a novel algorithm to represent a target by composing of a PCA-based filter bank layer, a nonlinear layer, and a patch-based pooling layer, respectively. Then, based on the feature representation, a neural network with one hidden layer is trained in a supervised mode to construct a discriminative appearance model. Finally, to alleviate the tracker drifting problem, a sample update scheme is carefully designed to keep track of the most representative and diverse samples during tracking. We test the proposed tracking method on two standard individual cell/object tracking benchmarks to show our tracker's state-of-the-art performance.

show abstract

“…In computer vision, researchers have utilized weak labels to learn models for several tasks including semantic segmentation [18,28,63], visual tracking [69], reconstruction [52,25], video summarization [37], learning robotic manipulations [46], video captioning [41], object boundaries [29], place recognition [2], and so on. The weak TALC problem is European Conference on Computer Vision (ECCV), 2018 arXiv:1807.10418v3 [cs.CV] 15 Dec 2018 Fig.…”

Section: Introductionmentioning

confidence: 99%

W-TALC: Weakly-Supervised Temporal Activity Localization and Classification

Shrivastava

Roy

Roy-Chowdhury

2018

Lecture Notes in Computer Science

275

335

View full text Add to dashboard Cite

Most activity localization methods in the literature suffer from the burden of frame-wise annotation requirement. Learning from weak labels may be a potential solution towards reducing such manual labeling effort. Recent years have witnessed a substantial influx of tagged videos on the Internet, which can serve as a rich source of weakly-supervised training data. Specifically, the correlations between videos with similar tags can be utilized to temporally localize the activities. Towards this goal, we present W-TALC, a Weakly-supervised Temporal Activity Localization and Classification framework using only video-level labels. The proposed network can be divided into two sub-networks, namely the Two-Stream based feature extractor network and a weakly-supervised module, which we learn by optimizing two complimentary loss functions. Qualitative and quantitative results on two challenging datasets -Thumos14 and ActivityNet1.2, demonstrate that the proposed method is able to detect activities at a fine granularity and achieve better performance than current state-of-the-art methods. Codes available at https://github.com/sujoyp/wtalc-pytorch

show abstract

Visual tracking via weakly supervised learning from multiple imperfect oracles

Abstract: Abstract

Cited by 69 publications

References 48 publications

Triplet Network Template for Siamese Trackers

Triplet Network Template for Siamese Trackers

Robust Individual-Cell/Object Tracking via PCANet Deep Network in Biomedicine and Computer Vision

W-TALC: Weakly-Supervised Temporal Activity Localization and Classification

Contact Info

Product

Resources

About