首页/论文/1708.00577

arXiv 1708.005772017-08-02cs.CV

Kernalised Multi-resolution Convnet for Visual Tracking

Shenzhen University（深圳大学）；Peking University Shenzhen Graduate School（北京大学深圳研究生院）

Di Wu, Wenbin Zou, Xia Li, Yong Zhao

备注：: CVPRW 2017

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Visual tracking is intrinsically a temporal problem. Discriminative Correlation Filters (DCF) have demonstrated excellent performance for high-speed generic visual object tracking. Built upon their seminal work, there has been a plethora of recent improvements relying on convolutional neural network (CNN) pretrained on ImageNet as a feature extractor for visual tracking. However, most of their works relying on ad hoc analysis to design the weights for different layers either using boosting or hedging techniques as an ensemble tracker. In this paper, we go beyond the conventional DCF framework and propose a Kernalised Multi-resolution Convnet (KMC) formulation that utilises hierarchical response maps to directly output the target movement. When directly deployed the learnt network to predict the unseen challenging UAV tracking dataset without any weight adjustment, the proposed model consistently achieves excellent tracking performance. Moreover, the transfered multi-reslution CNN renders it possible to be integrated into the RNN temporal learning framework, therefore opening the door on the end-to-end temporal deep learning (TDL) for visual tracking.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Divert More Attention to Vision-Language Tracking

Beijing Jiaotong University（北京交通大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of North Texas（北得克萨斯大学）

Relying on Transformer for complex visual feature learning, object tracking has witnessed the new standard for state-of-the-arts (SOTAs). However, this advancement accompanies by larger training data and longer training period, making tracking increasingly expensive. In this paper, we demonstrate that the Transformer-reliance is not necessary and the pure ConvNets are still competitive and even better yet more economical and friendly in achieving SOTA tracking. Our solution is to unleash the power of multimodal vision-language (VL) tracking, simply using ConvNets. The essence lies in learning …

2022-07-03cs.CV

基于深度学习方法的逐细胞目标跟踪、速度估计与传感器数据时间投影

Deep Learning Method for Cell-Wise Object Tracking, Velocity Estimation and Projection of Sensor Data over Time

Aptiv（安波福）；University of Wuppertal（伍珀塔尔大学）

提出一种利用Transformer机制的新型循环神经网络单元，通过键-查询对跟踪目标并估计速度，以解决卷积神经网络在时空关联上的架构限制，并投影记忆状态以修正时空错位。

2023-06-18cs.CVcs.LG

End-to-end Active Object Tracking via Reinforcement Learning

Tencent AI Lab（腾讯人工智能实验室）；Peking University（北京大学）

We study active object tracking, where a tracker takes as input the visual observation (i.e., frame sequence) and produces the camera control signal (e.g., move forward, turn left, etc.). Conventional methods tackle the tracking and the camera control separately, which is challenging to tune jointly. It also incurs many human efforts for labeling and many expensive trial-and-errors in realworld. To address these issues, we propose, in this paper, an end-to-end solution via deep reinforcement learning, where a ConvNet-LSTM function approximator is adopted for the direct frame-toaction predictio…

2018-06-01cs.CV

End-to-end Active Object Tracking and Its Real-world Deployment via Reinforcement Learning

Tencent AI Lab（腾讯人工智能实验室）；Computer Science Dept., Peking University（北京大学计算机科学系）；Cooperative Medianet Innovation Center（合作媒体网络创新中心）；Peng Cheng Lab（鹏程实验室）

We study active object tracking, where a tracker takes visual observations (i.e., frame sequences) as input and produces the corresponding camera control signals as output (e.g., move forward, turn left, etc.). Conventional methods tackle tracking and camera control tasks separately, and the resulting system is difficult to tune jointly. These methods also require significant human efforts for image labeling and expensive trial-and-error system tuning in the real world. To address these issues, we propose, in this paper, an end-to-end solution via deep reinforcement learning. A ConvNet-LSTM fu…

2019-02-12cs.CV

Detect to Track and Track to Detect

Graz University of Technology（格拉茨工业大学）；University of Oxford（牛津大学）

Recent approaches for high accuracy detection and tracking of object categories in video consist of complex multistage solutions that become more cumbersome each year. In this paper we propose a ConvNet architecture that jointly performs detection and tracking, solving the task in a simple and effective way. Our contributions are threefold: (i) we set up a ConvNet architecture for simultaneous detection and tracking, using a multi-task objective for frame-based object detection and across-frame track regression; (ii) we introduce correlation features that represent object co-occurrences across…

2018-03-07cs.CV

Involution融合卷积网络用于自闭症谱系障碍儿童眼动追踪模式分类

Involution Fused ConvNet for Classifying Eye-Tracking Patterns of Children with Autism Spectrum Disorder

BRAC University（BRAC大学）；Dublin City University（都柏林城市大学）；University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）；Concordia University（康考迪亚大学）

本文提出将involution与卷积结合的混合深度学习模型IC，用于自闭症儿童眼动追踪模式分类，通过增强空间信息捕捉能力，在多个数据集上优于以往方法。

2024-01-07cs.CVeess.IV

更多相关论文收起更多论文

Tracking Objects and Activities with Attention for Temporal Sentence Grounding

Huazhong University of Science and Technology（华中科技大学）；Peking University（北京大学）；Wangxuan Institute of Computer Technology（王选计算机研究所）

Temporal sentence grounding (TSG) aims to localize the temporal segment which is semantically aligned with a natural language query in an untrimmed video.Most existing methods extract frame-grained features or object-grained features by 3D ConvNet or detection network under a conventional TSG framework, failing to capture the subtle differences between frames or to model the spatio-temporal behavior of core persons/objects. In this paper, we introduce a new perspective to address the TSG task by tracking pivotal objects and activities to learn more fine-grained spatio-temporal behaviors. Speci…

2023-02-21cs.CV

Online Domain Adaptation for Multi-Object Tracking

Xerox Research Centre Europe（施乐欧洲研究中心）

Automatically detecting, labeling, and tracking objects in videos depends first and foremost on accurate category-level object detectors. These might, however, not always be available in practice, as acquiring high-quality large scale labeled training datasets is either too costly or impractical for all possible real-world application scenarios. A scalable solution consists in re-using object detectors pre-trained on generic datasets. This work is the first to investigate the problem of on-line domain adaptation of object detectors for causal multi-object tracking (MOT). We propose to alleviat…

2015-08-04cs.CV

用于计数的卷积神经网络：钢鼓瞬态现象的目标检测

ConvNets for Counting: Object Detection of Transient Phenomena in Steelpan Drums

Belmont University（贝尔蒙特大学）；Joliet Junior College（乔利埃特初级学院）

本研究构建卷积神经网络目标检测器计数钢鼓干涉条纹，结合众包标注数据与风格迁移合成数据训练评估，发现高八度音共振振荡早于对应二次谐波声强上升，为钢鼓时变行为研究提供模型工具。

2021-09-07cs.CVcs.LGphysics.app-ph