paper-with-me

홈 › Papers

ROAM: Recurrently Optimizing Tracking Model

2019-07-28 · CVPR 2020 6 · Tianyu Yang, Pengfei Xu, Runbo Hu, Hua Chai, Antoni B. Chan

In this paper, we design a tracking model consisting of response generation and bounding box regression, where the first component produces a heat map to indicate the presence of the object at different positions and the second part regresses the relative bounding box shifts to anchors mounted on sliding-window locations. Thanks to the resizable convolutional filters used in both components to adapt to the shape changes of objects, our tracking model does not need to enumerate different sized anchors, thus saving model parameters. To effectively adapt the model to appearance variations, we propose to offline train a recurrent neural optimizer to update tracking model in a meta-learning setting, which can converge the model in a few gradient steps. This improves the convergence speed of updating the tracking model while achieving better performance. We extensively evaluate our trackers, ROAM and ROAM++, on the OTB, VOT, LaSOT, GOT-10K and TrackingNet benchmark and our methods perform favorably against state-of-the-art algorithms.

📄 PDF Abstract BibTeX arXiv:1907.12006

Code (0)

등록된 구현이 없습니다.

Tasks

Meta-LearningmodelResponse Generation

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

NeuroAMP: A Novel End-to-end General Purpose Deep Neural Amplifier for Personalized Hearing Aids

2025-02-15 · Shafique Ahmed, Ryandhimas E. Zezario, Hui-Guan Yuan, Amir Hussain 외

The prevalence of hearing aids is increasing. However, optimizing the amplification processes of hearing aids remains challenging due to the complexity of integrating multiple modular components in traditional methods. T…

Data AugmentationDenoising

Advancing the AmbientGAN for learning stochastic object models

2021-01-30 · Weimin Zhou, Sayantan Bhadra, Frank J. Brooks, Jason L. Granstedt 외

Medical imaging systems are commonly assessed and optimized by use of objective-measures of image quality (IQ) that quantify the performance of an observer at specific tasks. Variation in the objects to-be-imaged is an i…

Generative Adversarial NetworkObject

Recurrently Target-Attending Tracking

2016-06-01 · CVPR 2016 6 · Zhen Cui, Shengtao Xiao, Jiashi Feng, Shuicheng Yan

Robust visual tracking is a challenging task in computer vision. Due to the accumulation and propagation of estimation error, model drifting often occurs and degrades the tracking performance. To mitigate this problem, i…

Visual Tracking

WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models

2026-06-30 · Ting-Bing Xu, Jiacheng Sui, Zhe Gao, Kewei Shi 외 arxiv

Despite rapid progress in interactive world models (IWMs), existing benchmarks evaluate action following only at trajectory level and ignore memory and interaction physics. We introduce WorldRoamBench, an open-world benc…

User Identification via Free Roaming Eye Tracking Data

2024-03-14 · Rishabh Vallabh Varsha Haria, Amin El Abed, Sebastian Maneth

We present a new dataset of "free roaming" (FR) and "targeted roaming" (TR): a pool of 41 participants is asked to walk around a university campus (FR) or is asked to find a particular room within a library (TR). Eye mov…

User Identification