HiFT: Hierarchical Feature Transformer for Aerial Tracking

Cao, Ziang; Fu, Changhong; Ye, Junjie; Li, Bowen; Li, Yiming

doi:10.1109/iccv48922.2021.01517

Cited by 183 publications

(136 citation statements)

References 41 publications

Supporting

Mentioning

136

Contrasting

Order By: Relevance

“…Object tracking approaches can be broadly divided into methods based on correlation filters (CF) [21], [22], [23] and methods based on convolutional neural network (CNN) [11], [24], [25]. Due to their efficiency [5], [22], CF-based trackers were considered as the promising choice for UAV tracking.…”

Section: Related Work a Cf-based Uav Trackingmentioning

confidence: 99%

“…As a continuation of SiamAPN, SiamAPN++ [9] introduces a novel attentional aggregation network to handle semantic information variation. HiFT [11] proposes a brand-new lightweight hierarchical feature transformer for effective and efficient multi-level feature fusion.…”

Section: B Siamese-based Uav Trackingmentioning

confidence: 99%

“…In this section we discuss the effectiveness of our attack methods on SiamRPN++ [24], SiamAPN [10], SiamMask [38], SiamAPN++ [9], SiamGAT [28], SiamCAR [27], and HiFT [11]. Attack results on three public benchmarks are shown in Fig.…”

Section: Overall Performancementioning

confidence: 99%

“…Although the former is energy-saving and less expensive in computation, the performance remains significantly inferior to that of the latter. In recent years, approaches based on DL have made substantial progress in UAV tracking [9], [10], [11]. The most eye-catching work is the trackers based on the Siamese network.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Ad2Attack: Adaptive Adversarial Attack on Real-Time UAV Tracking

Fu¹,

Li²,

Yuan³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Visual tracking is adopted to extensive unmanned aerial vehicle (UAV)-related applications, which leads to a highly demanding requirement on the robustness of UAV trackers. However, adding imperceptible perturbations can easily fool the tracker and cause tracking failures. This risk is often overlooked and rarely researched at present. Therefore, to help increase awareness of the potential risk and the robustness of UAV tracking, this work proposes a novel adaptive adversarial attack approach, i.e., Ad 2 Attack, against UAV object tracking. Specifically, adversarial examples are generated online during the resampling of the search patch image, which leads trackers to lose the target in the following frames. Ad 2 Attack is composed of a direct downsampling module and a super-resolution upsampling module with adaptive stages. A novel optimization function is proposed for balancing the imperceptibility and efficiency of the attack. Comprehensive experiments on several well-known benchmarks and real-world conditions show the effectiveness of our attack method, which dramatically reduces the performance of the most advanced Siamese trackers.

show abstract

Section: Related Work a Cf-based Uav Trackingmentioning

confidence: 99%

Section: B Siamese-based Uav Trackingmentioning

confidence: 99%

Section: Overall Performancementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Ad2Attack: Adaptive Adversarial Attack on Real-Time UAV Tracking

Fu¹,

Li²,

Yuan³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Owing to the superior mobility of unmanned aerial vehicles (UAVs), tracking-based applications are experiencing rapid developments, e.g., motion object analysis [57], geographical survey [61], and visual localization [47]. Nevertheless, aerial tracking still faces two difficulties: 1) aerial conditions inevitably introduce special challenges including motion blur, camera motion, occlusion, etc; 2) the limited power of aerial platforms restricts the computational resource, impeding the deployment of time-consuming state-of-the-art methods [6]. Hence, an ideal tracker for aerial tracking must be robust and efficient.…”

Section: Introductionmentioning

confidence: 99%

TCTrack: Temporal Contexts for Aerial Tracking

Cao¹,

Huang²,

Peng³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Temporal contexts among consecutive frames are far from being fully utilized in existing visual trackers. In this work, we present TCTrack 1 , a comprehensive framework to fully exploit temporal contexts for aerial tracking. The temporal contexts are incorporated at two levels: the extraction of features and the refinement of similarity maps. Specifically, for feature extraction, an online temporally adaptive convolution is proposed to enhance the spatial features using temporal information, which is achieved by dynamically calibrating the convolution weights according to the previous frames. For similarity map refinement, we propose an adaptive temporal transformer, which first effectively encodes temporal knowledge in a memory-efficient way, before the temporal knowledge is decoded for accurate adjustment of the similarity map. TCTrack is effective and efficient: evaluation on four aerial tracking benchmarks shows its impressive performance; real-world UAV tests show its high speed of over 27 FPS on NVIDIA Jetson AGX Xavier.

show abstract

Learning to generalize aerial person re‐identification using the meta‐transfer method

Peng

Lü

et al. 2023

Concurrency and Computation

View full text Add to dashboard Cite

Person re-identification (Re-ID) aims to retrieve a person of interest across multiple nonoverlapping cameras. In recent years, to enable person Re-ID technology to play out its application value in real-world scenarios, visual surveillance through unmanned aerial vehicle (UAV) platforms has received intense attention, and aerial person datasets have been constructed. However, the pedestrian images captured by ground cameras and those captured by UAVs exhibit great differences. Person Re-ID methods based on ground person images have difficulty performing Re-ID on aerial person images. In this paper, we first use a meta-transfer method to learn to gener-aerial imagery, meta-transfer learning, person re-identification

show abstract

HiFT: Hierarchical Feature Transformer for Aerial Tracking

Cited by 183 publications

References 41 publications

Ad2Attack: Adaptive Adversarial Attack on Real-Time UAV Tracking

Ad2Attack: Adaptive Adversarial Attack on Real-Time UAV Tracking

TCTrack: Temporal Contexts for Aerial Tracking

Learning to generalize aerial person re‐identification using the meta‐transfer method

Contact Info

Product

Resources

About