CIRNet: An improved RGBT tracking via cross-modality interaction and re-identification

Xia, Weidai; Zhou, Dongming; Cao, Jinde; Liu, Yanyu; R, Hou

doi:10.1016/j.neucom.2022.04.017

Cited by 17 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, cross-camera target matching is still a difficult problem due to the differences in viewpoints, lighting, and backgrounds between cameras, as well as changes in poses, expressions, and clothing of the targets themselves. In addition, the need to process a large amount of video streaming data in real time places high demands on the computational efficiency of the algorithms [12][13].…”

Section: Introductionmentioning

confidence: 99%

A Video Target Re-Recognition Method Based on Adaptive Attention Enhancement and Multi-Scale Feature Fusion

Xu,

Chen,

Chen

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Within the realm of computer vision, the task of re-identifying targets across multiple video frames has emerged as a pivotal challenge, particularly in domains like video surveillance, smart transportation systems, and pedestrian flow analytics. Conventional re-identification techniques often grapple with constraints stemming from varying camera perspectives, inconsistent lighting conditions, and prevalent occlusions. Addressing these challenges, this research introduces MVF-Re, a sophisticated re-identification approach that synergizes adaptive attention mechanisms with multi-scale feature fusion. Initially, we architect a deep attention-enhanced feature pyramid network, a pioneering framework that dynamically tailors itself to video frame content, thereby capturing intricate target details. Subsequently, we incorporate a multi-input Siamese network, ensuring the derivation of consistent and resilient feature sets across diverse contexts. To augment feature distinctiveness, we conceptualize a context-sensitive dynamic attention mechanism, adept at judiciously allocating weights to individual video frames. Culminating our approach, we deploy an innovative multi-scale feature fusion methodology, offering a holistic and robust target representation. Empirical evaluations on multiple benchmark datasets underscore the superior performance of our methodology, underscoring its proficiency in multi-frame target re-identification.INDEX TERMS multi-video frame target re-recognition, deep attention mechanism, siamese network, context-aware dynamic attention

show abstract

Section: Introductionmentioning

confidence: 99%

A Video Target Re-Recognition Method Based on Adaptive Attention Enhancement and Multi-Scale Feature Fusion

Xu,

Chen,

Chen

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Although rich information is preserved, it will bring greater computational costs during tracking. In feature-level fusion tracking, the features of RGB and infrared images are first extracted and then fused according to the designed fusion rules to obtain the fused feature and finally use the fused feature to perform tracking [ 6 , 7 , 8 ]. Decision-level fusion tracking is first performed in individual modalities to obtain tracking results or response maps.…”

Section: Introductionmentioning

confidence: 99%

Multi-Scale Feature Interactive Fusion Network for RGBT Tracking

Xiao

Xiong

Meng

et al. 2023

Sensors

View full text Add to dashboard Cite

The fusion tracking of RGB and thermal infrared image (RGBT) is paid wide attention to due to their complementary advantages. Currently, most algorithms obtain modality weights through attention mechanisms to integrate multi-modalities information. They do not fully exploit the multi-scale information and ignore the rich contextual information among features, which limits the tracking performance to some extent. To solve this problem, this work proposes a new multi-scale feature interactive fusion network (MSIFNet) for RGBT tracking. Specifically, we use different convolution branches for multi-scale feature extraction and aggregate them through the feature selection module adaptively. At the same time, a Transformer interactive fusion module is proposed to build long-distance dependencies and enhance semantic representation further. Finally, a global feature fusion module is designed to adjust the global information adaptively. Numerous experiments on publicly available GTOT, RGBT234, and LasHeR datasets show that our algorithm outperforms the current mainstream tracking algorithms.

show abstract