Multi-modal trackers have drawn widespread attention for robust tracking in challenging scenarios. However, existing multi-modal trackers often rely solely on spatial matching between the initial target template and the search regions, or incorporate only single-frame historical information, failing to fully exploit temporal correlations in tracking sequences. Additionally, most trackers that introduce temporal modeling require either retraining the entire network or designing specialized modules for temporal feature extraction, which incurs additional computational costs. To alleviate these limitations, inspired by human visual memory, we propose MPTrack, a novel tracker that directly reuses pre-extracted historical target features as memory prompts, establishing temporal dependencies without redundant feature extraction or specially designed temporal extraction networks. Our proposed Memory Prompt Fusion module effectively combines initial target templates with multiple historical memory cues to generate enhanced templates, enabling the perception of long-term appearance dynamics while mitigating potential interference from individual memory. Simultaneously, to avoid the computational cost of full-model training, we design a lightweight memory adapter that allows the frozen backbone network to efficiently adapt to the memory-enhanced template. Extensive experiments demonstrate that our method effectively incorporates temporal information and achieves promising results across different multi-modal tracking scenarios, including RGB+Thermal, RGB+Event, and RGB+Depth tracking tasks.

Depth estimation plays a crucial role in 3D scene understanding and is extensively used in a wide range of vision tasks. Image-based methods struggle in challenging scenarios, while event cameras offer high dynamic range and temporal resolution but face difficulties with sparse data. Combining event and image data provides significant advantages, yet effective integration remains challenging. Existing CNN-based fusion methods struggle with occlusions and depth disparities due to limited receptive fields, while Transformer-based fusion methods often lack deep modality interaction. To address these issues, we propose UniCT Depth, an event-image fusion method that unifies CNNs and Transformers to model local and global features. We propose the Convolution-compensated ViT Dual SA (CcViT-DA) Block, designed for the encoder, which integrates Context Modeling Self-Attention (CMSA) to capture spatial dependencies and Modal Fusion Self-Attention (MFSA) for effective cross-modal fusion. Furthermore, we design the tailored Detail Compensation Convolution (DCC) Block to improve texture details and enhances edge representations. Extensive experiments show that UniCT Depth outperforms existing image, event, and fusion-based monocular depth estimation methods across key metrics.

The goal of RGB-T tracking is to fully utilize the information of the RGB and TIR modality sequences to enhance the robustness of object tracking. Existing RGB-T tracking methods usually simply fuse the features of the RGB and TIR search regions, resulting in insufficient information interaction and introducing unnecessary background noise. In addition, the utilization of temporal context information has not been fully explored. To address the above limitations, we propose an RGB-T tracking framework STTrack. We propose a Spatio-Temporal Bidirectional Adapter (STA), which is integrated into the ViT backbone. The STA conducts bidirectional information interaction between spatial and temporal context, so as to explore and fuse the synergistic and complementary information between modalities and the temporal context information during the tracking process more effectively. Simultaneously, we propose an Asynchronous Online Template Update (AOTU) strategy to update high-quality temporal context information for the tracker, to adapt to the appearance changes of the target over time. In addition, we introduce a Modal State Guided Fusion (MSGF) module to adaptively filter out unnecessary modality or background noise. Extensive experiments conducted on five popular RGB-T benchmark datasets demonstrate that STTrack outperforms existing state-of-the-art methods.

Tracking an Unmanned Aerial Vehicle (UAV) to obtain its locations and trajectory is a crucial task to avoid the unlawful use of UAVs. However, most existing UAV tracking methods fail when facing cluster environments, out-of-view, and occlusions because of their insufficient representation of global context information capacity. To mitigate these issues, we propose a new tracker, namely SiamFusion, to innovate a dual fusion procedure that leverages the advantages in both the feature and decision levels. In particular, we propose a novel feature fusion module named Modality-Fusion to utilize multi-modal information, enhancing the perception of the target. From the decision level, we further develop a local-global converter based on a multi-modal fusion decision-making mechanism to reduce the accumulation during tracking, which significantly increases the robustness of the tracking process. Extensive experiments demonstrate the superiority of the proposed SiamFusion, which achieves the best performance on Anti-UAV in terms of accuracy and speed. In particular, we exceed the state-of-the-art tracking algorithm in the tracking accuracy by 4.2% at a similar frame rate. Our source codes, pre-trained models, and online demos will be released upon acceptance.

Visual localization is a fundamental task in computer vision and robotics. Training existing visual localization methods requires a large number of posed images to generalize to novel views, while state-of-the-art methods generally require dense ground truth 3D labels for supervision. However, acquiring a large number of posed images and dense 3D labels in the real world is challenging and costly. In this paper, we present a novel visual localization method that achieves accurate localization while using only a few posed images compared to other localization methods. To achieve this, we first use a few posed images with coarse pseudo-3D labels provided by NeRF to train a coordinate regression network. Then a coarse pose is estimated from the regression network with PNP. Finally, we use the image-based visual servo (IBVS) with the scene prior provided by NeRF for pose optimization. Furthermore, our method can provide effective navigation prior, which enable navigation based on IBVS without using custom markers and depth sensor. Extensive experiments on 7-Scenes and 12-Scenes datasets demonstrate that our method outperforms state-of-the-art methods under the same setting, with only 5\% to 25\% training data. Furthermore, our framework can be naturally extended to the visual navigation task based on IBVS, and its effectiveness is verified in simulation experiments.