Scene perception and trajectory forecasting are two fundamental challenges that are crucial to a safe and reliable autonomous driving (AD) system. However, most proposed methods aim at addressing one of the two challenges mentioned above with a single model. To tackle this dilemma, this paper proposes spatio‐temporal semantics and interaction graph aggregation for multi‐agent perception and trajectory forecasting (ST‐SIGMA), an efficient end‐to‐end method to jointly and accurately perceive the AD environment and forecast the trajectories of the surrounding traffic agents within a unified framework. ST‐SIGMA adopts a trident encoder–decoder architecture to learn scene semantics and agent interaction information on bird’s‐eye view (BEV) maps simultaneously. Specifically, an iterative aggregation network is first employed as the scene semantic encoder (SSE) to learn diverse scene information. To preserve dynamic interactions of traffic agents, ST‐SIGMA further exploits a spatio‐temporal graph network as the graph interaction encoder. Meanwhile, a simple yet efficient feature fusion method to fuse semantic and interaction features into a unified feature space as the input to a novel hierarchical aggregation decoder for downstream prediction tasks is designed. Extensive experiments on the nuScenes data set have demonstrated that the proposed ST‐SIGMA achieves significant improvements compared to the state‐of‐the‐art (SOTA) methods in terms of scene perception and trajectory forecasting, respectively. Therefore, the proposed approach outperforms SOTA in terms of model generalisation and robustness and is therefore more feasible for deployment in real‐world AD scenarios.

As data with diverse representations become high-dimensional, multi-view unsupervised feature selection has been an important learning paradigm. Generally, existing methods encounter the following challenges: (i) traditional solutions either concatenate different views or introduce extra parameters to weight them, affecting the performance and applicability; (ii) emphasis is typically placed on graph construction, yet disregarding the clustering information of data; (iii) exploring the similarity structure of all samples from the original features is suboptimal and extremely time-consuming. To solve this dilemma, we propose an efficient multi-view unsupervised feature selection (EMUFS) to construct bipartite graphs between samples and anchors. Specifically, a parameter-free manner is devised to collaboratively fuse the membership matrices and graphs to learn the compatible structure information across all views, naturally balancing different views. Moreover, EMUFS leverages the similarity relations of data in the feature subspace induced by l2,0-norm to dynamically update the graph. Accordingly, the cluster information of anchors can be accurately propagated to samples via the graph structure and further guide feature selection, enhancing the quality of selected features and the computational costs in solution processes. A convergent optimization is developed to solve the formulated problem, and experiments demonstrate the effectiveness and efficiency of EMUFS.

Although the image dehazing problem has received considerable attention over recent years, the existing models often prioritise performance at the expense of complexity, making them unsuitable for real‐world applications, which require algorithms to be deployed on resource constrained‐devices. To address this challenge, we propose WaveLiteDehaze‐Network (WLD‐Net), an end‐to‐end dehazing model that delivers performance comparable to complex models while operating in real time and using significantly fewer parameters. This approach capitalises on the insight that haze predominantly affects low‐frequency information. By exclusively processing the image in the frequency domain using discrete wavelet transform (DWT), we segregate the image into high and low frequencies and process them separately. This allows us to preserve high‐frequency details and recover low‐frequency components affected by haze, distinguishing our method from existing approaches that use spatial domain processing as the backbone, with DWT serving as an auxiliary component. DWT is applied at multiple levels for better information retention while also accelerating computation by downsampling feature maps. Subsequently, a learning‐based fusion mechanism reintegrates the processed frequencies to reconstruct the dehazed image. Experiments show that WLD‐Net outperforms other low‐parameter models on real‐world hazy images and rivals much larger models, achieving the highest PSNR and SSIM scores on the O‐Haze dataset. Qualitatively, the proposed method demonstrates its effectiveness in handling a diverse range of haze types, delivering visually pleasing results and robust performance, while also generalising well across different scenarios. With only 0.385 million parameters (more than 100 times smaller than comparable dehazing methods), WLD‐Net processes 1024 × 1024 images in just 0.045 s, highlighting its applicability across various real‐world scenarios. The code is available at https://github.com/AliMurtaza29/WLD‐Net .

Transformer tracking always takes paired template and search images as encoder input and conduct feature extraction and target‐search feature correlation by self and/or cross attention operations, thus the model complexity will grow quadratically with the number of input images. To alleviate the burden of this tracking paradigm and facilitate practical deployment of Transformer‐based trackers, we propose a dual pooling transformer tracking framework, dubbed as DPT, which consists of three components: a simple yet efficient spatiotemporal attention model (SAM), a mutual correlation pooling Transformer (MCPT) and a multiscale aggregation pooling Transformer (MAPT). SAM is designed to gracefully aggregates temporal dynamics and spatial appearance information of multi‐frame templates along space‐time dimensions. MCPT aims to capture multi‐scale pooled and correlated contextual features, which is followed by MAPT that aggregates multi‐scale features into a unified feature representation for tracking prediction. DPT tracker achieves AUC score of 69.5 on LaSOT and precision score of 82.8 on TrackingNet while maintaining a shorter sequence length of attention tokens, fewer parameters and FLOPs compared to existing state‐of‐the‐art (SOTA) Transformer tracking methods. Extensive experiments demonstrate that DPT tracker yields a strong real‐time tracking baseline with a good trade‐off between tracking performance and inference efficiency.

Martian terrain segmentation plays a crucial role in autonomous navigation and safe driving of Mars rovers as well as global analysis of Martian geological landforms. However, most deep learning-based segmentation models cannot effectively handle the challenges of highly unstructured and unbalanced terrain distribution on the Martian surface, thus leading to inadequate adaptability and generalization ability. In this paper, we propose a novel multi-view Martian Terrain Segmentation framework (MTSNet) by developing an efficient Martian Terrain text-Guided Segment Anything Model (MTG-SAM) and combining it with a tailored Local Terrain Feature Enhancement Network (LTEN) to capture intricate terrain details. Specifically, the proposed MTG-SAM is equipped with a Terrain Context attention Adapter Module (TCAM) to efficiently and effectively unleashing the model adaptability and transferability on Mars-specific terrain distribution. Then, a Local Terrain Feature Enhancement Network (LTEN) is designated to compensate for the limitations of MTG-SAM in capturing the fine-grained local terrain features of Mars surface. Afterwards, a simple yet efficient Gated Fusion Module (GFM) is introduced to dynamically merge the global contextual features from MTG-SAM encoder and the local refined features from LTEN module for comprehensive terrain feature learning. Moreover, the proposed MTSNet enables terrain-specific text as prompts resolving the efficiency issue of existing methods that require costly annotation of bounding boxes or foreground points. Experimental results on AI4Mars and ConeQuest datasets demonstrate that our proposed MTSNet can effectively learns the unique Martian terrain feature distribution and achieves state-of-the-art performance on multi-view terrain segmentation from both the perspectives of the Mars rover and the satellite remote sensing. Code is available at https://github.com/raoxuefeng/mtsnet.