Explore the vast range of titles available.

Visual representation learning is ubiquitous in various real-world applications, including visual comprehension, video understanding, multi-modal analysis, human-computer interaction, and urban computing. Due to the emergence of huge amounts of multimodal heterogeneous spatial/temporal/spatial-temporal data in the big data era, the lack of interpretability, robustness, and out-of-distribution generalization are becoming the challenges of the existing visual models. The majority of the existing methods tend to fit the original data/variable distributions and ignore the essential causal relations behind the multi-modal knowledge, which lacks unified guidance and analysis about why modern visual representation learning methods easily collapse into data bias and have limited generalization and cognitive abilities. Inspired by the strong inference ability of human-level agents, recent years have therefore witnessed great effort in developing causal reasoning paradigms to realize robust representation and model learning with good cognitive ability. In this paper, we conduct a comprehensive review of existing causal reasoning methods for visual representation learning, covering fundamental theories, models, and datasets. The limitations of current methods and datasets are also discussed. Moreover, we propose some prospective challenges, opportunities, and future research directions for benchmarking causal reasoning algorithms in visual representation learning. This paper aims to provide a comprehensive overview of this emerging field, attract attention, encourage discussions, bring to the forefront the urgency of developing novel causal reasoning methods, publicly available benchmarks, and consensus-building standards for reliable visual representation learning and related real-world applications more efficiently.

Fueled by data-intensive science, urban morphology studies have shifted from small-scale case studies to large-scale pattern recognition, thus an effective, machine-readable representation of complex urban forms is therefore critical. Beside classic metrics-based representation with morphological indicators, vision-based representation extracted by deep learning from images have gained prominence, but their relative strengths remain unexplored. This study implements a unified pipeline that constructs both representations across four morphological perspectives—street, building, landscape, and context—and evaluates their efficacy through clustering based on K-Means and Self-Organizing Map (SOM), supplemented by expert-validated case retrieval. Clustering reveals complementary logics: morphometrics segment cases along quantitative thresholds yet often group visually dissimilar forms, while vision-based models cluster perceptual patterns but sacrifice numeric precision. Expert retrieval indicates a modest but consistent tilt: vision-based result holds a slight edge in street-network and building queries, whereas metric-based representations led landscape and context queries. This study also demonstrates the efficacy of vision-based representations compared with metric-based ways and their operational trade-offs (interpretability, compute, data demand). The comparative framework guides researchers in selecting representation strategies tailored to various urban-form perspectives, enhancing the accuracy and applicability of large-scale morphological analyses for planning and design.

Recent self-supervised contrastive learning methods are powerful and efficient for robust representation learning, pulling semantic features from different cropping views of the same image while pushing other features away from other images in the embedding vector space. However, model training for contrastive learning is quite inefficient. In the high-dimensional vector space of the images, images can differ from each other in many ways. We address this problem with heuristic attention pixel-level contrastive loss for representation learning (HAPiCLR), a self-supervised joint embedding contrastive framework that operates at the pixel level and makes use of heuristic mask information. HAPiCLR leverages pixel-level information from the object’s contextual representation instead of identifying pair-wise differences in instance-level representations. Thus, HAPiCLR enhances contrastive learning objectives without requiring large batch sizes, memory banks, or queues, thereby reducing the memory footprint and the processing needed for large datasets. Furthermore, HAPiCLR loss combined with other contrastive objectives such as SimCLR or MoCo loss produces considerable performance boosts on all downstream tasks, including image classification, object detection, and instance segmentation.

Recently, self-supervised learning methods have been shown to be very powerful and efficient for yielding robust representation learning by maximizing the similarity across different augmented views in embedding vector space. However, the main challenge is generating different views with random cropping; the semantic feature might exist differently across different views leading to inappropriately maximizing similarity objective. We tackle this problem by introducing Heuristic Attention Representation Learning (HARL). This self-supervised framework relies on the joint embedding architecture in which the two neural networks are trained to produce similar embedding for different augmented views of the same image. HARL framework adopts prior visual object-level attention by generating a heuristic mask proposal for each training image and maximizes the abstract object-level embedding on vector space instead of whole image representation from previous works. As a result, HARL extracts the quality semantic representation from each training sample and outperforms existing self-supervised baselines on several downstream tasks. In addition, we provide efficient techniques based on conventional computer vision and deep learning methods for generating heuristic mask proposals on natural image datasets. Our HARL achieves +1.3% advancement in the ImageNet semi-supervised learning benchmark and +0.9% improvement in AP50 of the COCO object detection task over the previous state-of-the-art method BYOL. Our code implementation is available for both TensorFlow and PyTorch frameworks.

Small object detection in remote sensing images provides significant value for urban monitoring, aerospace reconnaissance, and other fields. However, detection accuracy still faces multiple challenges including limited target information, weak feature representation, and complex backgrounds. This research aims to improve the performance of the YOLO11 model for small object detection in remote sensing imagery by addressing key issues in long-distance spatial dependency modeling, multi-scale feature adaptive fusion, and computational efficiency. We constructed a specialized Remote Sensing Airport-Plane Detection (RS-APD) dataset and used the public VisDrone2019 dataset for generalization verification. Based on the YOLO11 architecture, we proposed the DAE-YOLO model with three innovative modules: Dynamic Spatial Sequence Module (DSSM) for enhanced long-distance spatial dependency capture; Adaptive Multi-scale Feature Enhancement (AMFE) for multi-scale feature adaptive receptive field adjustment; and Efficient Dual-level Attention Mechanism (EDAM) to reduce computational complexity while maintaining feature expression capability. Experimental results demonstrate that compared to the baseline YOLO11, our proposed model improved mAP50 and mAP50:95 on the RS-APD dataset by 2.1% and 2.5%, respectively, with APs increasing by 2.8%. This research provides an efficient and reliable small object detection solution for remote sensing applications.

Visual perception is fundamental to robotic manipulation for recognizing objects, goals, and contextual details. Third-person cameras provide global views but can miss contact-rich interactions and require calibration. Wrist-mounted egocentric cameras reduce these limitations but introduce occlusion, motion blur, and partial observability, which complicate visuomotor learning. Furthermore, existing perception modules that rely solely on pixels or fuse imagery with proprioception as flat vectors do not explicitly model structured scene representations in dynamic egocentric views. To address these challenges, a multi-slot attention fusion encoder for egocentric manipulation is introduced. Learnable slot queries extract localized visual features from image tokens, and Feature-wise Linear Modulation (FiLM) conditions each slot on the robot’s joint states, producing a structured slot-based latent representation that adapts to viewpoint and configuration changes without requiring object labels or external camera priors. The resulting structured slot-based latent representation is used as input to a Soft Actor–Critic (SAC) agent, which achieves a higher mean cumulative return than pixel-only CNN/DrQ and state-only baselines on a ManiSkill3 egocentric manipulation task. Probing experiments and real-camera evaluation further show that the learned representation remains stable under egocentric viewpoint shifts and partial occlusions, indicating robustness in practical manipulation settings.

Lyme disease diagnosis poses a significant challenge, with blood tests exhibiting an alarming inaccuracy rate of nearly 60% in detecting early-stage infections. As a result, there is an urgent need for improved diagnostic methods that can offer more accurate detection outcomes. To address this pressing issue, our study focuses on harnessing the potential of deep learning approaches, specifically by employing model pipelining through progressive resizing and multiple self-supervised learning models. In this paper, we present a comprehensive exploration of self-supervised learning models, including SimCLR, SwAV, MoCo, and BYOL, tailored to the context of Lyme disease detection using medical imaging. The effectiveness and performance of these models are evaluated using standard metrics such as F1 score, precision, recall, and accuracy. Furthermore, we emphasize the significance of progressive resizing and its implications when dealing with convolutional neural networks (CNNs) for medical image analysis. By leveraging deep learning approaches, progressive resizing, and self-supervised learning models, the challenges associated with Lyme disease detection are effectively addressed in this study. The application of our novel methodology and the execution of a comprehensive evaluation framework contribute invaluable insights, fostering the development of more efficient and accurate diagnostic methods for Lyme disease. It is firmly believed that our research will serve as a catalyst, inspiring interdisciplinary collaborations that accelerate progress at the convergence of medicine, computing, and technology, ultimately benefiting public health.

Significant advancements have been witnessed in visual tracking applications leveraging ViT in recent years, mainly due to the formidable modeling capabilities of Vision Transformer (ViT). However, the strong performance of such trackers heavily relies on ViT models pretrained for long periods, limiting more flexible model designs for tracking tasks. To address this issue, we propose an efficient unsupervised ViT pretraining method for the tracking task based on masked autoencoders, called TrackMAE. During pretraining, we employ two shared-parameter ViTs, serving as the appearance encoder and motion encoder, respectively. The appearance encoder encodes randomly masked image data, while the motion encoder encodes randomly masked pairs of video frames. Subsequently, an appearance decoder and a motion decoder separately reconstruct the original image data and video frame data at the pixel level. In this way, ViT learns to understand both the appearance of images and the motion between video frames simultaneously. Experimental results demonstrate that ViT-Base and ViT-Large models, pretrained with TrackMAE and combined with a simple tracking head, achieve state-of-the-art (SOTA) performance without additional design. Moreover, compared to the currently popular MAE pretraining methods, TrackMAE consumes only 1/5 of the training time, which will facilitate the customization of diverse models for tracking. For instance, we additionally customize a lightweight ViT-XS, which achieves SOTA efficient tracking performance.

Aiming at the problem that the existing methods are insufficient in dealing with the background noise anti-interference of underwater fish images, a contrastive learning method of ignoring background called CLIB for underwater fish image classification is proposed to improve the accuracy and robustness of underwater fish image classification. First, CLIB effectively separates the subject from the background in the image through the extraction module and applies it to contrastive learning by composing three complementary views with the original image. To further improve the adaptive ability of CLIB in complex underwater images, we propose a multi-view-based contrastive loss function, whose core idea is to enhance the similarity between the original image and the subject and maximize the difference between the subject and the background, making CLIB focus more on learning the core features of the subject during the training process, and effectively ignoring the interference of background noise. Experiments on the Fish4Knowledge, Fish-gres, WildFish-30, and QUTFish-89 public datasets show that our method performs well, with improvements of 1.43–6.75%, 8.16–8.95%, 13.1–14.82%, and 3.92–6.19%, respectively, compared with the baseline model, further validating the effectiveness of CLIB.

In this study, the authors study a deep learning model that can convert vision into tactile information, so that different texture images can be fed back to the tactile signal close to the real tactile sensation after training and learning. This study focuses on the classification of different image visual information and its corresponding tactile feedback output mode. A training model of ensembled generative adversarial networks is proposed, which has the characteristics of simple training and stable efficiency of the result. At the same time, compared with the previous methods of judging the tactile output, in addition to subjective human perception, this study also provides an objective and quantitative evaluation system to verify the performance of the model. The experimental results show that the learning model can transform the visual information of the image into the tactile information, which is close to the real tactile sensation, and also verify the scientificity of the tactile evaluation method.