Large vision-language models (LVLMs) demonstrate strong performance in dermatology; however, evaluating diagnostic reasoning for rare conditions remains largely unexplored. Existing benchmarks focus on common diseases and assess only final accuracy, overlooking the clinical reasoning process, which is critical for complex cases. We address this gap by constructing DermCase, a long-context benchmark derived from peer-reviewed case reports. Our dataset contains 26,030 multi-modal image-text pairs and 6,354 clinically challenging cases, each annotated with comprehensive clinical information and step-by-step reasoning chains. To enable reliable evaluation, we establish DermLIP-based similarity metrics that achieve stronger alignment with dermatologists for assessing differential diagnosis quality. Benchmarking 22 leading LVLMs exposes significant deficiencies across diagnosis accuracy, differential diagnosis, and clinical reasoning. Fine-tuning experiments demonstrate that instruction tuning substantially improves performance while Direct Preference Optimization (DPO) yields minimal gains. Systematic error analysis further reveals critical limitations in current models' reasoning capabilities.

Face super-resolution aims to recover high-quality facial images from severely degraded low-resolution inputs, but remains challenging due to the loss of fine structural details and identity-specific features. This work introduces SwinIFS, a landmark-guided super-resolution framework that integrates structural priors with hierarchical attention mechanisms to achieve identity-preserving reconstruction at both moderate and extreme upscaling factors. The method incorporates dense Gaussian heatmaps of key facial landmarks into the input representation, enabling the network to focus on semantically important facial regions from the earliest stages of processing. A compact Swin Transformer backbone is employed to capture long-range contextual information while preserving local geometry, allowing the model to restore subtle facial textures and maintain global structural consistency. Extensive experiments on the CelebA benchmark demonstrate that SwinIFS achieves superior perceptual quality, sharper reconstructions, and improved identity retention; it consistently produces more photorealistic results and exhibits strong performance even under 8× magnification, where most methods fail to recover meaningful structure. SwinIFS also provides an advantageous balance between reconstruction accuracy and computational efficiency, making it suitable for real-world applications in facial enhancement, surveillance, and digital restoration. Our code, model weights, and results are available at https://github.com/Habiba123-stack/SwinIFS.

Most recent extreme rescaling methods struggle to preserve semantically consistent structures and produce realistic details, due to the severely ill-posed nature of low- to high-resolution mapping under scaling factors of 16× or higher. To alleviate the above problems, we propose FaithEIR, a diffusion-based framework for extreme image rescaling. Inspired by singular value decomposition, we develop learnable reversible transformation that enables invertible downscaling and upscaling in the latent space. To compensate for information loss due to quantization, we propose an adaptive detail prior, a high-frequency dictionary that captures the empirical average of commonly occurring structures in the training data. Finally, we design a lightweight pixel semantic embedder to provide semantic conditioning for the pretrained diffusion model. We present extensive experimental results demonstrating that our FaithEIR consistently outperforms state-of-the-art methods, achieving superior reconstruction fidelity and perceptual quality. Our code, model weights, and detailed results are released at https://github.com/cshw2021/FaithEIR.

Vision Language Models (VLMs) provide rich semantic priors but are underexplored in Semi supervised Semantic Segmentation. Recent attempts to integrate VLMs to inject high level semantics overlook the semantic misalignment between visual and textual representations that arises from using domain invariant text embeddings without adapting them to dataset and image specific contexts. This lack of domain awareness, coupled with limited annotations, weakens the model semantic understanding by preventing effective vision language alignment. As a result, the model struggles with contextual reasoning, shows weak intra class discrimination, and confuses similar classes. To address these challenges, we propose Hierarchical Vision Language transFormer (HVLFormer), which achieves domain aware and domain robust alignment between visual and textual representations within a mask transformer architecture. Firstly, we transform text embeddings from pretrained VLMs into textual object queries, enabling the generation of multi scale, dataset aware queries that capture class semantics from coarse to fine granularity and enhance contextual reasoning. Next, we refine these queries by injecting image specific visual context to align textual semantics with local scene structures and enhance class discrimination. Finally, to achieve domain robustness, we introduce cross view and modal consistency regularization, which enforces prediction consistency within mask-transformer architecture across augmented views. Moreover, it ensures stable vision language alignment during decoding. With less than 1

Backlit and low-light images often suffer from severe exposure imbalance or global underexposure, presenting significant challenges for both visual perception and downstream computer vision tasks. In this paper, we propose a unified, unsupervised enhancement framework that addresses both types of degradation without relying on paired ground-truth data. Our approach builds on CLIP-guided prompt learning to semantically supervise enhancement using learned positive and negative textual prompts. To improve the quality of our improvements over prior work, we design a symmetric residual U-Net backbone augmented with an Atrous Spatial Pyramid Pooling module. This architecture captures multi-scale contextual information, enabling adaptive correction under spatially heterogeneous illumination. During training, the enhancement network is guided by CLIP-based semantic similarity losses and refined via an iterative prompt optimization mechanism. Extensive experiments on both paired and unpaired datasets, including BAID, Backlit300, LOL, and VE-LOL-L, demonstrate that our framework consistently outperforms state-of-the-art supervised and unsupervised methods in terms of fidelity, perceptual quality, and generalization. Furthermore, our work emphasizes the need for stronger benchmarking protocols for backlit enhancement, a relatively underexplored area. The proposed framework provides a robust, scalable solution for real-world illumination enhancement across diverse lighting conditions.

This review provides an in-depth exploration of the field of animal action recognition, focusing on coarse-grained (CG) and fine-grained (FG) techniques. The primary aim is to examine the current state of research in animal behaviour recognition and to elucidate the unique challenges associated with recognising subtle animal actions in outdoor environments. These challenges differ significantly from those encountered in human action recognition due to factors such as non-rigid body structures, frequent occlusions, and the lack of large-scale, annotated datasets. This review underscores the critical differences between human and animal action recognition. While inspired by progress in the human domain, animal action recognition presents unique challenges due to high intra-species variability, complex environmental interactions, and unstructured datasets that human-centric models cannot fully address. Recent multimodal frameworks such as ARTEMIS and MSQNet exemplify state-of-the-art progress by integrating textual cues derived from video with visual and audio modalities. When considered alongside established spatio-temporal architectures like SlowFast, these developments signal a shift toward richer multimodal paradigms in behaviour analysis. By assessing the strengths and weaknesses of current methodologies and introducing a recently published dataset, the review outlines future directions for advancing fine-grained action recognition, aiming to improve accuracy and generalisability in behaviour analysis across species. This review extends beyond earlier reviews by offering the first systematic treatment of coarse-grained (CG) and fine-grained (FG) action recognition in animals.

Diffusion probabilistic models are traditionally used to generate colors at fixed pixel positions in 2D images. Building on this, we extend diffusion models to point cloud semantic segmentation, where point positions also remain fixed, and the diffusion model generates point labels instead of colors. To accelerate the denoising process in reverse diffusion, we introduce a noisy label embedding mechanism. This approach integrates semantic information into the noisy label, providing an initial semantic reference that improves the reverse diffusion efficiency. Additionally, we propose a point frequency transformer that enhances the adjustment of high-level context in point clouds. To reduce computational complexity, we introduce the position condition into MLP and propose denoising PointNet to process the high-resolution point cloud without sacrificing geometric details. Finally, we integrate the proposed noisy label embedding, point frequency transformer and denoising PointNet in our proposed dual conditional diffusion model-based network (PointDiffuse) to perform large-scale point cloud semantic segmentation. Extensive experiments on five benchmarks demonstrate the superiority of PointDiffuse, achieving the state-of-the-art mIoU of 74.2% on S3DIS Area 5, 81.2% on S3DIS 6-fold and 64.8% on SWAN dataset.

Reconstructing continuous surfaces from unoriented and unordered 3D points is a fundamental challenge in computer vision and graphics. Recent advancements address this problem by training neural signed distance functions to pull 3D location queries to their closest points on a surface, following the predicted signed distances and the analytical gradients computed by the network. In this paper, we introduce NumGrad-Pull, leveraging the representation capability of tri-plane structures to accelerate the learning of signed distance functions and enhance the fidelity of local details in surface reconstruction. To further improve the training stability of grid-based tri-planes, we propose to exploit numerical gradients, replacing conventional analytical computations. Additionally, we present a progressive plane expansion strategy to facilitate faster signed distance function convergence and design a data sampling strategy to mitigate reconstruction artifacts. Our extensive experiments across a variety of benchmarks demonstrate the effectiveness and robustness of our approach. Code is available at https://github.com/CuiRuikai/NumGrad-Pull

We propose an automatic framework for toll collection, consisting of three steps: vehicle type recognition, license plate localization, and reading. However, each of the three steps becomes non-trivial due to image variations caused by several factors. The traditional vehicle decorations on the front cause variations among vehicles of the same type. These decorations make license plate localization and recognition difficult due to severe background clutter and partial occlusions. Likewise, on most vehicles, specifically trucks, the position of the license plate is not consistent. Lastly, for license plate reading, the variations are induced by non-uniform font styles, sizes, and partially occluded letters and numbers. Our proposed framework takes advantage of both data availability and performance evaluation of the backbone deep learning architectures. We gather a novel dataset, \emph{Diverse Vehicle and License Plates Dataset (DVLPD)}, consisting of 10k images belonging to six vehicle types. Each image is then manually annotated for vehicle type, license plate, and its characters and digits. For each of the three tasks, we evaluate You Only Look Once (YOLO)v2, YOLOv3, YOLOv4, and FasterRCNN. For real-time implementation on a Raspberry Pi, we evaluate the lighter versions of YOLO named Tiny YOLOv3 and Tiny YOLOv4. The best Mean Average Precision (mAP@0.5) of 98.8% for vehicle type recognition, 98.5% for license plate detection, and 98.3% for license plate reading is achieved by YOLOv4, while its lighter version, i.e., Tiny YOLOv4 obtained a mAP of 97.1%, 97.4%, and 93.7% on vehicle type recognition, license plate detection, and license plate reading, respectively. The dataset and the training codes are available at https://github.com/usama-x930/VT-LPR

Most existing extreme compression methods fail to achieve an optimal rate-distortion-perception trade-off, as they typically prioritize perceptual fidelity and visual realism over pixel-level accuracy. Consequently, the resulting reconstructions often deviate noticeably from the originals. Ultra-low bitrate image compression is therefore crucial-not only for producing extremely compact representations but also for ensuring that reconstructed images remain semantically coherent and faithful to the source at the pixel level. To this end, we propose SPRDiff, a diffusion-based compression method that fully leverages both semantic and pixel representations, thereby enhancing reconstruction fidelity under ultra-low bitrate constraints. Specifically, we develop a triple-encoder architecture that utilizes high-fidelity features from the pretrained distortion-oriented and semantic-oriented encoders to compensate for the limited representations extracted by the frozen VAE encoder, thereby improving latent compression and entropy modeling. To further enhance the reconstruction fidelity of diffusion models, we introduce a distortion-aware reconstruction module with dual feature extraction. This module not only generates a coarse reconstruction that preserves the main structures, but also provides practical and accurate semantic- and pixel-level conditional signals to guide the diffusion model. Extensive experiments on benchmark datasets demonstrate that our method outperforms state-of-the-art approaches in the rate-distortion-perception tradeoff at extremely low bitrates (below 0.03 bpp), effectively preserving both perceptual quality and pixel-wise fidelity in the reconstructed images. We will release the source code and trained models at https://github.com/cshw2021/SPRDiff.

Point cloud learning is receiving increasing attention. However, most existing point cloud models lack the practical ability to deal with the unavoidable presence of unknown objects. This paper primarily discusses point cloud learning in open-set settings, where we train the model without data from unknown classes and identify them during the inference stage. In essence, we propose a novel Point Cut-and-Mix mechanism for solving open-set point cloud learning, comprising an Unknown-Point Simulator and an Unknown-Point Estimator module. Specifically, we use the Unknown-Point Simulator to simulate out-of-distribution data in the training stage by manipulating the geometric context of partially known data. Based on this, the Unknown-Point Estimator module learns to exploit the point cloud's feature context to discriminate between known and unknown data. Unlike existing methods that only consider classifier features, our proposed solution leverages multi-level feature contexts to recognize unknown point cloud objects more effectively. We test the proposed approach on several datasets, including customized S3DIS, ModelNet40, and ScanObjectNN. The improved open-set performances over comparative baselines show the effectiveness of our PointCaM method. Our code is available at https://github.com/JHome1/pointcam.

Road damage detection and assessment are crucial components of infrastructure maintenance. However, detecting multiple crack types in a single image remains a challenging limitation, particularly at varying scales. This is due to the lack of road datasets with various types of damage on varying scales. To address this challenge, we introduce: 1) A novel dataset called the Diverse Road Damage Dataset (DRDD) that captures multiple damage types per individual image. 2) A new detection model called RDD4D that exploits Attention4D blocks to enable better feature refinement across multiple scales. The Attention4D module processes feature maps through an attention mechanism combining positional encoding and talking head components to extract both local and global contextual features. In our comprehensive experimental analysis comparing various state-of-the-art models, our enhanced model demonstrates superior performance in detecting large-sized road cracks with an Average Precision (AP) of 0.458 and maintained competitive performance with an overall mAP of 0.446 on our proposed dataset. Moreover, we also provide results on the CrackTinyNet dataset; our model achieved around a 0.21 increase in performance. The code, model weights, dataset, and our results are publicly available at https://github.com/msaqib17/Road_Damage_Detection.

3D skeletal action recognition has emerged as a powerful alternative to traditional RGB and depth-based approaches, offering robustness to environmental variations, computational efficiency, and enhanced privacy. Despite remarkable progress, current research remains fragmented across diverse input representations and lacks evaluation under scenarios that reflect real-world challenges. This paper presents a representation-centric review of supervised skeletal action recognition, systematically categorizing state-of-the-art methods by their input feature types: joint coordinates, bone vectors, motion flows, and extended representations, and analyzing how these choices influence spatiotemporal modeling strategies. Building on the insights from this review, we introduce ANUBIS, a large-scale, challenging dataset designed to address critical gaps in existing benchmarks. ANUBIS incorporates multi-view recordings with back-view perspectives, complex multi-person interactions, fine-grained and violent actions, and contemporary social behaviors. We benchmark a diverse set of state-of-the-art models on ANUBIS and conduct an in-depth analysis of how different feature types affect recognition performance across 102 action categories. Our results show strong action-feature dependencies, highlight the limitations of na & iuml;ve multi-representational fusion, and point toward the need for task-aware, semantically aligned integration strategies. This work offers both a comprehensive foundation and a practical benchmarking resource, aiming to guide the next generation of robust, generalizable skeleton-based action recognition systems for complex real-world scenarios. The dataset, benchmarking framework, and code are available at https://yliu1082.github.io/ANUBIS/.

Camouflaged object detection segments objects with intrinsic similarity and edge disruption. Current detection methods rely on accumulated complex components. Each approach adds components such as boundary modules, attention mechanisms, and multi-scale processors independently. This accumulation creates a computational burden without proportional gains. To manage this complexity, they process at reduced resolutions, eliminating fine details essential for camouflage. We present SPEGNet, addressing fragmentation through synergistic design. The architecture integrates multi-scale features via channel calibration and spatial enhancement. Boundaries emerge directly from context-rich representations, maintaining semantic-spatial alignment. Progressive refinement implements scale-adaptive edge modulation with peak influence at intermediate resolutions. This design strikes a balance between boundary precision and regional consistency. SPEGNet achieves $0.887~S_{\alpha } $ on CAMO, 0.890 on COD10K, and 0.895 on NC4K, with real-time inference speed. Our approach excels across scales, from tiny, intricate objects to large, pattern-similar ones, while handling occlusion and ambiguous boundaries. Code, model weights, and results are available at https://github.com/Baber-Jan/SPEGNet.

The rapid advancement of generative AI has outpaced our ability to reliably detect its outputs, particularly when detectors encounter generators they have not seen before. We introduce GenSyn10, a CIFAR-10-aligned synthetic image dataset of 60,000 images (10 classes, 32×32, 50k/10k split) generated using three architecturally diverse state-of-the-art models: FLUX.2-dev (Rectified Flow Transformer), HunyuanImage-3.0 (MoE Transformer), and Qwen-Image-2512 (Multimodal Diffusion Transformer), to advance research in AI-generated image detection. A central challenge in this domain is that detectors perform well on known generators but degrade on unseen ones. GenSyn10 addresses this limitation by curating data from multiple contemporary architectures under a standardized generation protocol, enabling controlled and systematic evaluation of out-of-distribution (OOD) generalization to novel generators. Images are generated using a template-based prompt engine and downsampled to ensure consistency. We evaluate 17 image classification models under a four-stage protocol: real-data baseline, zero-shot transfer, fine-tuning, and retention. Despite a measurable domain gap, CIFAR-10-trained models achieve up to 96.86% zero-shot accuracy on GenSyn10, increasing to 99.88% after fine-tuning. In binary real-vs-synthetic classification, fine-tuned models achieve 97-99.9% accuracy on seen generators but drop to 79-96% on images from an unseen generator, highlighting persistent limitations in OOD generalization. These results establish GenSyn10 as a controlled benchmark for studying synthetic image detection beyond single-generator settings, supporting research on robustness, domain adaptation, and cross-generator generalization.

While conventional lossy compression methods predominantly depend on autoencoders to map point clouds into latent representations, they often neglect the intrinsic redundancy within these latent points. To address this limitation, this paper presents a diffusion-based architecture steered by sparse priors, designed to minimize latent redundancy while securing superior reconstruction fidelity, particularly in low-bitrate scenarios. A key feature of the framework is an efficient dual-density data flow that alleviates the stringent size constraints imposed on latent points. By integrating a Probabilistic Attention-based Conditional Denoiser (PACD), the method effectively encapsulates critical reconstruction details within sparse priors, which are hierarchically decoupled into intra- and inter-point components. Specifically, separate encoders are utilized to transform the source point cloud into latent points and decoupled sparse priors, respectively. To dynamically exploit geometric and semantic information, an attention-driven latent denoiser, conditioned on these decoupled priors, is applied across the encoding and decoding layers. Furthermore, inter-point distributions are incorporated into the arithmetic codec to refine local context modeling for sparse points, with the final point cloud recovered via a point decoder. Comprehensive experiments conducted on ShapeNet and standard MPEG PCC datasets demonstrate that the proposed method outperforms state-of-the-art techniques, achieving a superior rate-distortion trade-off.

Deep learning has evolved from early perceptron models to modern foundation models through a series of breakthroughs that addressed fundamental limitations in representation learning, optimization, computational efficiency, and scalability. While numerous surveys review specific architectures, learning paradigms, or application domains, few examine the field from a historical and evolutionary perspective. This paper traces the evolution of deep learning by identifying the key discoveries that shaped its development, the bottlenecks that motivated each advance, and the innovations that enabled subsequent progress. Without an understanding of the historical motivations behind major breakthroughs, researchers may inadvertently revisit previously resolved challenges or overlook design principles that have shaped modern deep learning architectures. Understanding why particular architectures emerged and how they addressed existing limitations can help researchers avoid revisiting previously solved problems and make more informed design decisions for future models. Beginning with the origins of artificial neural networks and the introduction of backpropagation, we examine the resurgence of deep learning driven by large-scale datasets, GPU computing, and architectural innovations, followed by developments in convolutional, recurrent, attention-based, graph, generative, and foundation models. Rather than providing an exhaustive review, this paper focuses on the seminal methods that established new research directions and highlights representative applications in which these advances have been successfully adopted. By connecting major breakthroughs with the challenges they addressed, this survey equips new researchers with a principled understanding of deep learning’s evolution and a foundation for developing novel approaches to emerging problems.

Text-Based Person Retrieval is a fine-grained cross-modal task that matches natural language descriptions with person images. However, text descriptions and person images often exhibit different semantic granularity and diverse variations. This discrepancy induces cross-modal semantic dispersion, leading to fragmented attribute binding, which hinders precise person matching. In this paper, we propose Auto-Feedback Semantic Interface Learning (ASIL), a framework that learns structured semantic representations to mitigate cross-modal semantic dispersion via self-supervised consistency feedback. First, we introduce an Interface-Induced Semantic Representation Learning mechanism, which employs a set of semantic interfaces to induce structured semantic subspaces. This design supports continuous and self-organized semantic representation learning. Second, we propose a Self-Supervised Semantic Auto-Feedback mechanism, which treats each image and each text as a selfcontained knowledge source for inferring context-aware semantic responses. By leveraging internal semantic consistency as feedback, ASIL enables semantic learning without relying on explicit semantic annotations or external supervision. Third, we design a Cross-Modal Answer Consistency strategy to enforce point-topoint mutual supervision between visual and textual semantic responses within each semantic subspace. This constraint promotes precise instance-level semantic continuity across modalities. Finally, we introduce a Person-Level Topological Consistency Constraint to preserve the global semantic structure of the shared embedding space. Extensive experiments on three public benchmarks demonstrate that ASIL consistently outperforms existing methods.

This review provides an in-depth exploration of the field of animal action recognition, focusing on coarse-grained (CG) and fine-grained (FG) techniques. The primary aim is to examine the current state of research in animal behaviour recognition and to elucidate the unique challenges associated with recognising subtle animal actions in outdoor environments. These challenges differ significantly from those encountered in human action recognition due to factors such as non-rigid body structures, frequent occlusions, and the lack of large-scale, annotated datasets. The review begins by discussing the evolution of human action recognition, a more established field, highlighting how it progressed from broad, coarse actions in controlled settings to the demand for fine-grained recognition in dynamic environments. This shift is particularly relevant for animal action recognition, where behavioural variability and environmental complexity present unique challenges that human-centric models cannot fully address. The review then underscores the critical differences between human and animal action recognition, with an emphasis on high intra-species variability, unstructured datasets, and the natural complexity of animal habitats. Techniques like spatio-temporal deep learning frameworks (e.g., SlowFast) are evaluated for their effectiveness in animal behaviour analysis, along with the limitations of existing datasets. By assessing the strengths and weaknesses of current methodologies and introducing a recently-published dataset, the review outlines future directions for advancing fine-grained action recognition, aiming to improve accuracy and generalisability in behaviour analysis across species.

Deep convolutional neural networks perform better on images containing spatially invariant degradations, also known as synthetic degradations; however, their performance is limited on real-degraded photographs and requires multiple-stage network modeling. To advance the practicability of restoration algorithms, this article proposes a novel single-stage blind real image restoration network (R²Net) by employing a modular architecture. We use a residual on the residual structure to ease low-frequency information flow and apply feature attention to exploit the channel dependencies. Furthermore, the evaluation in terms of quantitative metrics and visual quality for four restoration tasks, i.e., denoising, super-resolution, raindrop removal, and JPEG compression on 11 real degraded datasets against more than 30 state-of-the-art algorithms, demonstrates the superiority of our R²Net. We also present the comparison on three synthetically generated degraded datasets for denoising to showcase our method's capability on synthetics denoising. The codes, trained models, and results are available on https://github.com/saeed-anwar/R2Net.