Sketch–photo recognition refers to matching hand-drawn sketches with their corresponding photos, where the performance essentially depends on how well the representations of the two modalities are aligned in the feature spaces. Existing works bluntly force models to reduce the representation discrepancy between the modalities, making the learning less effective. Besides, the current symmetric feature extraction framework prefers the photo modality for richer information while neglecting the sketch modality. Driven by these observations, we argue that, instead of forcefully wiping out the modality discrepancy, we may utilize the discrepancy to enhance model learning. Thus, we propose a Cross-Modality Bootstrapping learning framework (CROMBO) that utilizes the modality discrepancy to bootstrap cross-modality representation learning via a differentiated interaction manner. Specifically, we first present a Sketch Implicit Bootstrapping (SIB) module to magnify the recognizable elements in the photo modality by utilizing the characteristic of sketches having only contours and key details. Second, a Photo-driven Sketch Refinement (PSR) module is developed to guide the sketch representation in the shared feature extraction process by supplementing rich information from the photo modality. Moreover, we design a second-order alignment strategy to dynamically align the latent distribution of two modalities in a Hilbert space. Also, our CROMBO can learn fewer parameters by freezing the weights of shallow layers in the backbone while making no sacrifice in performance. Extensive experiments on six public datasets verify the superior performance of our CROMBO for sketch–photo-based tasks, such as sketch re-identification (Re-ID), sketch–photo face recognition, and sketch-based image retrieval.

Face de-identification (FDeID) aims to remove personally identifiable information from facial images while preserving task-relevant utility attributes such as age, gender, and expression. It is critical for privacy-preserving computer vision, yet the field suffers from fragmented implementations, inconsistent evaluation protocols, and incomparable results across studies. These challenges stem from the inherent complexity of the task: FDeID spans multiple downstream applications (e.g., age estimation, gender recognition, expression analysis) and requires evaluation across three dimensions (e.g., privacy protection, utility preservation, and visual quality), making existing codebases difficult to use and extend. To address these issues, we present FDeID-Toolbox, a comprehensive toolbox designed for reproducible FDeID research. Our toolbox features a modular architecture comprising four core components: (1) standardized data loaders for mainstream benchmark datasets, (2) unified method implementations spanning classical approaches to SOTA generative models, (3) flexible inference pipelines, and (4) systematic evaluation protocols covering privacy, utility, and quality metrics. Through experiments, we demonstrate that FDeID-Toolbox enables fair and reproducible comparison of diverse FDeID methods under consistent conditions.

Face de-identification (De-ID) aims to remove or conceal personally identifiable facial features in images or videos to prevent identity recognition while preserving utility for downstream tasks. With the rising emphasis on data privacy and responsible AI, face De-ID has emerged as an active research area spanning computer vision and privacy-preserving communities. Early approaches, and many contemporary ones, operate in the digital domain by modifying pixel-level or appearance-level features through post-capture processing. Recent advances extend face De-ID beyond post-processing by integrating privacy mechanisms directly into sensors during image acquisition, bridging sensing systems and downstream vision algorithms. In parallel, physical-domain methods explore wearable accessories and materials that conceal identity information in real-world environments prior to capture. In this survey, we present the first unified overview that spans the full data acquisition pipeline, encompassing the physical, sensor, and digital domains. Through this domain-centric lens, we systematically analyze current methodologies, technical progress, and the distinct challenges inherent to each stage. We then review and organize existing evaluation protocols, examining current practices and highlighting the critical need for standardized, comprehensive benchmarks. Finally, we identify key open problems and outline emerging research directions to guide future work in this rapidly evolving field. To support ongoing research, we maintain a project page that organizes relevant literature with collected datasets and open source code: https://github.com/CV-AC/Awesome-FaceDe-ID.

Visible-infrared person re-identification is a challenging task in video surveillance. Most existing works achieve performance gains by aligning feature distributions or image styles across modalities, whereas the multi-granularity information and domain knowledge are usually neglected. Motivated by these issues, we propose a novel modality-aware domain alignment network (MDANet) for visible-infrared person re-identification (VI-ReID), which utilizes global-local context cues and the generalized domain alignment strategy to solve modal differences and poor generalization. Firstly, modality-aware global-local context attention (MGLCA) is proposed to obtain multi-granularity context features and identity-aware patterns. Secondly, we present a generalized domain alignment learning head (GDALH) to relieve the modality discrepancy and enhance the generalization of MDANet, whose core idea is to enrich feature diversity in the domain alignment procedure. Finally, the entire network model is trained by proposing cross-modality circle, classification, and domain alignment losses in an end-to-end fashion. We conduct comprehensive experiments on two standards and their corrupted VI-ReID datasets to validate the robustness and generalization of our approach. MDANet is obviously superior to the most state-of-the-art methods. Specifically, the proposed method can gain 8.86% and 2.50% in Rank-1 accuracy on SYSU-MM01 (all-search and single-shot mode) and RegDB (infrared to visible mode) datasets, respectively. The source code will be made available soon.

Aiming to match pedestrian images captured under varying lighting conditions, visible-infrared person re-identification (VI-ReID) has drawn intensive research attention and achieved promising results. However, in real-world surveillance contexts, data is distributed across multiple devices/entities, raising privacy and ownership concerns that make existing centralized training impractical for VI-ReID. To tackle these challenges, we propose L2RW, a benchmark that brings VI-ReID closer to real-world applications. The rationale of L2RW is that integrating decentralized training into VI-ReID can address privacy concerns in scenarios with limited data-sharing regulation. Specifically, we design protocols and corresponding algorithms for different privacy sensitivity levels. In our new benchmark, we ensure the model training is done in the conditions that: 1) data from each camera remains completely isolated, or 2) different data entities (e.g., data controllers of a certain region) can selectively share the data. In this way, we simulate scenarios with strict privacy constraints which is closer to real-world conditions. Intensive experiments with various server-side federated algorithms are conducted, showing the feasibility of decentralized VI-ReID training. Notably, when evaluated in unseen domains (i.e., new data entities), our L2RW, trained with isolated data (privacy-preserved), achieves performance comparable to SOTAs trained with shared data (privacy-unrestricted). We hope this work offers a novel research entry for deploying VI-ReID that fits real-world scenarios and can benefit the community.

In the pursuit of efficient vision architectures, substantial efforts have been devoted to optimizing operator efficiency. Depth-wise separable operators, such as DWConv, are found cheap in both FLOPs and parameters. As a result, they are increasingly incorporated into efficient backbones, trading for deeper and wider architectures to enhance performance. However, separable operators are not really fast on devices due to the discontinuous memory access requirements. In this paper, we propose FreeNets, a family of simple and efficient backbones that free the separable operation to further accelerate the running speed. We introduce sparse sampling mixers (S2-Mixer) to supersede existing separable token mixers. The S2-Mixer samples multiple segments of partially continuous signals across spatial and channel dimensions for convolutional processing, achieving extremely fast on-device speed. The sparse sampling also enables S2-Mixer to capture long-range pixel relationships from dynamic receptive fields. Furthermore, we introduce a Shift Feed-Forward Network (ShiftFFN) as a faster alternative to existing channel mixers. It utilizes a shift neck architecture that aggregates global information to shift features, enabling faster channel mixing while incorporating global pixel information. Extensive experiments demonstrate that FreeNet offers a superior accuracy-efficiency tradeoff compared to the latest efficient models. On ImageNet-1k, FreeNet-S2 outperforms the StarNet-S4 by 0.4% in top-1 accuracy, while running around 40% faster on desktop GPU and 15% faster on Mobile GPU.

Self-attention (SA) has become the cornerstone of modern vision backbones for its powerful expressivity over traditional Convolutions (Conv). However, its quadratic complexity remains a critical bottleneck for practical applications. Given that Conv offers linear complexity and strong visual priors, continuing efforts have been made to promote the renaissance of Conv. However, a persistent performance chasm remains, highlighting that these modernizations have not yet captured the intrinsic expressivity that defines SA. In this paper, we re-examine the design of the CNNs, directed by a key question: what principles give SA its edge over Conv? As a result, we reveal two fundamental insights that challenge the long-standing design intuitions in prior research (e.g., Receptive field). The two findings are: (1) Adaptive routing: SA dynamically regulates positional information flow according to semantic content, whereas Conv employs static kernels uniformly across all positions. (2) Lateral inhibition: SA induces score competition among token weighting, effectively suppressing redundancy and sharpening representations, whereas Conv filters lack such inhibitory dynamics and exhibit considerable redundancy. Based on this, we propose Attentive Convolution (ATConv), a principled reformulation of the convolutional operator that intrinsically injects these principles. Interestingly, with only 3×3 kernels, ATConv consistently outperforms various SA mechanisms in fundamental vision tasks. Building on ATConv, we introduce AttNet, a CNN family that can attain 84.4% ImageNet-1K Top-1 accuracy with only 27M parameters. In diffusion-based image generation, replacing all SA with the proposed 3× 3 ATConv in SiT-XL/2 reduces ImageNet FID by 0.15 in 400k steps with faster sampling. Code is available at: github.com/price112/Attentive-Convolution.

Visible-infrared person re-identification (VI-ReID) is a cross-modality retrieval task that aims to match visible and infrared pedestrian images across non-overlapped cameras. However, we observe that three crucial challenges remain inadequately addressed by existing methods: (i) limited discriminative capacity for modality-shared representation, (ii) modality misalignment, and (iii) neglect of identity consistency knowledge. To solve the above issues, we propose a novel dual space alignment framework (DSAF) to constrain the modality in two specific spaces. Specifically, for (i), we design a lightweight and plug-and-play modality invariant enhancement (MIE) module to capture fine-grained semantic information and render identity discriminative. This facilitates the establishment of correlations between visible and infrared modalities, enabling the model to learn robust modality-shared features. To tackle (ii), a dual space alignment (DSA) is introduced to conduct the pixel-level alignment in both Euclidean space and Hilbert space. DSA establishes an elastic relationship between these two spaces, remaining invariant knowledge across two spaces. To solve (iii), we propose an adaptive identity-consistent learning (AIL) to discover identity-consistent knowledge between visible and infrared modalities in a dynamic manner. Extensive experiments on mainstream VI-ReID benchmarks show the superiority and flexibility of our proposed method, achieving competitive performance on mainstream datasets.

Image matching, which aims to identify corresponding pixel locations between images, is crucial in a wide range of scientific disciplines, aiding in image registration, fusion, and analysis. In recent years, deep learning-based image matching algorithms have dramatically outperformed humans in rapidly and accurately finding large amounts of correspondences. However, when dealing with images captured under different imaging modalities that result in significant appearance changes, the performance of these algorithms often deteriorates due to the scarcity of annotated cross-modal training data. This limitation hinders applications in various fields that rely on multiple image modalities to obtain complementary information. To address this challenge, we propose a large-scale pre-training framework that utilizes synthetic cross-modal training signals, incorporating diverse data from various sources, to train models to recognize and match fundamental structures across images. This capability is transferable to real-world, unseen cross-modality image matching tasks. Our key finding is that the matching model trained with our framework achieves remarkable generalizability across more than eight unseen cross-modality registration tasks using the same network weight, substantially outperforming existing methods, whether designed for generalization or tailored for specific tasks. This advancement significantly enhances the applicability of image matching technologies across various scientific disciplines and paves the way for new applications in multi-modality human and artificial intelligence analysis and beyond.

Image tampering techniques can lead to distorted or misleading information, which in turn poses a threat in many areas, including social, legal and commercial. Numerous image tampering detection algorithms lose important low-level detail information when extracting deep features, reducing the accuracy and robustness of detection. In order to solve the problems of current methods, this paper proposes a new network called IFE-Net to detect three types of tampered images, namely copy-move, heterologous splicing and removal. Firstly, this paper constructs the noise stream using the attention mechanism CBAM to extract and optimize the noise features. The high-level features are extracted by the backbone network of RGB stream, and the FEASPP module is built for capturing and enhancing the features at different scales. In addition, in this paper, the initial features of RGB stream are additionally supervised so as to limit the detection area and reduce the false alarm. Finally, the final prediction results are obtained by fusing the noise features with the RGB features through the Dual Attention Mechanism (DAM) module. Extensive experimental results on multiple standard datasets show that IFE-Net can accurately locate the tampering region and effectively reduce false alarms, demonstrating superior performance.

Visible-infrared person re-identification (VI-ReID) presents significant challenges on account of the substantial cross-modality gap and intra-class variations. Most existing methods primarily concentrate on aligning cross-modality at the feature or image levels and training with an equal number of samples from different modalities. However, in the real world, there exists an issue of modality imbalance between visible and infrared data. Besides, imbalanced samples between train and test impact the robustness and generalization of the VI-ReID. To alleviate this problem, we propose a dual-path imbalanced feature compensation network (DICNet) for VI-ReID, which provides equal opportunities for each modality to learn inconsistent information from different identities of others, enhancing identity discrimination performance and generalization. First, a modality consistency perception (MCP) module is designed to assist the backbone focus on spatial and channel information, extracting diverse and salient features to enhance feature representation. Second, we propose a cross-modality features re-assignment strategy to simulate modality imbalance by grouping and re-organizing the cross-modality features. Third, we perform bidirectional heterogeneous cooperative compensation with cross-modality imbalanced feature interaction modules (CIFIMs), allowing our network to explore the identity-aware patterns from imbalanced features of multiple groups for cross-modality interaction and fusion. Further, we design a feature re-construction difference loss to reduce cross-modality discrepancy and enrich feature diversity within each modality. Extensive experiments on three mainstream datasets show the superiority of the DICNet. Additionally, competitive results in corrupted scenarios verify its generalization and robustness.

We investigate generalizable face anti-spoofing (FAS) using information bottleneck theory. As generalizable FAS aims to detect spoofing in unseen scenarios, it has recently gained significant attention. Existing methods often use adversarial strategies or auxiliary modules to learn domain-invariant features by mining data relationships from distinct source domains. However, their learned feature space may still shift for unseen data due to the spurious correlations overfitted from training domains. Our rationale is that the problem of generalized pattern learning in FAS can be framed as a unified binary-antithetical information transition process, grounded in information bottleneck theory. Specifically, we leverage mutual-information optimization to preserve the instance-level spoof-aware information while compressing domain-related information modeled from the antithetical identity distribution. This enables the model to dynamically identify domain-agnostic, minimal sufficient representations that consistently describe the live/spoof distributions while mitigating spurious correlations through cross-identity compression. In light of this, we propose a novel learning framework for FAS, named Binary-Antithetical Information Bottleneck (BIB)-FAS, which is proven to be effectively generalized to unseen scenarios without using auxiliary information (e.g., domain labels) for training. Extensive cross-domain evaluations show that BIB-FAS significantly outperforms state-of-the-art methods. The code is available at: github.com/CV-AC/BIB-FAS.

The problem of classifying plastic bottles for colour recognition was solved using machine learning and multi-objective detection, which would be used to aid in the recycling of plastic bottles. For a single plastic bottle image, this paper used Sobel edge detection to obtain the edge information, located it to the original image and calculate the average RGB value at the corresponding position to eliminate the effects of bottle deformation, overlaped and some noise caused by colour classification. The RGB values were used as classification labels and the bottle colours were the output of the classification model. Through model comparison, a linear SVM-based colour classification model for a single plastic bottle was finally obtained, achieving a processing speed of 0.02 sec/sheet and 99% accuracy. The multi-target detection problem for the presence of multiple plastic bottles in a single photo is solved using YOLOX, achieving an accuracy of 97.18%. Combining the colour recognition and target detection models, a complete plastic bottle colour recognition model is finally constructed.

Cross-modality person re-identification (ReID) is a challenging task that aims to match cross-modality pedestrian images across multiple camera views. Existing methods are tailored to specific tasks and perform well for visible-infrared or visible-sketch ReID. However, the performance exhibits a notable decline when the same method is utilized for multiple cross-modality ReIDs, limiting its generalization and applicability. To address this issue, we propose a generalized domain shifting method (DNS) for cross-modality ReID, which can address the generalization and perform well in both visible-infrared and visible-sketch modalities. Specifically, we propose the heterogeneous space shifting and common space shifting modules to augment specific and shared representations in heterogeneous space and common space, respectively, thereby regulating the model to learn the consistency between modalities. Further, a domain alignment loss is developed to alleviate the cross-modality discrepancies by aligning the patterns across modalities. In addition, a domain distillation loss is designed to distill identity-invariant knowledge by learning the distribution of different modalities. Extensive experiments on two cross-modality ReID tasks (i.e., visible-infrared ReID, visible-sketch ReID) demonstrate that the proposed method outperforms the state-of-the-art methods by a large margin.

Remote photoplethysmography (rPPG) is a non-contact method that employs facial videos for measuring physiological parameters. Existing rPPG methods have achieved remarkable performance. However, the success mainly profits from supervised learning over massive labeled data. On the other hand, existing unsupervised rPPG methods fail to fully utilize spatio-temporal features and encounter challenges in low-light or noise environments. To address these problems, we propose an unsupervised contrast learning approach, ST-Phys. We incorporate a low-light enhancement module, a temporal dilated module, and a spatial enhanced module to better deal with long-term dependencies under the random low-light conditions. In addition, we design a circular margin loss, wherein rPPG signals originating from identical videos are attracted, while those from distinct videos are repelled. Our method is assessed on six openly accessible datasets, including RGB and NIR videos. Extensive experiments reveal the superior performance of our proposed ST-Phys over state-of-the-art unsupervised rPPG methods. Moreover, it offers advantages in parameter reduction and noise robustness.

Micro action recognition is an important research area in human motion analysis, which can be applied to the fields of healthcare, motion analysis and human-computer interaction. In this paper, we propose a 3D convolutional neural network-based micro-gesture recognition network to improve the performance, which combines skeletal and semantic embedding losses to enhance network discrimination. Specifically, first, various data enhancement techniques, such as level flipping and random Gaussian noise, are utilized to improve the robustness and generalization of the model. Horizontal flipping aims to help the model better recognise mirrored and stacked features in images by flipping them on the symmetry axis. Meanwhile, Gaussian noise, also known as white noise, is a set of random values with a normal distribution designed to force the model to learn features that are robust to small variations in the input, which can represent smudges or subtle absences in the image. We have evaluated our methods on a micro-posture recognition benchmark dataset, and these methods improve on previous methods. The model was tested on the iMiGUE dataset and achieved a Top1% accuracy of 59.01%-a notable improvement over other models.

Visible-infrared person re-identification (VI Re-ID) is an essential and challenging task. Existing studies mainly focus on learning the unified modality-invariant representations directly from visible and infrared images. However, it is hard to obtain the identity-aware patterns due to the co-existence of inter- and intra-modality discrepancies. In this paper, we propose a novel attention-guided cross-modality correlation method (AGCC) to achieve the modality-invariant and identity-discriminative representations for visible-infrared person Re-ID. Specifically, we introduce a modality-aware attention (MAA) mechanism to model the inter- and intra-modality variations, which generates attention masks of two modalities for preserving the most significant region and obtaining the discriminative patterns in each identity. Further, we present an attention-guided channel and spatial correlation scheme (AGCSC) to establish the attention-guided cross-modality correlation, which can bridge the gap between inter- and intra-modalities. Moreover, a novel joint-modality learning head (JMLH) is developed to promote the metric and mutual learning from both feature distribution and classification logit levels. Extensive experiments on two public SYSU-MM01 and RegDB datasets demonstrate the remarkable superiority of our method over the state of the arts. The implementation codes will be made available soon.

Correlation-based detection techniques are widely used in the weak periodic signal detection field. Traditionally, they are based on extracting the correlation of a weak signal from noise. Considering the impact of a weak signal on the randomness of background noise, this article takes the opposite approach and proposes a weak signal detection technique based on the Durbin-Watson (DW) test and one-bit sampling, detecting the weak signal due to the extent to which the randomness of noise is affected. The randomness of noise is analyzed through the DW test, which is a method for detecting the randomness of data sequences through first-order autocorrelation. One-bit sampling is adopted to reduce the complexity of the sampling circuit and data processing algorithm. The effectiveness of the DW test in the situation of one-bit sampling is demonstrated through simulation and analysis. Simulation results show that the proposed technique is capable of detecting weak sinusoidal and square-wave signals with a signal-to-noise ratio (SNR) above -30 dB, and the frequency or SNR of a weak signal can be further estimated based on mutual constraints. The measured results confirm the capability. In addition, the factors of coherent sampling, noise bandwidth, and comparator threshold that influence the performance of the proposed technique are simulated and discussed in detail.

Sketch re-identification (Re-ID) seeks to match pedestrians' photos from surveillance videos with corresponding sketches. However, we observe that existing works still have two critical limitations: (i) cross- and intra-modality discrepancies hinder the extraction of modality-shared features, (ii) standard triplet loss fails to constrain latent feature distribution in each modality with inadequate samples. To overcome the above issues, we propose a differentiable auxiliary learning network (DALNet) to explore a robust auxiliary modality for Sketch Re-ID. Specifically, for (i) we construct an auxiliary modality by using a dynamic auxiliary generator (DAG) to bridge the gap between sketch and photo modalities. The auxiliary modality highlights the described person in photos to mitigate background clutter and learns sketch style through style refinement. Moreover, a modality interactive attention module (MIA) is presented to align the features and learn the invariant patterns of two modalities by auxiliary modality. To address (ii), we propose a multi-modality collaborative learning scheme (MMCL) to align the latent distribution of three modalities. An intra-modality circle loss in MMCL brings learned global and modality-shared features of the same identity closer in the case of insufficient samples within each modality. Extensive experiments verify the superior performance of our DALNet over the state-of-the-art methods for Sketch Re-ID, and the generalization in sketch-based image retrieval and sketch-photo face recognition tasks.