Search

Presents a correction to an article on nonlinear dynamic systems that was previously published in the August 2002 issue of the periodical "IEEE Transactions on Systems, Man and Cybernatics."

Face Anti-Spoofing (FAS) research is challenged by the cross-domain problem, where there is a domain gap between the training and testing data. While recent FAS works are mainly model-centric, focusing on developing domain generalization algorithms for improving cross-domain performance, data-centric research for face anti-spoofing, improving generalization from data quality and quantity, is largely ignored. Therefore, our work starts with data-centric FAS by conducting a comprehensive investigation from the data perspective for improving cross-domain generalization of FAS models. More specifically, at first, based on physical procedures of capturing and recapturing, we propose task-specific FAS data augmentation (FAS-Aug), which increases data diversity by synthesizing data of artifacts, such as printing noise, color distortion, moiré pattern, etc. Our experiments show that using our FAS augmentation can surpass traditional image augmentation in training FAS models to achieve better cross-domain performance. Nevertheless, we observe that models may rely on the augmented artifacts, which are not environment-invariant, and using FAS-Aug may have a negative effect. As such, we propose Spoofing Attack Risk Equalization (SARE) to prevent models from relying on certain types of artifacts and improve the generalization performance. Last but not least, our proposed FAS-Aug and SARE with recent Vision Transformer backbones can achieve state-of-the-art performance on the FAS cross-domain generalization protocols. The implementation is available at https://github.com/RizhaoCai/FAS-Aug. [ABSTRACT FROM AUTHOR]

Recent advancements in face forgery techniques have continuously evolved, leading to emergent security concerns in society. Existing detection methods have poor generalization ability due to the insufficient extraction of dynamic inconsistency cues on the one hand, and their inability to deal well with the gaps between forgery techniques on the other hand. To develop a new generalized framework that emphasizes extracting generalizable multi-timescale inconsistency cues. Firstly, we capture subtle dynamic inconsistency via magnifying the multipath dynamic inconsistency from the local-consecutive short-term temporal view. Secondly, the inter-group graph learning is conducted to establish the sufficient-interactive long-term temporal view for capturing dynamic inconsistency comprehensively. Finally, we design the domain alignment module to directly reduce the distribution gaps via simultaneously disarranging inter- and intra-domain feature distributions for obtaining a more generalized framework. Extensive experiments on six large-scale datasets and the designed generalization evaluation protocols show that our framework outperforms state-of-the-art deepfake video detection methods. [ABSTRACT FROM AUTHOR]

While raw images possess distinct advantages over sRGB images, e.g., linearity and fine-grained quantization levels, they are not widely adopted by general users due to their substantial storage requirements. Very recent studies propose to compress raw images by designing sampling masks within the pixel space of the raw image. However, these approaches often leave space for pursuing more effective image representations and compact metadata. In this work, we propose a novel framework that learns a compact representation in the latent space, serving as metadata, in an end-to-end manner. Compared with lossy image compression, we analyze the intrinsic difference of the raw image reconstruction task caused by rich information from the sRGB image. Based on the analysis, a novel design of the backbone with asymmetric and hybrid spatial feature resolutions is proposed, which significantly improves the rate-distortion performance. Besides, we propose a novel design of the sRGB-guided context model, which can better predict the order masks of encoding/decoding based on both the sRGB image and the the masks of already processed features. Benefited from the better modeling of the correlation between order masks, the already processed information can be better utilized. Moreover, a novel sRGB-guided adaptive quantization precision strategy, which dynamically assigns varying levels of quantization precision to different regions, further enhances the representation ability of the model. Finally, based on the iterative properties of the proposed context model, we propose a novel strategy to achieve variable bit rates using a single model. This strategy allows for the continuous convergence of a wide range of bit rates. We demonstrate how our raw image compression scheme effectively allocates more bits to image regions that hold greater global importance. Extensive experimental results validate the superior performance of the proposed method, achieving high-quality raw image reconstruction with a smaller metadata size, compared with existing SOTA methods. [ABSTRACT FROM AUTHOR]

• Group activity recognition using skeletons to reason about the actors interactions. • Novel method describes the interactions via learned relations between human joints. • Usage of previously unexplored interactions between humans and objects. • Leveraging of individual action information for higher quality feature learning. • Tailored attention mechanism over relations gives more importance to key individuals. Research on group activity recognition mostly leans on the standard two-stream approach (RGB and Optical Flow) as their input features. Few have explored explicit pose information, with none using it directly to reason about the persons interactions. In this paper, we leverage the skeleton information to learn the interactions between the individuals straight from it. With our proposed method GIRN, multiple relationship types are inferred from independent modules, that describe the relations between the body joints pair-by-pair. Additionally to the joints relations, we also experiment with the previously unexplored relationship between individuals and relevant objects (e.g. volleyball). The individuals distinct relations are then merged through an attention mechanism, that gives more importance to those individuals more relevant for distinguishing the group activity. We evaluate our method in the Volleyball dataset, obtaining competitive results to the state-of-the-art. Our experiments demonstrate the potential of skeleton-based approaches for modeling multi-person interactions. [ABSTRACT FROM AUTHOR]

Detection of double compression is of great significance to reveal video compression history. However, efficient detection algorithm for High Efficiency Video Coding (HEVC) double compression with non-aligned Group of Pictures (GOP) structures is rarely reported. To address this issue, a novel algorithm based on inter-frame quality degradation process analysis is proposed in this paper. Firstly, a brief introduction to HEVC standard and double compression with non-aligned GOP structures is provided. Next, theoretical analysis of inter-frame quality degradation process is given. Then, from the perspective of filtering decision, the inter-frame In-Loop Filtering Decision Mode (ILFDM) feature is adopted for double compression detection. Finally, the detection framework is given, which includes feature extraction, feature combination and periodic analysis. Experiments are conducted under different coding scenarios, by comparing with existing algorithms, results demonstrate that the proposed algorithm has better performance not only in terms of double compression detection, but also in original GOP size estimation. Furthermore, the proposed scheme is proved to be satisfactory in relocated I-frame detection. [ABSTRACT FROM AUTHOR]

Face images captured through glass are usually contaminated by reflections. The low-transmitted reflections make the reflection removal more challenging than for general scenes because important facial features would be completely occluded. In this paper, we propose and solve the face image reflection removal problem. We recover the important facial structures by incorporating inpainting ideas into a guided reflection removal framework, which takes two images as the input and considers various face-specific priors. We use a newly collected face reflection image dataset to train our model and compare with state-of-the-art methods. The proposed method shows advantages in estimating reflection-free face images for improving face recognition. [ABSTRACT FROM AUTHOR]

Most recently proposed unsupervised domain adaptation algorithms attempt to learn domain invariant features by confusing a domain classifier through adversarial training. In this paper, we argue that this may not be an optimal solution in the real-world setting (a.k.a. in the wild) as the difference in terms of label information between domains has been largely ignored. As labeled instances are not available in the target domain in unsupervised domain adaptation tasks, it is difficult to explicitly capture the label difference between domains. To address this issue, we propose to learn a disentangled latent representation based on implicit autoencoders. In particular, a latent representation is disentangled into a global code and a local code. The global code is capturing category information via an encoder with a prior, and the local code is transferable across domains, which captures the "style" related information via an implicit decoder. Experimental results on digit recognition, object recognition and semantic segmentation demonstrate the effectiveness of our proposed method. [ABSTRACT FROM AUTHOR]

Scale variations occur frequently and present a great challenge for crowd counting in practical applications. In this paper, we propose a scale adaptive network to address the scale variation problem for crowd counting. We design a scale expansion unit which uses normal and dilated convolution to expand the receptive field size range of its input and connect several such units densely to cover a large range of densely distributed receptive field sizes so as to fit objects of different sizes in images. To alleviate competition among different scales, especially the negative effect of inappropriate scales, we also design a residual channel-wise re-weighting unit which is inserted after each scale expansion unit to enhance informative feature channels. We evaluate the effectiveness of the proposed scale adaptive network on ShanghaiTech-B and WorldExpo'10 datasets. [ABSTRACT FROM AUTHOR]

With the increasing maturity of video editing technology, forgers are more inclined to transcode videos to High Efficiency Video Coding (HEVC) videos, as HEVC not only enables people to enjoy high-definition videos but also allows broadcasters to stream it more efficiently across networks. Therefore, to verify the originality and authenticity, it is of great significance to propose an algorithm for detecting transcoded HEVC videos. In this paper, a theoretical model of video transcoding is first constructed, and a novel transcoding detection algorithm based on In-loop Filtering and Prediction Units (PU) Partition (IFPP) is proposed. By analyzing the statistical characteristics of strong and normal filtering modes in deblocking filtering and calculating offset values in Sample Adaptive Offset (SAO) filtering, the transcoding traces in inter-coded frames can be captured. In addition, PU partition statistics are also extracted to make full use of traces in intra-coded frames. By fusing these subfeatures, the proposed IFPP feature with 17 dimensions can be obtained, which is further fed to the Support Vector Machine (SVM) classifier. Finally, experiments are conducted on datasets with various coding parameters. Results show that the proposed algorithm outperforms existing algorithms and has better robustness. • Transcoding a video would inevitably introduce additional errors. • The difference in filtering modes would affect the exposure of coding traces. • A novel algorithm is proposed to detect transcoded HEVC videos. [ABSTRACT FROM AUTHOR]

Learning the generalizable feature representation is critical to few-shot image classification. While recent works exploited task-specific feature embedding using meta-tasks for few-shot learning, they are limited in many challenging tasks as being distracted by the excursive features such as the background, domain, and style of the image samples. In this work, we propose a novel disentangled feature representation (DFR) framework, dubbed DFR, for few-shot learning applications. DFR can adaptively decouple the discriminative features that are modeled by the classification branch, from the class-irrelevant component of the variation branch. In general, most of the popular deep few-shot learning methods can be plugged in as the classification branch, thus DFR can boost their performance on various few-shot tasks. Furthermore, we propose a novel FS-DomainNet dataset based on DomainNet, for benchmarking the few-shot domain generalization (DG) tasks. We conducted extensive experiments to evaluate the proposed DFR on general, fine-grained, and cross-domain few-shot classification, as well as few-shot DG, using the corresponding four benchmarks, i.e., mini-ImageNet, tiered-ImageNet, Caltech-UCSD Birds 200-2011 (CUB), and the proposed FS-DomainNet. Thanks to the effective feature disentangling, the DFR-based few-shot classifiers achieved state-of-the-art results on all datasets.

One-shot skeleton action recognition, which aims to learn a skeleton action recognition model with a single training sample, has attracted increasing interest due to the challenge of collecting and annotating large-scale skeleton action data. However, most existing studies match skeleton sequences by comparing their feature vectors directly which neglects spatial structures and temporal orders of skeleton data. This paper presents a novel one-shot skeleton action recognition technique that handles skeleton action recognition via multi-scale spatial-temporal feature matching. We represent skeleton data at multiple spatial and temporal scales and achieve optimal feature matching from two perspectives. The first is multi-scale matching which captures the scale-wise semantic relevance of skeleton data at multiple spatial and temporal scales simultaneously. The second is cross-scale matching which handles different motion magnitudes and speeds by capturing sample-wise relevance across multiple scales. Extensive experiments over three large-scale datasets (NTU RGB+D, NTU RGB+D 120, and PKU-MMD) show that our method achieves superior one-shot skeleton action recognition, and outperforms SOTA consistently by large margins.

In heavy rain video, rain streak and rain accumulation are the most common causes of degradation. They occlude background information and can significantly impair the visibility. Most existing methods rely heavily on the synthetic training data, and thus raise the domain gap problem that prevents the trained models from performing adequately in real testing cases. Unlike these methods, we introduce a self-learning method to remove both rain streaks and rain accumulation without using any ground-truth clean images in training our model, which consequently can alleviate the domain gap issue. The main idea is based on the assumptions that (1) adjacent clean frames can be aligned or warped from one frame to another frame, (2) rain streaks are distributed randomly in the temporal domain, (3) the rain streak/accumulation related variables/priors can be inferred reliably from the information within the images/sequences. Based on these assumptions, we construct an augmented Self-Learned Deraining Network (SLDNet+) to remove both rain streaks and rain accumulation by utilizing temporal correlation, consistency, and rain-related priors. For the temporal correlation, our SLDNet+ takes rain degraded adjacent frames as its input, aligns them, and learns to predict the clean version of the current frame. For the temporal consistency, a new loss is designed to build a robust mapping between the predicted clean frame and non-rain regions from the adjacent rain frames. For the rain-streak-related prior, the rain streak removal network is optimized jointly with motion estimation and rain region detection; while for the rain-accumulation-related prior, a novel non-local video rain accumulation removal method is developed to estimate the accumulation-lines from the whole input video and to offer better color constancy and temporal smoothness. Extensive experiments show the effectiveness of our approach, which provides superior results compared with the existing state of the art methods both quantitatively and qualitatively. The source code will be made publicly available at: https://github.com/flyywh/CVPR-2020-Self-Rain-Removal-Journal.

3D Skeleton-based human action recognition has attracted increasing attention in recent years. Most of the existing work focuses on supervised learning which requires a large number of labeled action sequences that are often expensive and time-consuming to annotate. In this paper, we address self-supervised 3D action representation learning for skeleton-based action recognition. We investigate self-supervised representation learning and design a novel skeleton cloud colorization technique that is capable of learning spatial and temporal skeleton representations from unlabeled skeleton sequence data. We represent a skeleton action sequence as a 3D skeleton cloud and colorize each point in the cloud according to its temporal and spatial orders in the original (unannotated) skeleton sequence. Leveraging the colorized skeleton point cloud, we design an auto-encoder framework that can learn spatial-temporal features from the artificial color labels of skeleton joints effectively. Specifically, we design a two-steam pretraining network that leverages fine-grained and coarse-grained colorization to learn multi-scale spatial-temporal features. In addition, we design a Masked Skeleton Cloud Repainting task that can pretrain the designed auto-encoder framework to learn informative representations. We evaluate our skeleton cloud colorization approach with linear classifiers trained under different configurations, including unsupervised, semi-supervised, fully-supervised, and transfer learning settings. Extensive experiments on NTU RGB+D, NTU RGB+D 120, PKU-MMD, NW-UCLA, and UWA3D datasets show that the proposed method outperforms existing unsupervised and semi-supervised 3D action recognition methods by large margins and achieves competitive performance in supervised 3D action recognition as well.

In this article, we investigate the problem of panoramic image reflection removal to relieve the content ambiguity between the reflection layer and the transmission scene. Although a partial view of the reflection scene is attainable in the panoramic image and provides additional information for reflection removal, it is not trivial to directly apply this for getting rid of undesired reflections due to its misalignment with the reflection-contaminated image. We propose an end-to-end framework to tackle this problem. By resolving misalignment issues with adaptive modules, the high-fidelity recovery of reflection layer and transmission scenes is accomplished. We further propose a new data generation approach that considers the physics-based formation model of mixture images and the in-camera dynamic range clipping to diminish the domain gap between synthetic and real data. Experimental results demonstrate the effectiveness of the proposed method and its applicability for mobile devices and industrial applications.

Reflection removal has been discussed for more than decades. This paper aims to provide the analysis for different reflection properties and factors that influence image formation, an up-to-date taxonomy for existing methods, a benchmark dataset, and the unified benchmarking evaluations for state-of-the-art (especially learning-based) methods. Specifically, this paper presents a SIngle-image Reflection Removal Plus dataset "SIR 2+ " with the new consideration for in-the-wild scenarios and glass with diverse color and unplanar shapes. We further perform quantitative and visual quality comparisons for state-of-the-art single-image reflection removal algorithms. Open problems for improving reflection removal algorithms are discussed at the end. Our dataset and follow-up update can be found at https://reflectionremoval.github.io/sir2data/.

The recent advances of hardware technology have made the intelligent analysis equipped at the front-end with deep learning more prevailing and practical. To better enable the intelligent sensing at the front-end, instead of compressing and transmitting visual signals or the ultimately utilized top-layer deep learning features, we propose to compactly represent and convey the intermediate-layer deep learning features with high generalization capability, to facilitate the collaborating approach between front and cloud ends. This strategy enables a good balance among the computational load, transmission load and the generalization ability for cloud servers when deploying the deep neural networks for large scale cloud based visual analysis. Moreover, the presented strategy also makes the standardization of deep feature coding more feasible and promising, as a series of tasks can simultaneously benefit from the transmitted intermediate layer features. We also present the results for evaluations of both lossless and lossy deep feature compression, which provide meaningful investigations and baselines for future research and standardization activities.

Cross-domain shoe image retrieval is a challenging problem, because the query photo from the street domain (daily life scenario) and the reference photo in the online domain (online shop images) have significant visual differences due to the viewpoint and scale variation, self-occlusion, and cluttered background. This paper proposes the semantic hierarchy of attribute convolutional neural network (SHOE-CNN) with a three-level feature representation for discriminative shoe feature expression and efficient retrieval. The SHOE-CNN with its newly designed loss function systematically merges semantic attributes of closer visual appearances to prevent shoe images with the obvious visual differences being confused with each other; the features extracted from image, region, and part levels effectively match the shoe images across different domains. We collect a large-scale shoe data set composed of 14341 street domain and 12652 corresponding online domain images with fine-grained attributes to train our network and evaluate our system. The top-20 retrieval accuracy improves significantly over the solution with the pre-trained CNN features.

Distortions cause structural changes in digital images, leading to degraded visual quality. Dictionary-based sparse representation has been widely studied recently due to its ability to extract inherent image structures. Meantime, it can extract image features with slightly higher level semantics. Intuitively, sparse representation can be used for image quality assessment, because visible distortions can cause significant changes to the sparse features. In this paper, a new sparse representation-based image quality assessment model is proposed based on the construction of adaptive sub-dictionaries. An overcomplete dictionary trained from natural images is employed to capture the structure changes between the reference and distorted images by sparse feature extraction via adaptive sub-dictionary selection. Based on the observation that image sparse features are invariant to weak degradations and the perceived image quality is generally influenced by diverse issues, three auxiliary quality features are added, including gradient, color, and luminance information. The proposed method is not sensitive to training images, so a universal dictionary can be adopted for quality evaluation. Extensive experiments on five public image quality databases demonstrate that the proposed method produces the state-of-the-art results, and it delivers consistently well performances when tested in different image quality databases.