Search

Pan Gao,1,2 Xinyu Li,1,2 Ziqiu He,1,2 Hongbo Zhang,1,2 Zhi Zhang,1,2 Zonglai Liu1,2 1Department of Urology, Second People’s Hospital of Yichang, Yichang, Hubei Province, People’s Republic of China; 2Department of Urology, Second People’s Hospital of China Three Gorges University, Yichang, Hubei Province, People’s Republic of ChinaCorrespondence: Zonglai Liu, Department of Urology, Second People’s Hospital of Yichang, Second People’s Hospital of China Three Gorges University, 21 Xiling One Road, Yichang, 443000, Hubei Province, People’s Republic of China, Email 85538230@qq.comAbstract: Immune checkpoint inhibitors (ICI) have become a new hope for many patients with advanced cancer by blocking tumor immune escape. Bladder cancer is a common malignant tumor of the urinary tract epithelium that often relapses and metastasizes after surgery, chemotherapy, and radiotherapy. Immunotherapy has dramatically improved patient survival rates and clinical benefits as a new, potentially effective therapy. However, avoidance of various immune-related adverse events (irAEs) remains an implausible idea. ICI-induced myocarditis is different from viral myocarditis, and mortality is still high with the current treatment. We report the case of an 82-year-old female patient with ICI-induced fulminant myocarditis and myasthenia gravis. Although she actively accepted the current mainstream treatment for immune-related myocarditis and myasthenia, she died of heart and respiratory failure. Analyzing and reporting the patient’s disease development process and the changes in related indicators may help peers gain a deeper understanding of immune-related adverse events and reduce the mortality of immune-related myocarditis.Keywords: immune checkpoint inhibitors, immunotherapy, heart failure, multiple organs failure

Style transfer aims to render an image with the artistic features of a style image, while maintaining the original structure. Various methods have been put forward for this task, but some challenges still exist. For instance, it is difficult for CNN-based methods to handle global information and long-range dependencies between input images, for which transformer-based methods have been proposed. Although transformers can better model the relationship between content and style images, they require high-cost hardware and time-consuming inference. To address these issues, we design a novel transformer model that includes only the encoder, thus significantly reducing the computational cost. In addition, we also find that existing style transfer methods may lead to images under-stylied or missing content. In order to achieve better stylization, we design a content feature extractor and a style feature extractor, based on which pure content and style images can be fed to the transformer. Finally, we propose a novel network termed Puff-Net, i.e., pure content and style feature fusion network. Through qualitative and quantitative experiments, we demonstrate the advantages of our model compared to state-of-the-art ones in the literature., Comment: 11 pages, 11 figures, to be published in IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2024)

Existing Blind image Super-Resolution (BSR) methods focus on estimating either kernel or degradation information, but have long overlooked the essential content details. In this paper, we propose a novel BSR approach, Content-aware Degradation-driven Transformer (CDFormer), to capture both degradation and content representations. However, low-resolution images cannot provide enough content details, and thus we introduce a diffusion-based module $CDFormer_{diff}$ to first learn Content Degradation Prior (CDP) in both low- and high-resolution images, and then approximate the real distribution given only low-resolution information. Moreover, we apply an adaptive SR network $CDFormer_{SR}$ that effectively utilizes CDP to refine features. Compared to previous diffusion-based SR methods, we treat the diffusion model as an estimator that can overcome the limitations of expensive sampling time and excessive diversity. Experiments show that CDFormer can outperform existing methods, establishing a new state-of-the-art performance on various benchmarks under blind settings. Codes and models will be available at \href{https://github.com/I2-Multimedia-Lab/CDFormer}{https://github.com/I2-Multimedia-Lab/CDFormer}.

The past several years have witnessed the emergence of learned point cloud compression (PCC) techniques. However, current learning-based lossless point cloud attribute compression (PCAC) methods either suffer from high computational complexity or deteriorated compression performance. Moreover, the significant variations in point cloud scale and sparsity encountered in real-world applications make developing an all-in-one neural model a challenging task. In this paper, we propose PoLoPCAC, an efficient and generic lossless PCAC method that achieves high compression efficiency and strong generalizability simultaneously. We formulate lossless PCAC as the task of inferring explicit distributions of attributes from group-wise autoregressive priors. A progressive random grouping strategy is first devised to efficiently resolve the point cloud into groups, and then the attributes of each group are modeled sequentially from accumulated antecedents. A locality-aware attention mechanism is utilized to exploit prior knowledge from context windows in parallel. Since our method directly operates on points, it can naturally avoids distortion caused by voxelization, and can be executed on point clouds with arbitrary scale and density. Experiments show that our method can be instantly deployed once trained on a Synthetic 2k-ShapeNet dataset while enjoying continuous bit-rate reduction over the latest G-PCCv23 on various datasets (ShapeNet, ScanNet, MVUB, 8iVFB). Meanwhile, our method reports shorter coding time than G-PCCv23 on the majority of sequences with a lightweight model size (2.6MB), which is highly attractive for practical applications. Dataset, code and trained model are available at https://github.com/I2-Multimedia-Lab/PoLoPCAC.

In the field of transportation, it is of paramount importance to address and mitigate illegal actions committed by both motor and non-motor vehicles. Among those actions, wrong-way cycling (i.e., riding a bicycle or e-bike in the opposite direction of the designated traffic flow) poses significant risks to both cyclists and other road users. To this end, this paper formulates a problem of detecting wrong-way cycling ratios in CCTV videos. Specifically, we propose a sparse sampling method called WWC-Predictor to efficiently solve this problem, addressing the inefficiencies of direct tracking methods. Our approach leverages both detection-based information, which utilizes the information from bounding boxes, and orientation-based information, which provides insights into the image itself, to enhance instantaneous information capture capability. On our proposed benchmark dataset consisting of 35 minutes of video sequences and minute-level annotation, our method achieves an average error rate of a mere 1.475% while taking only 19.12% GPU time of straightforward tracking methods under the same detection model. This remarkable performance demonstrates the effectiveness of our approach in identifying and predicting instances of wrong-way cycling.

Recently, unsupervised salient object detection (USOD) has gained increasing attention due to its annotation-free nature. However, current methods mainly focus on specific tasks such as RGB and RGB-D, neglecting the potential for task migration. In this paper, we propose a unified USOD framework for generic USOD tasks. Firstly, we propose a Progressive Curriculum Learning-based Saliency Distilling (PCL-SD) mechanism to extract saliency cues from a pre-trained deep network. This mechanism starts with easy samples and progressively moves towards harder ones, to avoid initial interference caused by hard samples. Afterwards, the obtained saliency cues are utilized to train a saliency detector, and we employ a Self-rectify Pseudo-label Refinement (SPR) mechanism to improve the quality of pseudo-labels. Finally, an adapter-tuning method is devised to transfer the acquired saliency knowledge, leveraging shared knowledge to attain superior transferring performance on the target tasks. Extensive experiments on five representative SOD tasks confirm the effectiveness and feasibility of our proposed method. Code and supplement materials are available at https://github.com/I2-Multimedia-Lab/A2S-v3.

Despite considerable progress being achieved in point cloud geometry compression, there still remains a challenge in effectively compressing large-scale scenes with sparse surfaces. Another key challenge lies in reducing decoding latency, a crucial requirement in real-world application. In this paper, we propose Pointsoup, an efficient learning-based geometry codec that attains high-performance and extremely low-decoding-latency simultaneously. Inspired by conventional Trisoup codec, a point model-based strategy is devised to characterize local surfaces. Specifically, skin features are embedded from local windows via an attention-based encoder, and dilated windows are introduced as cross-scale priors to infer the distribution of quantized features in parallel. During decoding, features undergo fast refinement, followed by a folding-based point generator that reconstructs point coordinates with fairly fast speed. Experiments show that Pointsoup achieves state-of-the-art performance on multiple benchmarks with significantly lower decoding complexity, i.e., up to 90$\sim$160$\times$ faster than the G-PCCv23 Trisoup decoder on a comparatively low-end platform (e.g., one RTX 2080Ti). Furthermore, it offers variable-rate control with a single neural model (2.9MB), which is attractive for industrial practitioners.

The direct synthesis of organomanganese reagents from organic halides and manganese metal remains a challenge. Current solution-based approaches require the preparation of activated manganese (Rieke manganese) or the use of multiple metal additives to promote the insertion of manganese metal into a carbon-halogen bond. Here, we show that a mechanochemical ball-milling protocol facilitates the generation of various arylmanganese nucleophiles from aryl halides and commercially available, unactivated manganese metal without the need for complicated pre-activation processes and metal additives. These manganese-based carbon nucleophiles can be used directly for one-pot addition reactions with various electrophiles and palladium-catalyzed cross-coupling reactions under bulk-solvent-free mechanochemical conditions. Importantly, all experimental operations can be conducted under atmospheric conditions.

The direct synthesis of organomanganese reagents from organic halides and manganese metal remains a challenge. Current solution-based approaches require the preparation of activated manganese (Rieke manganese) or the use of multiple metal additives to promote the insertion of manganese metal into a carbon-halogen bond. Here, we show that a mechanochemical ball-milling protocol facilitates the generation of various arylmanganese nucleophiles from aryl halides and commercially available, unactivated manganese metal without the need for complicated pre-activation processes and metal additives. These manganese-based carbon nucleophiles can be used directly for one-pot addition reactions with various electrophiles and palladium-catalyzed cross-coupling reactions under bulk-solvent-free mechanochemical conditions. Importantly, all experimental operations can be conducted under atmospheric conditions.

The direct synthesis of organomanganese reagents from organic halides and manganese metal remains a challenge. Current solution-based approaches require the preparation of activated manganese (Rieke manganese) or the use of multiple metal additives to promote the insertion of manganese metal into a carbon-halogen bond. Here, we show that a mechanochemical ball-milling protocol facilitates the generation of various arylmanganese nucleophiles from aryl halides and commercially available, unactivated manganese metal without the need for complicated pre-activation processes and metal additives. These manganese-based carbon nucleophiles can be used directly for one-pot addition reactions with various electrophiles and palladium-catalyzed cross-coupling reactions under bulk-solvent-free mechanochemical conditions. Importantly, all experimental operations can be conducted under atmospheric conditions.

Thanks to the ability of providing an immersive and interactive experience, the uptake of 360 degree image content has been rapidly growing in consumer and industrial applications. Compared to planar 2D images, saliency prediction for 360 degree images is more challenging due to their high resolutions and spherical viewing ranges. Currently, most high-performance saliency prediction models for omnidirectional images (ODIs) rely on deeper or broader convolutional neural networks (CNNs), which benefit from CNNs' superior feature representation capabilities while suffering from their high computational costs. In this paper, inspired by the human visual cognitive process, i.e., human being's perception of a visual scene is always accomplished by multiple stages of analysis, we propose a novel multi-stage recurrent generative adversarial networks for ODIs dubbed MRGAN360, to predict the saliency maps stage by stage. At each stage, the prediction model takes as input the original image and the output of the previous stage and outputs a more accurate saliency map. We employ a recurrent neural network among adjacent prediction stages to model their correlations, and exploit a discriminator at the end of each stage to supervise the output saliency map. In addition, we share the weights among all the stages to obtain a lightweight architecture that is computationally cheap. Extensive experiments are conducted to demonstrate that our proposed model outperforms the state-of-the-art model in terms of both prediction accuracy and model size.

Problems such as equipment defects or limited viewpoints will lead the captured point clouds to be incomplete. Therefore, recovering the complete point clouds from the partial ones plays an vital role in many practical tasks, and one of the keys lies in the prediction of the missing part. In this paper, we propose a novel point cloud completion approach namely ProxyFormer that divides point clouds into existing (input) and missing (to be predicted) parts and each part communicates information through its proxies. Specifically, we fuse information into point proxy via feature and position extractor, and generate features for missing point proxies from the features of existing point proxies. Then, in order to better perceive the position of missing points, we design a missing part sensitive transformer, which converts random normal distribution into reasonable position information, and uses proxy alignment to refine the missing proxies. It makes the predicted point proxies more sensitive to the features and positions of the missing part, and thus make these proxies more suitable for subsequent coarse-to-fine processes. Experimental results show that our method outperforms state-of-the-art completion networks on several benchmark datasets and has the fastest inference speed. Code is available at https://github.com/I2-Multimedia-Lab/ProxyFormer., Comment: Accepted by CVPR2023

Empathy is an important characteristic to be considered when building a more intelligent and humanized dialogue agent. However, existing methods did not fully comprehend empathy as a complex process involving three aspects: cognition, affection and behavior. In this paper, we propose CAB, a novel framework that takes a comprehensive perspective of cognition, affection and behavior to generate empathetic responses. For cognition, we build paths between critical keywords in the dialogue by leveraging external knowledge. This is because keywords in a dialogue are the core of sentences. Building the logic relationship between keywords, which is overlooked by the majority of existing works, can improve the understanding of keywords and contextual logic, thus enhance the cognitive ability. For affection, we capture the emotional dependencies with dual latent variables that contain both interlocutors' emotions. The reason is that considering both interlocutors' emotions simultaneously helps to learn the emotional dependencies. For behavior, we use appropriate dialogue acts to guide the dialogue generation to enhance the empathy expression. Extensive experiments demonstrate that our multi-perspective model outperforms the state-of-the-art models in both automatic and manual evaluation.

Existing point cloud learning methods aggregate features from neighbouring points relying on constructing graph in the spatial domain, which results in feature update for each point based on spatially-fixed neighbours throughout layers. In this paper, we propose a dynamic feature aggregation (DFA) method that can transfer information by constructing local graphs in the feature domain without spatial constraints. By finding k-nearest neighbors in the feature domain, we perform relative position encoding and semantic feature encoding to explore latent position and feature similarity information, respectively, so that rich local features can be learned. At the same time, we also learn low-dimensional global features from the original point cloud for enhancing feature representation. Between DFA layers, we dynamically update the constructed local graph structure, so that we can learn richer information, which greatly improves adaptability and efficiency. We demonstrate the superiority of our method by conducting extensive experiments on point cloud classification and segmentation tasks. Implementation code is available: https://github.com/jiamang/DFA., Comment: 14 pages , 4 figures , submitted to Signal Processing:image communications

Image quality assessment is a fundamental problem in the field of image processing, and due to the lack of reference images in most practical scenarios, no-reference image quality assessment (NR-IQA), has gained increasing attention recently. With the development of deep learning technology, many deep neural network-based NR-IQA methods have been developed, which try to learn the image quality based on the understanding of database information. Currently, Transformer has achieved remarkable progress in various vision tasks. Since the characteristics of the attention mechanism in Transformer fit the global perceptual impact of artifacts perceived by a human, Transformer is thus well suited for image quality assessment tasks. In this paper, we propose a Transformer based NR-IQA model using a predicted objective error map and perceptual quality token. Specifically, we firstly generate the predicted error map by pre-training one model consisting of a Transformer encoder and decoder, in which the objective difference between the distorted and the reference images is used as supervision. Then, we freeze the parameters of the pre-trained model and design another branch using the vision Transformer to extract the perceptual quality token for feature fusion with the predicted error map. Finally, the fused features are regressed to the final image quality score. Extensive experiments have shown that our proposed method outperforms the current state-of-the-art in both authentic and synthetic image databases. Moreover, the attentional map extracted by the perceptual quality token also does conform to the characteristics of the human visual system., Comment: Submitted to TMM

Discovering inter-point connection for efficient high-dimensional feature extraction from point coordinate is a key challenge in processing point cloud. Most existing methods focus on designing efficient local feature extractors while ignoring global connection, or vice versa. In this paper, we design a new Inductive Bias-aided Transformer (IBT) method to learn 3D inter-point relations, which considers both local and global attentions. Specifically, considering local spatial coherence, local feature learning is performed through Relative Position Encoding and Attentive Feature Pooling. We incorporate the learned locality into the Transformer module. The local feature affects value component in Transformer to modulate the relationship between channels of each point, which can enhance self-attention mechanism with locality based channel interaction. We demonstrate its superiority experimentally on classification and segmentation tasks. The code is available at: https://github.com/jiamang/IBT

Automated radiology report generation has the potential to improve radiology reporting and alleviate the workload of radiologists. However, the medical report generation task poses unique challenges due to the limited availability of medical data and the presence of data bias. To maximize the utility of available data and reduce data bias, we propose MSCL (Medical image Segmentation with Contrastive Learning), a framework that utilizes the Segment Anything Model (SAM) to segment organs, abnormalities, bones, etc., and can pay more attention to the meaningful ROIs in the image to get better visual representations. Then we introduce a supervised contrastive loss that assigns more weight to reports that are semantically similar to the target while training. The design of this loss function aims to mitigate the impact of data bias and encourage the model to capture the essential features of a medical image and generate high-quality reports. Experimental results demonstrate the effectiveness of our proposed model, where we achieve state-of-the-art performance on the IU X-Ray public dataset., Comment: NLPCC 2023

Image Quality Assessment (IQA) has long been a research hotspot in the field of image processing, especially No-Reference Image Quality Assessment (NR-IQA). Due to the powerful feature extraction ability, existing Convolution Neural Network (CNN) and Transformers based NR-IQA methods have achieved considerable progress. However, they still exhibit limited capability when facing unknown authentic distortion datasets. To further improve NR-IQA performance, in this paper, a novel supervised contrastive learning (SCL) and Transformer-based NR-IQA model SaTQA is proposed. We first train a model on a large-scale synthetic dataset by SCL (no image subjective score is required) to extract degradation features of images with various distortion types and levels. To further extract distortion information from images, we propose a backbone network incorporating the Multi-Stream Block (MSB) by combining the CNN inductive bias and Transformer long-term dependence modeling capability. Finally, we propose the Patch Attention Block (PAB) to obtain the final distorted image quality score by fusing the degradation features learned from contrastive learning with the perceptual distortion information extracted by the backbone network. Experimental results on seven standard IQA datasets show that SaTQA outperforms the state-of-the-art methods for both synthetic and authentic datasets. Code is available at https://github.com/I2-Multimedia-Lab/SaTQA, Comment: Accepted by AAAI24

Compared to CNN-based methods, Transformer-based methods achieve impressive image restoration outcomes due to their abilities to model remote dependencies. However, how to apply Transformer-based methods to the field of blind super-resolution (SR) and further make an SR network adaptive to degradation information is still an open problem. In this paper, we propose a new degradation-aware self-attention-based Transformer model, where we incorporate contrastive learning into the Transformer network for learning the degradation representations of input images with unknown noise. In particular, we integrate both CNN and Transformer components into the SR network, where we first use the CNN modulated by the degradation information to extract local features, and then employ the degradation-aware Transformer to extract global semantic features. We apply our proposed model to several popular large-scale benchmark datasets for testing, and achieve the state-of-the-art performance compared to existing methods. In particular, our method yields a PSNR of 32.43 dB on the Urban100 dataset at $\times$2 scale, 0.94 dB higher than DASR, and 26.62 dB on the Urban100 dataset at $\times$4 scale, 0.26 dB improvement over KDSR, setting a new benchmark in this area. Source code is available at: https://github.com/I2-Multimedia-Lab/DSAT/tree/main., Comment: 12 pages

Most existing salient object detection methods mostly use U-Net or feature pyramid structure, which simply aggregates feature maps of different scales, ignoring the uniqueness and interdependence of them and their respective contributions to the final prediction. To overcome these, we propose the M$^3$Net, i.e., the Multilevel, Mixed and Multistage attention network for Salient Object Detection (SOD). Firstly, we propose Multiscale Interaction Block which innovatively introduces the cross-attention approach to achieve the interaction between multilevel features, allowing high-level features to guide low-level feature learning and thus enhancing salient regions. Secondly, considering the fact that previous Transformer based SOD methods locate salient regions only using global self-attention while inevitably overlooking the details of complex objects, we propose the Mixed Attention Block. This block combines global self-attention and window self-attention, aiming at modeling context at both global and local levels to further improve the accuracy of the prediction map. Finally, we proposed a multilevel supervision strategy to optimize the aggregated feature stage-by-stage. Experiments on six challenging datasets demonstrate that the proposed M$^3$Net surpasses recent CNN and Transformer-based SOD arts in terms of four metrics. Codes are available at https://github.com/I2-Multimedia-Lab/M3Net.

Video frame interpolation has been actively studied with the development of convolutional neural networks. However, due to the intrinsic limitations of kernel weight sharing in convolution, the interpolated frame generated by it may lose details. In contrast, the attention mechanism in Transformer can better distinguish the contribution of each pixel, and it can also capture long-range pixel dependencies, which provides great potential for video interpolation. Nevertheless, the original Transformer is commonly used for 2D images; how to develop a Transformer-based framework with consideration of temporal self-attention for video frame interpolation remains an open issue. In this paper, we propose Video Frame Interpolation Flow Transformer to incorporate motion dynamics from optical flows into the self-attention mechanism. Specifically, we design a Flow Transformer Block that calculates the temporal self-attention in a matched local area with the guidance of flow, making our framework suitable for interpolating frames with large motion while maintaining reasonably low complexity. In addition, we construct a multi-scale architecture to account for multi-scale motion, further improving the overall performance. Extensive experiments on three benchmarks demonstrate that the proposed method can generate interpolated frames with better visual quality than state-of-the-art methods., Comment: Accepted to ACM MM23

GAN inversion aims at inverting given images into corresponding latent codes for Generative Adversarial Networks (GANs), especially StyleGAN where exists a disentangled latent space that allows attribute-based image manipulation at latent level. As most inversion methods build upon Convolutional Neural Networks (CNNs), we transfer a hierarchical vision Transformer backbone innovatively to predict $\mathcal{W^+}$ latent codes at token level. We further apply a Style-driven Multi-scale Adaptive Refinement Transformer (SMART) in $\mathcal{F}$ space to refine the intermediate style features of the generator. By treating style features as queries to retrieve lost identity information from the encoder's feature maps, SMART can not only produce high-quality inverted images but also surprisingly adapt to editing tasks. We then prove that StylePrompter lies in a more disentangled $\mathcal{W^+}$ and show the controllability of SMART. Finally, quantitative and qualitative experiments demonstrate that StylePrompter can achieve desirable performance in balancing reconstruction quality and editability, and is "smart" enough to fit into most edits, outperforming other $\mathcal{F}$-involved inversion methods., Comment: Some figures in the appendix are compressed for the reason of arXiv submission constrict

In sharp contrast to the use of conventional magnesium-based Grignard reagents (R-MgX), the application of calcium-based heavy Grignard reagents (R-CaX) in organic synthesis remains poorly explored. This is mainly due to the lack of experimentally simple ways to access such organocalcium nucleophiles from readily available starting materials under mild conditions. Here, we show that a mechanochemical technique using ball milling allows the generation of calcium-based heavy Grignard reagents from aryl halides and commercially available calcium metal without complicated pre-activation processes. Notably, all experimental operations can be carried out in air. Our operationally simple protocol enables the rapid development of novel cross-electrophile-coupling reactions mediated by arylcalcium nucleophiles, which are rather difficult using conventional Grignard reagents. This method will allow synthetic chemists to readily access the novel and unique reactivity of organocalcium nucleophiles.

In sharp contrast to the use of conventional magnesium-based Grignard reagents (R-MgX), the application of calcium-based heavy Grignard reagents (R-CaX) in organic synthesis remains poorly explored. This is mainly due to the lack of experimentally simple ways to access such organocalcium nucleophiles from readily available starting materials under mild conditions. Here, we show that a mechanochemical technique using ball milling allows the generation of calcium-based heavy Grignard reagents from aryl halides and commercially available calcium metal without complicated pre-activation processes. Notably, all experimental operations can be carried out in air. Our operationally simple protocol enables the rapid development of novel cross-electrophile-coupling reactions mediated by arylcalcium nucleophiles, which are rather difficult using conventional Grignard reagents. This method will allow synthetic chemists to readily access the novel and unique reactivity of organocalcium nucleophiles.

In sharp contrast to the use of conventional magnesium-based Grignard reagents (R-MgX), the application of calcium-based heavy Grignard reagents (R-CaX) in organic synthesis remains poorly explored. This is mainly due to the lack of experimentally simple ways to access such organocalcium nucleophiles from readily available starting materials under mild conditions. Here, we show that a mechanochemical technique using ball milling allows the generation of calcium-based heavy Grignard reagents from aryl halides and commercially available calcium metal without complicated pre-activation processes. Notably, all experimental operations can be carried out in air. Our operationally simple protocol enables the rapid development of novel cross-electrophile-coupling reactions mediated by arylcalcium nucleophiles, which are rather difficult using conventional Grignard reagents. This method will allow synthetic chemists to readily access the novel and unique reactivity of organocalcium nucleophiles.

Semantic segmentation usually benefits from global contexts, fine localisation information, multi-scale features, etc. To advance Transformer-based segmenters with these aspects, we present a simple yet powerful semantic segmentation architecture, termed as IncepFormer. IncepFormer has two critical contributions as following. First, it introduces a novel pyramid structured Transformer encoder which harvests global context and fine localisation features simultaneously. These features are concatenated and fed into a convolution layer for final per-pixel prediction. Second, IncepFormer integrates an Inception-like architecture with depth-wise convolutions, and a light-weight feed-forward module in each self-attention layer, efficiently obtaining rich local multi-scale object features. Extensive experiments on five benchmarks show that our IncepFormer is superior to state-of-the-art methods in both accuracy and speed, e.g., 1) our IncepFormer-S achieves 47.7% mIoU on ADE20K which outperforms the existing best method by 1% while only costs half parameters and fewer FLOPs. 2) Our IncepFormer-B finally achieves 82.0% mIoU on Cityscapes dataset with 39.6M parameters. Code is available:github.com/shendu0321/IncepFormer., Comment: Preprint with 8 pages of main body and 3 pages of supplementary material

While a large number of recent works on semantic segmentation focus on designing and incorporating a transformer-based encoder, much less attention and vigor have been devoted to transformer-based decoders. For such a task whose hallmark quest is pixel-accurate prediction, we argue that the decoder stage is just as crucial as that of the encoder in achieving superior segmentation performance, by disentangling and refining the high-level cues and working out object boundaries with pixel-level precision. In this paper, we propose a novel transformer-based decoder called UperFormer, which is plug-and-play for hierarchical encoders and attains high quality segmentation results regardless of encoder architecture. UperFormer is equipped with carefully designed multi-head skip attention units and novel upsampling operations. Multi-head skip attention is able to fuse multi-scale features from backbones with those in decoders. The upsampling operation, which incorporates feature from encoder, can be more friendly for object localization. It brings a 0.4% to 3.2% increase compared with traditional upsampling methods. By combining UperFormer with Swin Transformer (Swin-T), a fully transformer-based symmetric network is formed for semantic segmentation tasks. Extensive experiments show that our proposed approach is highly effective and computationally efficient. On Cityscapes dataset, we achieve state-of-the-art performance. On the more challenging ADE20K dataset, our best model yields a single-scale mIoU of 50.18, and a multi-scale mIoU of 51.8, which is on-par with the current state-of-art model, while we drastically cut the number of FLOPs by 53.5%. Our source code and models are publicly available at: https://github.com/shiwt03/UperFormer

As being one of the main representation formats of 3D real world and well-suited for virtual reality and augmented reality applications, point clouds have gained a lot of popularity. In order to reduce the huge amount of data, a considerable amount of research on point cloud compression has been done. However, given a target bit rate, how to properly choose the color and geometry quantization parameters for compressing point clouds is still an open issue. In this paper, we propose a rate-distortion model based quantization parameter selection scheme for bit rate constrained point cloud compression. Firstly, to overcome the measurement uncertainty in evaluating the distortion of the point clouds, we propose a unified model to combine the geometry distortion and color distortion. In this model, we take into account the correlation between geometry and color variables of point clouds and derive a dimensionless quantity to represent the overall quality degradation. Then, we derive the relationships of overall distortion and bit rate with the quantization parameters. Finally, we formulate the bit rate constrained point cloud compression as a constrained minimization problem using the derived polynomial models and deduce the solution via an iterative numerical method. Experimental results show that the proposed algorithm can achieve optimal decoded point cloud quality at various target bit rates, and substantially outperform the video-rate-distortion model based point cloud compression scheme., Comment: Accepted to IEEE Transactions on Circuits and Systems for Video Technology

Point cloud is a crucial representation of 3D contents, which has been widely used in many areas such as virtual reality, mixed reality, autonomous driving, etc. With the boost of the number of points in the data, how to efficiently compress point cloud becomes a challenging problem. In this paper, we propose a set of significant improvements to patch-based point cloud compression, i.e., a learnable context model for entropy coding, octree coding for sampling centroid points, and an integrated compression and training process. In addition, we propose an adversarial network to improve the uniformity of points during reconstruction. Our experiments show that the improved patch-based autoencoder outperforms the state-of-the-art in terms of rate-distortion performance, on both sparse and large-scale point clouds. More importantly, our method can maintain a short compression time while ensuring the reconstruction quality., Comment: 12 pages

It is well believed that Transformer performs better in semantic segmentation compared to convolutional neural networks. Nevertheless, the original Vision Transformer may lack of inductive biases of local neighborhoods and possess a high time complexity. Recently, Swin Transformer sets a new record in various vision tasks by using hierarchical architecture and shifted windows while being more efficient. However, as Swin Transformer is specifically designed for image classification, it may achieve suboptimal performance on dense prediction-based segmentation task. Further, simply combing Swin Transformer with existing methods would lead to the boost of model size and parameters for the final segmentation model. In this paper, we rethink the Swin Transformer for semantic segmentation, and design a lightweight yet effective transformer model, called SSformer. In this model, considering the inherent hierarchical design of Swin Transformer, we propose a decoder to aggregate information from different layers, thus obtaining both local and global attentions. Experimental results show the proposed SSformer yields comparable mIoU performance with state-of-the-art models, while maintaining a smaller model size and lower compute.

Automatic smoky vehicle detection in videos is a superior solution to the traditional expensive remote sensing one with ultraviolet-infrared light devices for environmental protection agencies. However, it is challenging to distinguish vehicle smoke from shadow and wet regions coming from rear vehicle or clutter roads, and could be worse due to limited annotated data. In this paper, we first introduce a real-world large-scale smoky vehicle dataset with 75,000 annotated smoky vehicle images, facilitating the effective training of advanced deep learning models. To enable fair algorithm comparison, we also build a smoky vehicle video dataset including 163 long videos with segment-level annotations. Moreover, we present a new Coarse-to-fine Deep Smoky vehicle detection (CoDeS) framework for efficient smoky vehicle detection. The CoDeS first leverages a light-weight YOLO detector for fast smoke detection with high recall rate, and then applies a smoke-vehicle matching strategy to eliminate non-vehicle smoke, and finally uses a elaborately-designed 3D model to further refine the results in spatial temporal space. Extensive experiments in four metrics demonstrate that our framework is significantly superior to those hand-crafted feature based methods and recent advanced methods. The code and dataset will be released at https://github.com/pengxj/smokyvehicle.

Video frame interpolation task has recently become more and more prevalent in the computer vision field. At present, a number of researches based on deep learning have achieved great success. Most of them are either based on optical flow information, or interpolation kernel, or a combination of these two methods. However, these methods have ignored that there are grid restrictions on the position of kernel region during synthesizing each target pixel. These limitations result in that they cannot well adapt to the irregularity of object shape and uncertainty of motion, which may lead to irrelevant reference pixels used for interpolation. In order to solve this problem, we revisit the deformable convolution for video interpolation, which can break the fixed grid restrictions on the kernel region, making the distribution of reference points more suitable for the shape of the object, and thus warp a more accurate interpolation frame. Experiments are conducted on four datasets to demonstrate the superior performance of the proposed model in comparison to the state-of-the-art alternatives., Comment: Accepted to the 31st International Joint Conference on Artificial Intelligence(IJCAI-ECAI 2022)

Motion estimation and motion compensation are indispensable parts of inter prediction in video coding. Since the motion vector of objects is mostly in fractional pixel units, original reference pictures may not accurately provide a suitable reference for motion compensation. In this paper, we propose a deep reference picture generator which can create a picture that is more relevant to the current encoding frame, thereby further reducing temporal redundancy and improving video compression efficiency. Inspired by the recent progress of Convolutional Neural Network(CNN), this paper proposes to use a dilated CNN to build the generator. Moreover, we insert the generated deep picture into Versatile Video Coding(VVC) as a reference picture and perform a comprehensive set of experiments to evaluate the effectiveness of our network on the latest VVC Test Model VTM. The experimental results demonstrate that our proposed method achieves on average 9.7% bit saving compared with VVC under low-delay P configuration.

To investigate dietary calcium requirement of bighead carp (Aristichthys nobilis), six purified diets were formulated to contain different concentrations of calcium (0.09% (control), 0.43%, 0.76%, 1.12%, 1.44%, and 1.79% of dry diets). Each diet was hand-fed to triplicate 30 fish with an average initial body weight (3.31 ± 0.09 g) for 60 days. The results showed that weight gain (WG) and specific growth rate (SGR) significantly increased when dietary calcium level was from 0.09% to 0.76% (P < 0.05). The phosphorus and calcium contents of whole fish body were highest in the 0.76% and 1.12% group, respectively (P < 0.05). The serum phosphorus content in the 1.79% group was significantly lower than those in other groups (P < 0.05). As dietary calcium content was from 0.09% to 0.76%, the activities of lipase and proteinase in the intestine had a significant increase (P < 0.05), while the glutamic oxaloacetic transaminase (GOT) and glutamic pyruvic transaminase (GPT) activities were significantly decreased (P < 0.05). Based on quadratic curve model analysis with WG and WGR as the appraising criteria, the appropriate dietary requirement of calcium for the bighead carp larvae (3.31 ± 0.09 g) was 1.01% - 1.02%.

Since the discovery of Grignard reagents in 1900, the nucleophilic addition of magnesium-based carbon nucleophiles to various electrophiles has become one of the most powerful, versatile, and well-established methods for the formation of carbon-carbon bonds in organic synthesis. Grignard reagents are typically prepared via reactions between organic halides and magnesium metal in a solvent. However, this method usually requires the use of dry organic solvents, long reaction times, strict control of the reaction temperature, and inert-gas-line techniques. Despite the utility of Grignard reagents, these requirements still represent major drawbacks from both an environmental and an economic perspective, and often cause reproducibility problems. Here, we report the general mechanochemical synthesis of magnesium-based carbon nucleophiles (Grignard reagents in paste form) in air using a ball milling technique. These nucleophiles can be used directly for one-pot nucleophilic addition reactions with various electrophiles and nickel-catalyzed cross-coupling reactions under solvent-free conditions. Grignard reagents have widespread utility in organic chemistry, but their preparation is limited by several drawbacks, such as the use of dry organic solvents and long reaction times. Here, the authors report a general mechanochemical synthesis of Grignard reagents in paste form in air, using a ball milling technique.

Since the discovery of Grignard reagents in 1900, the nucleophilic addition of magnesium-based carbon nucleophiles to various electrophiles has become one of the most powerful, versatile, and well-established methods for the formation of carbon-carbon bonds in organic synthesis. Grignard reagents are typically prepared via reactions between organic halides and magnesium metal in a solvent. However, this method usually requires the use of dry organic solvents, long reaction times, strict control of the reaction temperature, and inert-gas-line techniques. Despite the utility of Grignard reagents, these requirements still represent major drawbacks from both an environmental and an economic perspective, and often cause reproducibility problems. Here, we report the general mechanochemical synthesis of magnesium-based carbon nucleophiles (Grignard reagents in paste form) in air using a ball milling technique. These nucleophiles can be used directly for one-pot nucleophilic addition reactions with various electrophiles and nickel-catalyzed cross-coupling reactions under solvent-free conditions. Grignard reagents have widespread utility in organic chemistry, but their preparation is limited by several drawbacks, such as the use of dry organic solvents and long reaction times. Here, the authors report a general mechanochemical synthesis of Grignard reagents in paste form in air, using a ball milling technique.

Recently 3D point cloud learning has been a hot topic in computer vision and autonomous driving. Due to the fact that it is difficult to manually annotate a qualitative large-scale 3D point cloud dataset, unsupervised domain adaptation (UDA) is popular in 3D point cloud learning which aims to transfer the learned knowledge from the labeled source domain to the unlabeled target domain. However, the generalization and reconstruction errors caused by domain shift with simply-learned model are inevitable which substantially hinder the model's capability from learning good representations. To address these issues, we propose an end-to-end self-ensembling network (SEN) for 3D point cloud domain adaption tasks. Generally, our SEN resorts to the advantages of Mean Teacher and semi-supervised learning, and introduces a soft classification loss and a consistency loss, aiming to achieve consistent generalization and accurate reconstruction. In SEN, a student network is kept in a collaborative manner with supervised learning and self-supervised learning, and a teacher network conducts temporal consistency to learn useful representations and ensure the quality of point clouds reconstruction. Extensive experiments on several 3D point cloud UDA benchmarks show that our SEN outperforms the state-of-the-art methods on both classification and segmentation tasks. Moreover, further analysis demonstrates that our SEN also achieves better reconstruction results.

The ever-increasing 3D application makes the point cloud compression unprecedentedly important and needed. In this paper, we propose a patch-based compression process using deep learning, focusing on the lossy point cloud geometry compression. Unlike existing point cloud compression networks, which apply feature extraction and reconstruction on the entire point cloud, we divide the point cloud into patches and compress each patch independently. In the decoding process, we finally assemble the decompressed patches into a complete point cloud. In addition, we train our network by a patch-to-patch criterion, i.e., use the local reconstruction loss for optimization, to approximate the global reconstruction optimality. Our method outperforms the state-of-the-art in terms of rate-distortion performance, especially at low bitrates. Moreover, the compression process we proposed can guarantee to generate the same number of points as the input. The network model of this method can be easily applied to other point cloud reconstruction problems, such as upsampling., Comment: Accepted to ACM Multimedia Asia (MMAsia '21)

Recent studies have shown that neural network (NN) based image classifiers are highly vulnerable to adversarial examples, which poses a threat to security-sensitive image recognition task. Prior work has shown that JPEG compression can combat the drop in classification accuracy on adversarial examples to some extent. But, as the compression ratio increases, traditional JPEG compression is insufficient to defend those attacks but can cause an abrupt accuracy decline to the benign images. In this paper, with the aim of fully filtering the adversarial perturbations, we firstly make modifications to traditional JPEG compression algorithm which becomes more favorable for NN. Specifically, based on an analysis of the frequency coefficient, we design a NN-favored quantization table for compression. Considering compression as a data augmentation strategy, we then combine our model-agnostic preprocess with noisy training. We fine-tune the pre-trained model by training with images encoded at different compression levels, thus generating multiple classifiers. Finally, since lower (higher) compression ratio can remove both perturbations and original features slightly (aggressively), we use these trained multiple models for model ensemble. The majority vote of the ensemble of models is adopted as final predictions. Experiments results show our method can improve defense efficiency while maintaining original accuracy.

Pan Gao,1,2,* Hongtao Liu,3,* Zhenzhen Yang,1,2 Yiran Hui,2,4 Zhuangzhuang Shi,2 Zhen Yang,2 Min Song,2 Menghui Yao,2 Wenfei Fan,1 Jinhua Yang,1 Yibin Hao,1 Tianli Fan2 1People’s Hospital of Zhengzhou, Zhengzhou, Henan, 450001, People’s Republic of China; 2Department of Pharmacology, School of Basic Medicine, Zhengzhou University, Zhengzhou, Henan, 450001, People’s Republic of China; 3Laboratory for Cell Biology, College of Life Sciences of Zhengzhou University, Zhengzhou, Henan, 450001, People’s Republic of China; 4University of Chinese Academy of Sciences-Shenzhen Hospital, Shenzhen, Guangdong, 518106, People’s Republic of China*These authors contributed equally to this workCorrespondence: Tianli FanDepartment of Pharmacology, School of Basic Medicine, Zhengzhou University, Zhengzhou, Henan, 450001, People’s Republic of ChinaEmail fantianli@zzu.edu.cnPurpose: Increasing evidence has demonstrated that animal models are imperative to investigate the potential molecular mechanism of metastasis and discover anti-metastasis drugs; however, efficient animal models to unveil the underlying mechanisms of metastasis in esophageal squamous cell carcinoma (ESCC) are limited.Methods: ESCC cell EC9706 with high invasiveness was screened by repeated Transwell assays. Its biological characteristics were identified by flow cytometry as well as by the wound healing and CCK-8 assays. Besides, the levels of epithelial–mesenchymal transition-related markers were examined using Western blotting. Parental (EC9706-I0) and subpopulation (EC9706-I3) cells were employed to establish the renal capsule model. Next, the tumor growth was detected by a live animal imaging system, and hematoxylin and eosin staining was applied to evaluate the metastatic status in ESCC.Results: EC9706-I3 cells showed rapid proliferation ability, S phase abundance, and high invasive ability; obvious upregulation in N-cadherin, Snail, Vimentin, a

The optimization of occlusion-inducing depth pixels in depth map coding has received little attention in the literature, since their associated texture pixels are occluded in the synthesized view and their effect on the synthesized view is considered negligible. However, the occlusion-inducing depth pixels still need to consume the bits to be transmitted, and will induce geometry distortion that inherently exists in the synthesized view. In this paper, we propose an efficient depth map coding scheme specifically for the occlusion-inducing depth pixels by using allowable depth distortions. Firstly, we formulate a problem of minimizing the overall geometry distortion in the occlusion subject to the bit rate constraint, for which the depth distortion is properly adjusted within the set of allowable depth distortions that introduce the same disparity error as the initial depth distortion. Then, we propose a dynamic programming solution to find the optimal depth distortion vector for the occlusion. The proposed algorithm can improve the coding efficiency without alteration of the occlusion order. Simulation results confirm the performance improvement compared to other existing algorithms.

Three Dimensional (3-D) video, by definition, is a collection of signals that can provide depth perception of a 3-D scene. With the development of 3-D display technologies and interactive multimedia systems, 3-D video has attracted significant interest from both industries and academia with a variety of applications. In order to provide desired services in various 3-D video applications, the multiview video plus depth (MVD) representation, which can facilitate the generation of virtual views, has been determined to be the best format for 3-D video data. Similar to 2-D video, compressed 3-D video is highly sensitive to transmission errors due to errors propagated from the current frame to the future predicted frames. Moreover, since the virtual views required for auto-stereoscopic displays are rendered from the compressed texture videos and depth maps, transmission errors of the distorted texture videos and depth maps can be further propagated to the virtual views. Besides, the distortions in texture and depth show different effects on the rendering views. Therefore, compared to the reliability of the transmission of the 2-D video, error-resilient texture video and depth map coding are facing major new challenges. This research concentrates on improving the error resilience performance of MVD-based 3-D video in packet loss scenarios. Based on the analysis of the propagating behaviour of transmission errors, a Wyner-Ziv (WZ)-based error-resilient algorithm is first designed for coding of the multi-view video data or depth data. In this scheme, an auxiliary redundant stream encoded according to WZ principle is employed to protect a primary stream encoded with standard multi-view video coding codec. Then, considering the fact that different combinations of texture and depth coding mode will exhibit varying robustness to transmission errors, a rate-distortion optimized mode switching scheme is proposed to strike the optimal trade-off between robustness and compression ef