Baocai Yin

Fang Liu, Yuhao Liu, Yuqiu Kong et al.

Existing Referring Image Segmentation (RIS) methods typically require expensive pixel-level or box-level annotations for supervision. In this paper, we observe that the referring texts used in RIS already provide sufficient information to localize the target object. Hence, we propose a novel weakly-supervised RIS framework to formulate the target localization problem as a classification process to differentiate between positive and negative text expressions. While the referring text expressions for an image are used as positive expressions, the referring text expressions from other images can be used as negative expressions for this image. Our framework has three main novelties. First, we propose a bilateral prompt method to facilitate the classification process, by harmonizing the domain discrepancy between visual and linguistic features. Second, we propose a calibration method to reduce noisy background information and improve the correctness of the response maps for target object localization. Third, we propose a positive response map selection strategy to generate high-quality pseudo-labels from the enhanced response maps, for training a segmentation network for RIS inference. For evaluation, we propose a new metric to measure localization accuracy. Experiments on four benchmarks show that our framework achieves promising performances to existing fully-supervised RIS methods while outperforming state-of-the-art weakly-supervised methods adapted from related areas. Code is available at https://github.com/fawnliu/TRIS.

Xin Tian, Ke Xu, Xin Yang et al.

The saliency ranking task is recently proposed to study the visual behavior that humans would typically shift their attention over different objects of a scene based on their degrees of saliency. Existing approaches focus on learning either object-object or object-scene relations. Such a strategy follows the idea of object-based attention in Psychology, but it tends to favor those objects with strong semantics (e.g., humans), resulting in unrealistic saliency ranking. We observe that spatial attention works concurrently with object-based attention in the human visual recognition system. During the recognition process, the human spatial attention mechanism would move, engage, and disengage from region to region (i.e., context to context). This inspires us to model the region-level interactions, in addition to the object-level reasoning, for saliency ranking. To this end, we propose a novel bi-directional method to unify spatial attention and object-based attention for saliency ranking. Our model includes two novel modules: (1) a selective object saliency (SOS) module that models objectbased attention via inferring the semantic representation of the salient object, and (2) an object-context-object relation (OCOR) module that allocates saliency ranks to objects by jointly modeling the object-context and context-object interactions of the salient objects. Extensive experiments show that our approach outperforms existing state-of-theart methods. Our code and pretrained model are available at https://github.com/GrassBro/OCOR.

Mengnan Zhao, Lihe Zhang, Yuqiu Kong et al.

Fast adversarial training (FAT) is beneficial for improving the adversarial robustness of neural networks. However, previous FAT work has encountered a significant issue known as catastrophic overfitting when dealing with large perturbation budgets, \ie the adversarial robustness of models declines to near zero during training. To address this, we analyze the training process of prior FAT work and observe that catastrophic overfitting is accompanied by the appearance of loss convergence outliers. Therefore, we argue a moderately smooth loss convergence process will be a stable FAT process that solves catastrophic overfitting. To obtain a smooth loss convergence process, we propose a novel oscillatory constraint (dubbed ConvergeSmooth) to limit the loss difference between adjacent epochs. The convergence stride of ConvergeSmooth is introduced to balance convergence and smoothing. Likewise, we design weight centralization without introducing additional hyperparameters other than the loss balance coefficient. Our proposed methods are attack-agnostic and thus can improve the training stability of various FAT techniques. Extensive experiments on popular datasets show that the proposed methods efficiently avoid catastrophic overfitting and outperform all previous FAT methods. Code is available at \url{https://github.com/FAT-CS/ConvergeSmooth}.

Xiaoyan Li, Gang Zhang, Boyue Wang et al.

LiDAR panoptic segmentation facilitates an autonomous vehicle to comprehensively understand the surrounding objects and scenes and is required to run in real time. The recent proposal-free methods accelerate the algorithm, but their effectiveness and efficiency are still limited owing to the difficulty of modeling non-existent instance centers and the costly center-based clustering modules. To achieve accurate and real-time LiDAR panoptic segmentation, a novel center focusing network (CFNet) is introduced. Specifically, the center focusing feature encoding (CFFE) is proposed to explicitly understand the relationships between the original LiDAR points and virtual instance centers by shifting the LiDAR points and filling in the center points. Moreover, to leverage the redundantly detected centers, a fast center deduplication module (CDM) is proposed to select only one center for each instance. Experiments on the SemanticKITTI and nuScenes panoptic segmentation benchmarks demonstrate that our CFNet outperforms all existing methods by a large margin and is 1.6 times faster than the most efficient method. The code is available at https://github.com/GangZhang842/CFNet.

Zhenrong Zhang, Pengfei Hu, Jiefeng Ma et al.

Table structure recognition is an indispensable element for enabling machines to comprehend tables. Its primary purpose is to identify the internal structure of a table. Nevertheless, due to the complexity and diversity of their structure and style, it is highly challenging to parse the tabular data into a structured format that machines can comprehend. In this work, we adhere to the principle of the split-and-merge based methods and propose an accurate table structure recognizer, termed SEMv2 (SEM: Split, Embed and Merge). Unlike the previous works in the ``split'' stage, we aim to address the table separation line instance-level discrimination problem and introduce a table separation line detection strategy based on conditional convolution. Specifically, we design the ``split'' in a top-down manner that detects the table separation line instance first and then dynamically predicts the table separation line mask for each instance. The final table separation line shape can be accurately obtained by processing the table separation line mask in a row-wise/column-wise manner. To comprehensively evaluate the SEMv2, we also present a more challenging dataset for table structure recognition, dubbed iFLYTAB, which encompasses multiple style tables in various scenarios such as photos, scanned documents, etc. Extensive experiments on publicly available datasets (e.g. SciTSR, PubTabNet and iFLYTAB) demonstrate the efficacy of our proposed approach. The code and iFLYTAB dataset are available at https://github.com/ZZR8066/SEMv2.

Chengyang Zhang, Yong Zhang, Qitan Shao et al.

Traffic prediction is one of the most significant foundations in Intelligent Transportation Systems (ITS). Traditional traffic prediction methods rely only on historical traffic data to predict traffic trends and face two main challenges. 1) insensitivity to unusual events. 2) limited performance in long-term prediction. In this work, we explore how generative models combined with text describing the traffic system can be applied for traffic generation, and name the task Text-to-Traffic Generation (TTG). The key challenge of the TTG task is how to associate text with the spatial structure of the road network and traffic data for generating traffic situations. To this end, we propose ChatTraffic, the first diffusion model for text-to-traffic generation. To guarantee the consistency between synthetic and real data, we augment a diffusion model with the Graph Convolutional Network (GCN) to extract spatial correlations of traffic data. In addition, we construct a large dataset containing text-traffic pairs for the TTG task. We benchmarked our model qualitatively and quantitatively on the released dataset. The experimental results indicate that ChatTraffic can generate realistic traffic situations from the text. Our code and dataset are available at https://github.com/ChyaZhang/ChatTraffic.

Xueyan Yin, Feifan Li, Yanming Shen et al.

Recently, deep learning methods have made great progress in traffic prediction, but their performance depends on a large amount of historical data. In reality, we may face the data scarcity issue. In this case, deep learning models fail to obtain satisfactory performance. Transfer learning is a promising approach to solve the data scarcity issue. However, existing transfer learning approaches in traffic prediction are mainly based on regular grid data, which is not suitable for the inherent graph data in the traffic network. Moreover, existing graph-based models can only capture shared traffic patterns in the road network, and how to learn node-specific patterns is also a challenge. In this paper, we propose a novel transfer learning approach to solve the traffic prediction with few data, which can transfer the knowledge learned from a data-rich source domain to a data-scarce target domain. First, a spatial-temporal graph neural network is proposed, which can capture the node-specific spatial-temporal traffic patterns of different road networks. Then, to improve the robustness of transfer, we design a pattern-based transfer strategy, where we leverage a clustering-based mechanism to distill common spatial-temporal patterns in the source domain, and use these knowledge to further improve the prediction performance of the target domain. Experiments on real-world datasets verify the effectiveness of our approach.

Hongchen Tan, Xiuping Liu, Baocai Yin et al.

This paper presents a new Text-to-Image generation model, named Distribution Regularization Generative Adversarial Network (DR-GAN), to generate images from text descriptions from improved distribution learning. In DR-GAN, we introduce two novel modules: a Semantic Disentangling Module (SDM) and a Distribution Normalization Module (DNM). SDM combines the spatial self-attention mechanism and a new Semantic Disentangling Loss (SDL) to help the generator distill key semantic information for the image generation. DNM uses a Variational Auto-Encoder (VAE) to normalize and denoise the image latent distribution, which can help the discriminator better distinguish synthesized images from real images. DNM also adopts a Distribution Adversarial Loss (DAL) to guide the generator to align with normalized real image distributions in the latent space. Extensive experiments on two public datasets demonstrated that our DR-GAN achieved a competitive performance in the Text-to-Image task.

Jiapu Wang, Boyue Wang, Meikang Qiu et al.

Temporal characteristics are prominently evident in a substantial volume of knowledge, which underscores the pivotal role of Temporal Knowledge Graphs (TKGs) in both academia and industry. However, TKGs often suffer from incompleteness for three main reasons: the continuous emergence of new knowledge, the weakness of the algorithm for extracting structured information from unstructured data, and the lack of information in the source dataset. Thus, the task of Temporal Knowledge Graph Completion (TKGC) has attracted increasing attention, aiming to predict missing items based on the available information. In this paper, we provide a comprehensive review of TKGC methods and their details. Specifically, this paper mainly consists of three components, namely, 1)Background, which covers the preliminaries of TKGC methods, loss functions required for training, as well as the dataset and evaluation protocol; 2)Interpolation, that estimates and predicts the missing elements or set of elements through the relevant available information. It further categorizes related TKGC methods based on how to process temporal information; 3)Extrapolation, which typically focuses on continuous TKGs and predicts future events, and then classifies all extrapolation methods based on the algorithms they utilize. We further pinpoint the challenges and discuss future research directions of TKGC.

Hongchen Tan, Baocai Yin, Kun Wei et al.

We propose a novel Text-to-Image Generation Network, Adaptive Layout Refinement Generative Adversarial Network (ALR-GAN), to adaptively refine the layout of synthesized images without any auxiliary information. The ALR-GAN includes an Adaptive Layout Refinement (ALR) module and a Layout Visual Refinement (LVR) loss. The ALR module aligns the layout structure (which refers to locations of objects and background) of a synthesized image with that of its corresponding real image. In ALR module, we proposed an Adaptive Layout Refinement (ALR) loss to balance the matching of hard and easy features, for more efficient layout structure matching. Based on the refined layout structure, the LVR loss further refines the visual representation within the layout area. Experimental results on two widely-used datasets show that ALR-GAN performs competitively at the Text-to-Image generation task.

Mingqi Yang, Yanming Shen, Heng Qi et al.

For learning graph representations, not all detailed structures within a graph are relevant to the given graph tasks. Task-relevant structures can be $localized$ or $sparse$ which are only involved in subgraphs or characterized by the interactions of subgraphs (a hierarchical perspective). A graph neural network should be able to efficiently extract task-relevant structures and be invariant to irrelevant parts, which is challenging for general message passing GNNs. In this work, we propose to learn graph representations from a sequence of subgraphs of the original graph to better capture task-relevant substructures or hierarchical structures and skip $noisy$ parts. To this end, we design soft-mask GNN layer to extract desired subgraphs through the mask mechanism. The soft-mask is defined in a continuous space to maintain the differentiability and characterize the weights of different parts. Compared with existing subgraph or hierarchical representation learning methods and graph pooling operations, the soft-mask GNN layer is not limited by the fixed sample or drop ratio, and therefore is more flexible to extract subgraphs with arbitrary sizes. Extensive experiments on public graph benchmarks show that soft-mask mechanism brings performance improvements. And it also provides interpretability where visualizing the values of masks in each layer allows us to have an insight into the structures learned by the model.

Yuanyuan Liu, Chengjiang Long, Zhaoxuan Zhang et al.

3D scene graph generation (SGG) has been of high interest in computer vision. Although the accuracy of 3D SGG on coarse classification and single relation label has been gradually improved, the performance of existing works is still far from being perfect for fine-grained and multi-label situations. In this paper, we propose a framework fully exploring contextual information for the 3D SGG task, which attempts to satisfy the requirements of fine-grained entity class, multiple relation labels, and high accuracy simultaneously. Our proposed approach is composed of a Graph Feature Extraction module and a Graph Contextual Reasoning module, achieving appropriate information-redundancy feature extraction, structured organization, and hierarchical inferring. Our approach achieves superior or competitive performance over previous methods on the 3DSSG dataset, especially on the relationship prediction sub-task.

Zhaoxuan Zhang, Xiaoguang Han, Bo Dong et al.

We present a deep reinforcement learning method of progressive view inpainting for colored semantic point cloud scene completion under volume guidance, achieving high-quality scene reconstruction from only a single RGB-D image with severe occlusion. Our approach is end-to-end, consisting of three modules: 3D scene volume reconstruction, 2D RGB-D and segmentation image inpainting, and multi-view selection for completion. Given a single RGB-D image, our method first predicts its semantic segmentation map and goes through the 3D volume branch to obtain a volumetric scene reconstruction as a guide to the next view inpainting step, which attempts to make up the missing information; the third step involves projecting the volume under the same view of the input, concatenating them to complete the current view RGB-D and segmentation map, and integrating all RGB-D and segmentation maps into the point cloud. Since the occluded areas are unavailable, we resort to a A3C network to glance around and pick the next best view for large hole completion progressively until a scene is adequately reconstructed while guaranteeing validity. All steps are learned jointly to achieve robust and consistent results. We perform qualitative and quantitative evaluations with extensive experiments on the 3D-FUTURE data, obtaining better results than state-of-the-arts.

Yang Wang, Bo Dong, Ke Xu et al.

Deep Neural Networks (DNNs) are widely used for computer vision tasks. However, it has been shown that deep models are vulnerable to adversarial attacks, i.e., their performances drop when imperceptible perturbations are made to the original inputs, which may further degrade the following visual tasks or introduce new problems such as data and privacy security. Hence, metrics for evaluating the robustness of deep models against adversarial attacks are desired. However, previous metrics are mainly proposed for evaluating the adversarial robustness of shallow networks on the small-scale datasets. Although the Cross Lipschitz Extreme Value for nEtwork Robustness (CLEVER) metric has been proposed for large-scale datasets (e.g., the ImageNet dataset), it is computationally expensive and its performance relies on a tractable number of samples. In this paper, we propose the Adversarial Converging Time Score (ACTS), an attack-dependent metric that quantifies the adversarial robustness of a DNN on a specific input. Our key observation is that local neighborhoods on a DNN's output surface would have different shapes given different inputs. Hence, given different inputs, it requires different time for converging to an adversarial sample. Based on this geometry meaning, ACTS measures the converging time as an adversarial robustness metric. We validate the effectiveness and generalization of the proposed ACTS metric against different adversarial attacks on the large-scale ImageNet dataset using state-of-the-art deep networks. Extensive experiments show that our ACTS metric is an efficient and effective adversarial metric over the previous CLEVER metric.

Tengfei Liu, Yongli Hu, Junbin Gao et al.

Long Document Classification (LDC) has gained significant attention recently. However, multi-modal data in long documents such as texts and images are not being effectively utilized. Prior studies in this area have attempted to integrate texts and images in document-related tasks, but they have only focused on short text sequences and images of pages. How to classify long documents with hierarchical structure texts and embedding images is a new problem and faces multi-modal representation difficulties. In this paper, we propose a novel approach called Hierarchical Multi-modal Transformer (HMT) for cross-modal long document classification. The HMT conducts multi-modal feature interaction and fusion between images and texts in a hierarchical manner. Our approach uses a multi-modal transformer and a dynamic multi-scale multi-modal transformer to model the complex relationships between image features, and the section and sentence features. Furthermore, we introduce a new interaction strategy called the dynamic mask transfer module to integrate these two transformers by propagating features between them. To validate our approach, we conduct cross-modal LDC experiments on two newly created and two publicly available multi-modal long document datasets, and the results show that the proposed HMT outperforms state-of-the-art single-modality and multi-modality methods.

Yin Lin, Yehansen Chen, Baocai Yin et al.

Recently, visual-language learning (VLL) has shown great potential in enhancing visual-based person re-identification (ReID). Existing VLL-based ReID methods typically focus on image-text feature alignment at the whole-body level, while neglecting supervision on fine-grained part features, thus lacking constraints for local feature semantic consistency. To this end, we propose Part-Informed Visual-language Learning ($π$-VL) to enhance fine-grained visual features with part-informed language supervisions for ReID tasks. Specifically, $π$-VL introduces a human parsing-guided prompt tuning strategy and a hierarchical visual-language alignment paradigm to ensure within-part feature semantic consistency. The former combines both identity labels and human parsing maps to constitute pixel-level text prompts, and the latter fuses multi-scale visual features with a light-weight auxiliary head to perform fine-grained image-text alignment. As a plug-and-play and inference-free solution, our $π$-VL achieves performance comparable to or better than state-of-the-art methods on four commonly used ReID benchmarks. Notably, it reports 91.0% Rank-1 and 76.9% mAP on the challenging MSMT17 database, without bells and whistles.

Jiasong Feng, Lichun Wang, Hongbo Xu et al.

Scene Graph Generation (SGG) aims to generate a comprehensive graphical representation that accurately captures the semantic information of a given scenario. However, the SGG model's performance in predicting more fine-grained predicates is hindered by a significant predicate bias. According to existing works, the long-tail distribution of predicates in training data results in the biased scene graph. However, the semantic overlap between predicate categories makes predicate prediction difficult, and there is a significant difference in the sample size of semantically similar predicates, making the predicate prediction more difficult. Therefore, higher requirements are placed on the discriminative ability of the model. In order to address this problem, this paper proposes Ensemble Predicate Decoding (EPD), which employs multiple decoders to attain unbiased scene graph generation. Two auxiliary decoders trained on lower-frequency predicates are used to improve the discriminative ability of the model. Extensive experiments are conducted on the VG, and the experiment results show that EPD enhances the model's representation capability for predicates. In addition, we find that our approach ensures a relatively superior predictive capability for more frequent predicates compared to previous unbiased SGG methods.

Chengyang Zhang, Yong Zhang, Qitan Shao et al.

Traffic prediction is one of the most significant foundations in Intelligent Transportation Systems (ITS). Traditional traffic prediction methods rely only on historical traffic data to predict traffic trends and face two main challenges. 1) insensitivity to unusual events. 2) limited performance in long-term prediction. In this work, we explore how generative models combined with text describing the traffic system can be applied for traffic generation, and name the task Text-to-Traffic Generation (TTG). The key challenge of the TTG task is how to associate text with the spatial structure of the road network and traffic data for generating traffic situations. To this end, we propose ChatTraffic, the first diffusion model for text-to-traffic generation. To guarantee the consistency between synthetic and real data, we augment a diffusion model with the Graph Convolutional Network (GCN) to extract spatial correlations of traffic data. In addition, we construct a large dataset containing text-traffic pairs for the TTG task. We benchmarked our model qualitatively and quantitatively on the released dataset. The experimental results indicate that ChatTraffic can generate realistic traffic situations from the text. Our code and dataset are available at https://github.com/ChyaZhang/ChatTraffic.

Shi Yin, Shijie Huan, Shangfei Wang et al.

Recently, heatmap regression methods based on 1D landmark representations have shown prominent performance on locating facial landmarks. However, previous methods ignored to make deep explorations on the good potentials of 1D landmark representations for sequential and structural modeling of multiple landmarks to track facial landmarks. To address this limitation, we propose a Transformer architecture, namely 1DFormer, which learns informative 1D landmark representations by capturing the dynamic and the geometric patterns of landmarks via token communications in both temporal and spatial dimensions for facial landmark tracking. For temporal modeling, we propose a recurrent token mixing mechanism, an axis-landmark-positional embedding mechanism, as well as a confidence-enhanced multi-head attention mechanism to adaptively and robustly embed long-term landmark dynamics into their 1D representations; for structure modeling, we design intra-group and inter-group structure modeling mechanisms to encode the component-level as well as global-level facial structure patterns as a refinement for the 1D representations of landmarks through token communications in the spatial dimension via 1D convolutional layers. Experimental results on the 300VW and the TF databases show that 1DFormer successfully models the long-range sequential patterns as well as the inherent facial structures to learn informative 1D representations of landmark sequences, and achieves state-of-the-art performance on facial landmark tracking.

Mingqi Yang, Yanming Shen, Rui Li et al.

Many improvements on GNNs can be deemed as operations on the spectrum of the underlying graph matrix, which motivates us to directly study the characteristics of the spectrum and their effects on GNN performance. By generalizing most existing GNN architectures, we show that the correlation issue caused by the $unsmooth$ spectrum becomes the obstacle to leveraging more powerful graph filters as well as developing deep architectures, which therefore restricts GNNs' performance. Inspired by this, we propose the correlation-free architecture which naturally removes the correlation issue among different channels, making it possible to utilize more sophisticated filters within each channel. The final correlation-free architecture with more powerful filters consistently boosts the performance of learning graph representations. Code is available at https://github.com/qslim/gnn-spectrum.

Jiqing Zhang, Chengjiang Long, Yuxin Wang et al.

Recently, deep convolutional neural networks (CNNs) have been widely explored in single image super-resolution (SISR) and contribute remarkable progress. However, most of the existing CNNs-based SISR methods do not adequately explore contextual information in the feature extraction stage and pay little attention to the final high-resolution (HR) image reconstruction step, hence hindering the desired SR performance. To address the above two issues, in this paper, we propose a two-stage attentive network (TSAN) for accurate SISR in a coarse-to-fine manner. Specifically, we design a novel multi-context attentive block (MCAB) to make the network focus on more informative contextual features. Moreover, we present an essential refined attention block (RAB) which could explore useful cues in HR space for reconstructing fine-detailed HR image. Extensive evaluations on four benchmark datasets demonstrate the efficacy of our proposed TSAN in terms of quantitative metrics and visual effects. Code is available at https://github.com/Jee-King/TSAN.

Jiapu Wang, Kai Sun, Linhao Luo et al.

Temporal Knowledge Graph Reasoning (TKGR) is the process of utilizing temporal information to capture complex relations within a Temporal Knowledge Graph (TKG) to infer new knowledge. Conventional methods in TKGR typically depend on deep learning algorithms or temporal logical rules. However, deep learning-based TKGRs often lack interpretability, whereas rule-based TKGRs struggle to effectively learn temporal rules that capture temporal patterns. Recently, Large Language Models (LLMs) have demonstrated extensive knowledge and remarkable proficiency in temporal reasoning. Consequently, the employment of LLMs for Temporal Knowledge Graph Reasoning (TKGR) has sparked increasing interest among researchers. Nonetheless, LLMs are known to function as black boxes, making it challenging to comprehend their reasoning process. Additionally, due to the resource-intensive nature of fine-tuning, promptly updating LLMs to integrate evolving knowledge within TKGs for reasoning is impractical. To address these challenges, in this paper, we propose a Large Language Models-guided Dynamic Adaptation (LLM-DA) method for reasoning on TKGs. Specifically, LLM-DA harnesses the capabilities of LLMs to analyze historical data and extract temporal logical rules. These rules unveil temporal patterns and facilitate interpretable reasoning. To account for the evolving nature of TKGs, a dynamic adaptation strategy is proposed to update the LLM-generated rules with the latest events. This ensures that the extracted rules always incorporate the most recent knowledge and better generalize to the predictions on future events. Experimental results show that without the need of fine-tuning, LLM-DA significantly improves the accuracy of reasoning over several common datasets, providing a robust framework for TKGR tasks.

Jiapu Wang, Zheng Cui, Boyue Wang et al.

Temporal Knowledge Graphs (TKGs) incorporate a temporal dimension, allowing for a precise capture of the evolution of knowledge and reflecting the dynamic nature of the real world. Typically, TKGs contain complex geometric structures, with various geometric structures interwoven. However, existing Temporal Knowledge Graph Completion (TKGC) methods either model TKGs in a single space or neglect the heterogeneity of different curvature spaces, thus constraining their capacity to capture these intricate geometric structures. In this paper, we propose a novel Integrating Multi-curvature shared and specific Embedding (IME) model for TKGC tasks. Concretely, IME models TKGs into multi-curvature spaces, including hyperspherical, hyperbolic, and Euclidean spaces. Subsequently, IME incorporates two key properties, namely space-shared property and space-specific property. The space-shared property facilitates the learning of commonalities across different curvature spaces and alleviates the spatial gap caused by the heterogeneous nature of multi-curvature spaces, while the space-specific property captures characteristic features. Meanwhile, IME proposes an Adjustable Multi-curvature Pooling (AMP) approach to effectively retain important information. Furthermore, IME innovatively designs similarity, difference, and structure loss functions to attain the stated objective. Experimental results clearly demonstrate the superior performance of IME over existing state-of-the-art TKGC models.

Jinlu Wang, Jipeng Guo, Yanfeng Sun et al.

Graph neural networks (GNNs) demonstrate a robust capability for representation learning on graphs with complex structures, showcasing superior performance in various applications. The majority of existing GNNs employ a graph convolution operation by using both attribute and structure information through coupled learning. In essence, GNNs, from an optimization perspective, seek to learn a consensus and compromise embedding representation that balances attribute and graph information, selectively exploring and retaining valid information. To obtain a more comprehensive embedding representation of nodes, a novel GNNs framework, dubbed Decoupled Graph Neural Networks (DGNN), is introduced. DGNN explores distinctive embedding representations from the attribute and graph spaces by decoupled terms. Considering that semantic graph, constructed from attribute feature space, consists of different node connection information and provides enhancement for the topological graph, both topological and semantic graphs are combined for the embedding representation learning. Further, structural consistency among attribute embedding and graph embeddings is promoted to effectively remove redundant information and establish soft connection. This involves promoting factor sharing for adjacency reconstruction matrices, facilitating the exploration of a consensus and high-level correlation. Finally, a more powerful and complete representation is achieved through the concatenation of these embeddings. Experimental results conducted on several graph benchmark datasets verify its superiority in node classification task.

Mengnan Zhao, Lihe Zhang, Jingwen Ye et al.

Adversarial training (AT) refers to integrating adversarial examples -- inputs altered with imperceptible perturbations that can significantly impact model predictions -- into the training process. Recent studies have demonstrated the effectiveness of AT in improving the robustness of deep neural networks against diverse adversarial attacks. However, a comprehensive overview of these developments is still missing. This survey addresses this gap by reviewing a broad range of recent and representative studies. Specifically, we first describe the implementation procedures and practical applications of AT, followed by a comprehensive review of AT techniques from three perspectives: data enhancement, network design, and training configurations. Lastly, we discuss common challenges in AT and propose several promising directions for future research.

Mengnan Zhao, Lihe Zhang, Yuqiu Kong et al.

Fast Adversarial Training (FAT) has gained increasing attention within the research community owing to its efficacy in improving adversarial robustness. Particularly noteworthy is the challenge posed by catastrophic overfitting (CO) in this field. Although existing FAT approaches have made strides in mitigating CO, the ascent of adversarial robustness occurs with a non-negligible decline in classification accuracy on clean samples. To tackle this issue, we initially employ the feature activation differences between clean and adversarial examples to analyze the underlying causes of CO. Intriguingly, our findings reveal that CO can be attributed to the feature coverage induced by a few specific pathways. By intentionally manipulating feature activation differences in these pathways with well-designed regularization terms, we can effectively mitigate and induce CO, providing further evidence for this observation. Notably, models trained stably with these terms exhibit superior performance compared to prior FAT work. On this basis, we harness CO to achieve `attack obfuscation', aiming to bolster model performance. Consequently, the models suffering from CO can attain optimal classification accuracy on both clean and adversarial data when adding random noise to inputs during evaluation. We also validate their robustness against transferred adversarial examples and the necessity of inducing CO to improve robustness. Hence, CO may not be a problem that has to be solved.

Hongchen Tan, Yi Zhang, Xiuping Liu et al.

As a cutting-edge biosensor, the event camera holds significant potential in the field of computer vision, particularly regarding privacy preservation. However, compared to traditional cameras, event streams often contain noise and possess extremely sparse semantics, posing a formidable challenge for event-based person re-identification (event Re-ID). To address this, we introduce a novel event person re-identification network: the Spectrum-guided Feature Enhancement Network (SFE-Net). This network consists of two innovative components: the Multi-grain Spectrum Attention Mechanism (MSAM) and the Consecutive Patch Dropout Module (CPDM). MSAM employs a fourier spectrum transform strategy to filter event noise, while also utilizing an event-guided multi-granularity attention strategy to enhance and capture discriminative person semantics. CPDM employs a consecutive patch dropout strategy to generate multiple incomplete feature maps, encouraging the deep Re-ID model to equally perceive each effective region of the person's body and capture robust person descriptors. Extensive experiments on Event Re-ID datasets demonstrate that our SFE-Net achieves the best performance in this task.

Mengnan Zhao, Lihe Zhang, Yuqiu Kong et al.

3D instance segmentation plays a crucial role in comprehending 3D scenes. Despite recent advancements in this field, existing approaches exhibit certain limitations. These methods often rely on fixed instance positions obtained from sampled representative points in vast 3D point clouds, using center prediction or farthest point sampling. However, these selected positions may deviate from actual instance centers, posing challenges in precisely grouping instances. Moreover, the common practice of grouping candidate instances from a single type of coordinates introduces difficulties in identifying neighboring instances or incorporating edge points. To tackle these issues, we present a novel Transformer-based architecture, EipFormer, which comprises progressive aggregation and dual position embedding. The progressive aggregation mechanism leverages instance positions to refine instance proposals. It enhances the initial instance positions through weighted farthest point sampling and further refines the instance positions and proposals using aggregation averaging and center matching. Additionally, dual position embedding superposes the original and centralized position embeddings, thereby enhancing the model performance in distinguishing adjacent instances. Extensive experiments on popular datasets demonstrate that EipFormer achieves superior or comparable performance compared to state-of-the-art approaches.

Huajie Jiang, Zhengxian Li, Xiaohan Yu et al.

Generalized zero-shot learning aims to recognize both seen and unseen classes with the help of semantic information that is shared among different classes. It inevitably requires consistent visual-semantic alignment. Existing approaches fine-tune the visual backbone by seen-class data to obtain semantic-related visual features, which may cause overfitting on seen classes with a limited number of training images. This paper proposes a novel visual and semantic prompt collaboration framework, which utilizes prompt tuning techniques for efficient feature adaptation. Specifically, we design a visual prompt to integrate the visual information for discriminative feature learning and a semantic prompt to integrate the semantic formation for visualsemantic alignment. To achieve effective prompt information integration, we further design a weak prompt fusion mechanism for the shallow layers and a strong prompt fusion mechanism for the deep layers in the network. Through the collaboration of visual and semantic prompts, we can obtain discriminative semantic-related features for generalized zero-shot image recognition. Extensive experiments demonstrate that our framework consistently achieves favorable performance in both conventional zero-shot learning and generalized zero-shot learning benchmarks compared to other state-of-the-art methods.

Kai Han, Jin Wang, Yunhui Shi et al.

Deep unfolding networks have gained increasing attention in the field of compressed sensing (CS) owing to their theoretical interpretability and superior reconstruction performance. However, most existing deep unfolding methods often face the following issues: 1) they learn directly from single-channel images, leading to a simple feature representation that does not fully capture complex features; and 2) they treat various image components uniformly, ignoring the characteristics of different components. To address these issues, we propose a novel wavelet-domain deep unfolding framework named WTDUN, which operates directly on the multi-scale wavelet subbands. Our method utilizes the intrinsic sparsity and multi-scale structure of wavelet coefficients to achieve a tree-structured sampling and reconstruction, effectively capturing and highlighting the most important features within images. Specifically, the design of tree-structured reconstruction aims to capture the inter-dependencies among the multi-scale subbands, enabling the identification of both fine and coarse features, which can lead to a marked improvement in reconstruction quality. Furthermore, a wavelet domain adaptive sampling method is proposed to greatly improve the sampling capability, which is realized by assigning measurements to each wavelet subband based on its importance. Unlike pure deep learning methods that treat all components uniformly, our method introduces a targeted focus on important subbands, considering their energy and sparsity. This targeted strategy lets us capture key information more efficiently while discarding less important information, resulting in a more effective and detailed reconstruction. Extensive experimental results on various datasets validate the superior performance of our proposed method.

Yachao Yang, Yanfeng Sun, Jipeng Guo et al.

Graph Neural Networks (GNNs) have excelled in handling graph-structured data, attracting significant research interest. However, two primary challenges have emerged: interference between topology and attributes distorting node representations, and the low-pass filtering nature of most GNNs leading to the oversight of valuable high-frequency information in graph signals. These issues are particularly pronounced in heterophilic graphs. To address these challenges, we propose Dual-Frequency Filtering Self-aware Graph Neural Networks (DFGNN). DFGNN integrates low-pass and high-pass filters to extract smooth and detailed topological features, using frequency-specific constraints to minimize noise and redundancy in the respective frequency bands. The model dynamically adjusts filtering ratios to accommodate both homophilic and heterophilic graphs. Furthermore, DFGNN mitigates interference by aligning topological and attribute representations through dynamic correspondences between their respective frequency bands, enhancing overall model performance and expressiveness. Extensive experiments conducted on benchmark datasets demonstrate that DFGNN outperforms state-of-the-art methods in classification performance, highlighting its effectiveness in handling both homophilic and heterophilic graphs.

Jiqing Zhang, Yuanchen Wang, Wenxi Liu et al.

Most existing RGB-based trackers target low frame rate benchmarks of around 30 frames per second. This setting restricts the tracker's functionality in the real world, especially for fast motion. Event-based cameras as bioinspired sensors provide considerable potential for high frame rate tracking due to their high temporal resolution. However, event-based cameras cannot offer fine-grained texture information like conventional cameras. This unique complementarity motivates us to combine conventional frames and events for high frame rate object tracking under various challenging conditions. Inthispaper, we propose an end-to-end network consisting of multi-modality alignment and fusion modules to effectively combine meaningful information from both modalities at different measurement rates. The alignment module is responsible for cross-style and cross-frame-rate alignment between frame and event modalities under the guidance of the moving cues furnished by events. While the fusion module is accountable for emphasizing valuable features and suppressing noise information by the mutual complement between the two modalities. Extensive experiments show that the proposed approach outperforms state-of-the-art trackers by a significant margin in high frame rate tracking. With the FE240hz dataset, our approach achieves high frame rate tracking up to 240Hz.

Xin Tian, Ke Xu, Xin Yang et al.

Existing salient instance detection (SID) methods typically learn from pixel-level annotated datasets. In this paper, we present the first weakly-supervised approach to the SID problem. Although weak supervision has been considered in general saliency detection, it is mainly based on using class labels for object localization. However, it is non-trivial to use only class labels to learn instance-aware saliency information, as salient instances with high semantic affinities may not be easily separated by the labels. As the subitizing information provides an instant judgement on the number of salient items, it is naturally related to detecting salient instances and may help separate instances of the same class while grouping different parts of the same instance. Inspired by this observation, we propose to use class and subitizing labels as weak supervision for the SID problem. We propose a novel weakly-supervised network with three branches: a Saliency Detection Branch leveraging class consistency information to locate candidate objects; a Boundary Detection Branch exploiting class discrepancy information to delineate object boundaries; and a Centroid Detection Branch using subitizing information to detect salient instance centroids. This complementary information is then fused to produce a salient instance map. To facilitate the learning process, we further propose a progressive training scheme to reduce label noise and the corresponding noise learned by the model, via reciprocating the model with progressive salient instance prediction and model refreshing. Our extensive evaluations show that the proposed method plays favorably against carefully designed baseline methods adapted from related tasks.

Mengnan Zhao, Lihe Zhang, Yuqiu Kong et al.

Inferring missing facts in temporal knowledge graphs is a critical task and has been widely explored. Extrapolation in temporal reasoning tasks is more challenging and gradually attracts the attention of researchers since no direct history facts for prediction. Previous works attempted to apply evolutionary representation learning to solve the extrapolation problem. However, these techniques do not explicitly leverage various time-aware attribute representations, i.e. the reasoning performance is significantly affected by the history length. To alleviate the time dependence when reasoning future missing facts, we propose a memory-triggered decision-making (MTDM) network, which incorporates transient memories, long-short-term memories, and deep memories. Specifically, the transient learning network considers transient memories as a static knowledge graph, and the time-aware recurrent evolution network learns representations through a sequence of recurrent evolution units from long-short-term memories. Each evolution unit consists of a structural encoder to aggregate edge information, a time encoder with a gating unit to update attribute representations of entities. MTDM utilizes the crafted residual multi-relational aggregator as the structural encoder to solve the multi-hop coverage problem. We also introduce the dissolution learning constraint for better understanding the event dissolution process. Extensive experiments demonstrate the MTDM alleviates the history dependence and achieves state-of-the-art prediction performance. Moreover, compared with the most advanced baseline, MTDM shows a faster convergence speed and training speed.

Jiqing Zhang, Xin Yang, Yingkai Fu et al.

Inspired by the complementarity between conventional frame-based and bio-inspired event-based cameras, we propose a multi-modal based approach to fuse visual cues from the frame- and event-domain to enhance the single object tracking performance, especially in degraded conditions (e.g., scenes with high dynamic range, low light, and fast-motion objects). The proposed approach can effectively and adaptively combine meaningful information from both domains. Our approach's effectiveness is enforced by a novel designed cross-domain attention schemes, which can effectively enhance features based on self- and cross-domain attention schemes; The adaptiveness is guarded by a specially designed weighting scheme, which can adaptively balance the contribution of the two domains. To exploit event-based visual cues in single-object tracking, we construct a large-scale frame-event-based dataset, which we subsequently employ to train a novel frame-event fusion based model. Extensive experiments show that the proposed approach outperforms state-of-the-art frame-based tracking methods by at least 10.4% and 11.9% in terms of representative success rate and precision rate, respectively. Besides, the effectiveness of each key component of our approach is evidenced by our thorough ablation study.

Bin Sun, Shaofan Wang, Dehui Kong et al.

Domain adaptation aims to leverage information from the source domain to improve the classification performance in the target domain. It mainly utilizes two schemes: sample reweighting and feature matching. While the first scheme allocates different weights to individual samples, the second scheme matches the feature of two domains using global structural statistics. The two schemes are complementary with each other, which are expected to jointly work for robust domain adaptation. Several methods combine the two schemes, but the underlying relationship of samples is insufficiently analyzed due to the neglect of the hierarchy of samples and the geometric properties between samples. To better combine the advantages of the two schemes, we propose a Grassmannian graph-attentional landmark selection (GGLS) framework for domain adaptation. GGLS presents a landmark selection scheme using attention-induced neighbors of the graphical structure of samples and performs distribution adaptation and knowledge adaptation over Grassmann manifold. the former treats the landmarks of each sample differently, and the latter avoids feature distortion and achieves better geometric properties. Experimental results on different real-world cross-domain visual recognition tasks demonstrate that GGLS provides better classification accuracies compared with state-of-the-art domain adaptation methods.

Jiqing Zhang, Kai Zhao, Bo Dong et al.

Jointly exploiting multiple different yet complementary domain information has been proven to be an effective way to perform robust object tracking. This paper focuses on effectively representing and utilizing complementary features from the frame domain and event domain for boosting object tracking performance in challenge scenarios. Specifically, we propose Common Features Extractor (CFE) to learn potential common representations from the RGB domain and event domain. For learning the unique features of the two domains, we utilize a Unique Extractor for Event (UEE) based on Spiking Neural Networks to extract edge cues in the event domain which may be missed in RGB in some challenging conditions, and a Unique Extractor for RGB (UER) based on Deep Convolutional Neural Networks to extract texture and semantic information in RGB domain. Extensive experiments on standard RGB benchmark and real event tracking dataset demonstrate the effectiveness of the proposed approach. We show our approach outperforms all compared state-of-the-art tracking algorithms and verify event-based data is a powerful cue for tracking in challenging scenes.

Bin Sun, Dehui Kong, Shaofan Wang et al.

Zero-shot action recognition can recognize samples of unseen classes that are unavailable in training by exploring common latent semantic representation in samples. However, most methods neglected the connotative relation and extensional relation between the action classes, which leads to the poor generalization ability of the zero-shot learning. Furthermore, the learned classifier incline to predict the samples of seen class, which leads to poor classification performance. To solve the above problems, we propose a two-stage deep neural network for zero-shot action recognition, which consists of a feature generation sub-network serving as the sampling stage and a graph attention sub-network serving as the classification stage. In the sampling stage, we utilize a generative adversarial networks (GAN) trained by action features and word vectors of seen classes to synthesize the action features of unseen classes, which can balance the training sample data of seen classes and unseen classes. In the classification stage, we construct a knowledge graph (KG) based on the relationship between word vectors of action classes and related objects, and propose a graph convolution network (GCN) based on attention mechanism, which dynamically updates the relationship between action classes and objects, and enhances the generalization ability of zero-shot learning. In both stages, we all use word vectors as bridges for feature generation and classifier generalization from seen classes to unseen classes. We compare our method with state-of-the-art methods on UCF101 and HMDB51 datasets. Experimental results show that our proposed method improves the classification performance of the trained classifier and achieves higher accuracy.

Bin Sun, Shaofan Wang, Dehui Kong et al.

3D action recognition is referred to as the classification of action sequences which consist of 3D skeleton joints. While many research work are devoted to 3D action recognition, it mainly suffers from three problems: highly complicated articulation, a great amount of noise, and a low implementation efficiency. To tackle all these problems, we propose a real-time 3D action recognition framework by integrating the locally aggregated kinematic-guided skeletonlet (LAKS) with a supervised hashing-by-analysis (SHA) model. We first define the skeletonlet as a few combinations of joint offsets grouped in terms of kinematic principle, and then represent an action sequence using LAKS, which consists of a denoising phase and a locally aggregating phase. The denoising phase detects the noisy action data and adjust it by replacing all the features within it with the features of the corresponding previous frame, while the locally aggregating phase sums the difference between an offset feature of the skeletonlet and its cluster center together over all the offset features of the sequence. Finally, the SHA model which combines sparse representation with a hashing model, aiming at promoting the recognition accuracy while maintaining a high efficiency. Experimental results on MSRAction3D, UTKinectAction3D and Florence3DAction datasets demonstrate that the proposed method outperforms state-of-the-art methods in both recognition accuracy and implementation efficiency.

Xin Yang, Yu Qiao, Shaozhe Chen et al.

Image matting is an ill-posed problem that usually requires additional user input, such as trimaps or scribbles. Drawing a fne trimap requires a large amount of user effort, while using scribbles can hardly obtain satisfactory alpha mattes for non-professional users. Some recent deep learning-based matting networks rely on large-scale composite datasets for training to improve performance, resulting in the occasional appearance of obvious artifacts when processing natural images. In this article, we explore the intrinsic relationship between user input and alpha mattes and strike a balance between user effort and the quality of alpha mattes. In particular, we propose an interactive framework, referred to as smart scribbles, to guide users to draw few scribbles on the input images to produce high-quality alpha mattes. It frst infers the most informative regions of an image for drawing scribbles to indicate different categories (foreground, background, or unknown) and then spreads these scribbles (i.e., the category labels) to the rest of the image via our well-designed two-phase propagation. Both neighboring low-level afnities and high-level semantic features are considered during the propagation process. Our method can be optimized without large-scale matting datasets and exhibits more universality in real situations. Extensive experiments demonstrate that smart scribbles can produce more accurate alpha mattes with reduced additional input, compared to the state-of-the-art matting methods.

Xin Yang, Zongliang Ma, Letian Yu et al.

In this paper, we propose a fully automatic system for generating comic books from videos without any human intervention. Given an input video along with its subtitles, our approach first extracts informative keyframes by analyzing the subtitles, and stylizes keyframes into comic-style images. Then, we propose a novel automatic multi-page layout framework, which can allocate the images across multiple pages and synthesize visually interesting layouts based on the rich semantics of the images (e.g., importance and inter-image relation). Finally, as opposed to using the same type of balloon as in previous works, we propose an emotion-aware balloon generation method to create different types of word balloons by analyzing the emotion of subtitles and audios. Our method is able to vary balloon shapes and word sizes in balloons in response to different emotions, leading to more enriched reading experience. Once the balloons are generated, they are placed adjacent to their corresponding speakers via speaker detection. Our results show that our method, without requiring any user inputs, can generate high-quality comic pages with visually rich layouts and balloons. Our user studies also demonstrate that users prefer our generated results over those by state-of-the-art comic generation systems.

Guangyu Huo, Yong Zhang, Junbin Gao et al.

With the powerful learning ability of deep convolutional networks, deep clustering methods can extract the most discriminative information from individual data and produce more satisfactory clustering results. However, existing deep clustering methods usually ignore the relationship between the data. Fortunately, the graph convolutional network can handle such relationship, opening up a new research direction for deep clustering. In this paper, we propose a cross-attention based deep clustering framework, named Cross-Attention Fusion based Enhanced Graph Convolutional Network (CaEGCN), which contains four main modules: the cross-attention fusion module which innovatively concatenates the Content Auto-encoder module (CAE) relating to the individual data and Graph Convolutional Auto-encoder module (GAE) relating to the relationship between the data in a layer-by-layer manner, and the self-supervised model that highlights the discriminative information for clustering tasks. While the cross-attention fusion module fuses two kinds of heterogeneous representation, the CAE module supplements the content information for the GAE module, which avoids the over-smoothing problem of GCN. In the GAE module, two novel loss functions are proposed that reconstruct the content and relationship between the data, respectively. Finally, the self-supervised module constrains the distributions of the middle layer representations of CAE and GAE to be consistent. Experimental results on different types of datasets prove the superiority and robustness of the proposed CaEGCN.

Mingqi Yang, Yanming Shen, Heng Qi et al.

Recently, the Weisfeiler-Lehman (WL) graph isomorphism test was used to measure the expressiveness of graph neural networks (GNNs), showing that the neighborhood aggregation GNNs were at most as powerful as 1-WL test in distinguishing graph structures. There were also improvements proposed in analogy to $k$-WL test ($k>1$). However, the aggregators in these GNNs are far from injective as required by the WL test, and suffer from weak distinguishing strength, making it become expressive bottlenecks. In this paper, we improve the expressiveness by exploring powerful aggregators. We reformulate aggregation with the corresponding aggregation coefficient matrix, and then systematically analyze the requirements of the aggregation coefficient matrix for building more powerful aggregators and even injective aggregators. It can also be viewed as the strategy for preserving the rank of hidden features, and implies that basic aggregators correspond to a special case of low-rank transformations. We also show the necessity of applying nonlinear units ahead of aggregation, which is different from most aggregation-based GNNs. Based on our theoretical analysis, we develop two GNN layers, ExpandingConv and CombConv. Experimental results show that our models significantly boost performance, especially for large and densely connected graphs.

Xin Tian, Ke Xu, Xin Yang et al.

Existing salient instance detection (SID) methods typically learn from pixel-level annotated datasets. In this paper, we present the first weakly-supervised approach to the SID problem. Although weak supervision has been considered in general saliency detection, it is mainly based on using class labels for object localization. However, it is non-trivial to use only class labels to learn instance-aware saliency information, as salient instances with high semantic affinities may not be easily separated by the labels. We note that subitizing information provides an instant judgement on the number of salient items, which naturally relates to detecting salient instances and may help separate instances of the same class while grouping different parts of the same instance. Inspired by this insight, we propose to use class and subitizing labels as weak supervision for the SID problem. We propose a novel weakly-supervised network with three branches: a Saliency Detection Branch leveraging class consistency information to locate candidate objects; a Boundary Detection Branch exploiting class discrepancy information to delineate object boundaries; and a Centroid Detection Branch using subitizing information to detect salient instance centroids. This complementary information is further fused to produce salient instance maps. We conduct extensive experiments to demonstrate that the proposed method plays favorably against carefully designed baseline methods adapted from related tasks.

Hongchen Tan, Xiuping Liu, Baocai Yin et al.

This paper presents a novel person re-identification model, named Multi-Head Self-Attention Network (MHSA-Net), to prune unimportant information and capture key local information from person images. MHSA-Net contains two main novel components: Multi-Head Self-Attention Branch (MHSAB) and Attention Competition Mechanism (ACM). The MHSAB adaptively captures key local person information, and then produces effective diversity embeddings of an image for the person matching. The ACM further helps filter out attention noise and non-key information. Through extensive ablation studies, we verified that the Multi-Head Self-Attention Branch (MHSAB) and Attention Competition Mechanism (ACM) both contribute to the performance improvement of the MHSA-Net. Our MHSA-Net achieves competitive performance in the standard and occluded person Re-ID tasks.

Hongchen Tan, Yuhao Bian, Huasheng Wang et al.

In this paper, we propose a novel person Re-ID model, Consecutive Batch DropBlock Network (CBDB-Net), to capture the attentive and robust person descriptor for the person Re-ID task. The CBDB-Net contains two novel designs: the Consecutive Batch DropBlock Module (CBDBM) and the Elastic Loss (EL). In the Consecutive Batch DropBlock Module (CBDBM), we firstly conduct uniform partition on the feature maps. And then, we independently and continuously drop each patch from top to bottom on the feature maps, which can output multiple incomplete feature maps. In the training stage, these multiple incomplete features can better encourage the Re-ID model to capture the robust person descriptor for the Re-ID task. In the Elastic Loss (EL), we design a novel weight control item to help the Re-ID model adaptively balance hard sample pairs and easy sample pairs in the whole training process. Through an extensive set of ablation studies, we verify that the Consecutive Batch DropBlock Module (CBDBM) and the Elastic Loss (EL) each contribute to the performance boosts of CBDB-Net. We demonstrate that our CBDB-Net can achieve the competitive performance on the three standard person Re-ID datasets (the Market-1501, the DukeMTMC-Re-ID, and the CUHK03 dataset), three occluded Person Re-ID datasets (the Occluded DukeMTMC, the Partial-REID, and the Partial iLIDS dataset), and a general image retrieval dataset (In-Shop Clothes Retrieval dataset).

Xueyan Yin, Genze Wu, Jinze Wei et al.

Traffic prediction plays an essential role in intelligent transportation system. Accurate traffic prediction can assist route planing, guide vehicle dispatching, and mitigate traffic congestion. This problem is challenging due to the complicated and dynamic spatio-temporal dependencies between different regions in the road network. Recently, a significant amount of research efforts have been devoted to this area, especially deep learning method, greatly advancing traffic prediction abilities. The purpose of this paper is to provide a comprehensive survey on deep learning-based approaches in traffic prediction from multiple perspectives. Specifically, we first summarize the existing traffic prediction methods, and give a taxonomy. Second, we list the state-of-the-art approaches in different traffic prediction applications. Third, we comprehensively collect and organize widely used public datasets in the existing literature to facilitate other researchers. Furthermore, we give an evaluation and analysis by conducting extensive experiments to compare the performance of different methods on a real-world public dataset. Finally, we discuss open challenges in this field.

Xin Yang, Haiyang Mei, Ke Xu et al.

Mirrors are everywhere in our daily lives. Existing computer vision systems do not consider mirrors, and hence may get confused by the reflected content inside a mirror, resulting in a severe performance degradation. However, separating the real content outside a mirror from the reflected content inside it is non-trivial. The key challenge is that mirrors typically reflect contents similar to their surroundings, making it very difficult to differentiate the two. In this paper, we present a novel method to segment mirrors from an input image. To the best of our knowledge, this is the first work to address the mirror segmentation problem with a computational approach. We make the following contributions. First, we construct a large-scale mirror dataset that contains mirror images with corresponding manually annotated masks. This dataset covers a variety of daily life scenes, and will be made publicly available for future research. Second, we propose a novel network, called MirrorNet, for mirror segmentation, by modeling both semantical and low-level color/texture discontinuities between the contents inside and outside of the mirrors. Third, we conduct extensive experiments to evaluate the proposed method, and show that it outperforms the carefully chosen baselines from the state-of-the-art detection and segmentation methods.

Xin Yang, Haiyang Mei, Jiqing Zhang et al.

Recently, single-image super-resolution has made great progress owing to the development of deep convolutional neural networks (CNNs). The vast majority of CNN-based models use a pre-defined upsampling operator, such as bicubic interpolation, to upscale input low-resolution images to the desired size and learn non-linear mapping between the interpolated image and ground truth high-resolution (HR) image. However, interpolation processing can lead to visual artifacts as details are over-smoothed, particularly when the super-resolution factor is high. In this paper, we propose a Deep Recurrent Fusion Network (DRFN), which utilizes transposed convolution instead of bicubic interpolation for upsampling and integrates different-level features extracted from recurrent residual blocks to reconstruct the final HR images. We adopt a deep recurrence learning strategy and thus have a larger receptive field, which is conducive to reconstructing an image more accurately. Furthermore, we show that the multi-level fusion structure is suitable for dealing with image super-resolution problems. Extensive benchmark evaluations demonstrate that the proposed DRFN performs better than most current deep learning methods in terms of accuracy and visual effects, especially for large-scale images, while using fewer parameters.

Xin Yang, Wenbo Hu, Dawei Wang et al.

In this paper, we present DEMC, a deep Dual-Encoder network to remove Monte Carlo noise efficiently while preserving details. Denoising Monte Carlo rendering is different from natural image denoising since inexpensive by-products (feature buffers) can be extracted in the rendering stage. Most of them are noise-free and can provide sufficient details for image reconstruction. However, these feature buffers also contain redundant information, which makes Monte Carlo denoising different from natural image denoising. Hence, the main challenge of this topic is how to extract useful information and reconstruct clean images. To address this problem, we propose a novel network structure, Dual-Encoder network with a feature fusion sub-network, to fuse feature buffers firstly, then encode the fused feature buffers and a noisy image simultaneously, and finally reconstruct a clean image by a decoder network. Compared with the state-of-the-art methods, our model is more robust on a wide range of scenes and is able to generate satisfactory results in a significantly faster way.