Search

Trajectory prediction is a pivotal component of autonomous driving systems, enabling the application of accumulated movement experience to current scenarios. Although most existing methods concentrate on learning continuous representations to gain valuable experience, they often suffer from computational inefficiencies and struggle with unfamiliar situations. To address this issue, we propose the Fragmented-Memory-based Trajectory Prediction (FMTP) model, inspired by the remarkable learning capabilities of humans, particularly their ability to leverage accumulated experience and recall relevant memories in unfamiliar situations. The FMTP model employs discrete representations to enhance computational efficiency by reducing information redundancy while maintaining the flexibility to utilize past experiences. Specifically, we design a learnable memory array by consolidating continuous trajectory representations from the training set using defined quantization operations during the training phase. This approach further eliminates redundant information while preserving essential features in discrete form. Additionally, we develop an advanced reasoning engine based on language models to deeply learn the associative rules among these discrete representations. Our method has been evaluated on various public datasets, including ETH-UCY, inD, SDD, nuScenes, Waymo, and VTL-TP. The extensive experimental results demonstrate that our approach achieves significant performance and extracts more valuable experience from past trajectories to inform the current state.

Few-shot detection is a major task in pattern recognition which seeks to localize objects using models trained with few labeled data. One of the mainstream few-shot methods is transfer learning which consists in pretraining a detection model in a source domain prior to its fine-tuning in a target domain. However, it is challenging for fine-tuned models to effectively identify new classes in the target domain, particularly when the underlying labeled training data are scarce. In this paper, we devise a novel sparse context transformer (SCT) that effectively leverages object knowledge in the source domain, and automatically learns a sparse context from only few training images in the target domain. As a result, it combines different relevant clues in order to enhance the discrimination power of the learned detectors and reduce class confusion. We evaluate the proposed method on two challenging few-shot object detection benchmarks, and empirical results show that the proposed method obtains competitive performance compared to the related state-of-the-art.

Surface defect inspection plays an important role in the process of industrial manufacture and production. Though Convolutional Neural Network (CNN) based defect inspection methods have made huge leaps, they still confront a lot of challenges such as defect scale variation, complex background, low contrast, and so on. To address these issues, we propose a joint attention-guided feature fusion network (JAFFNet) for saliency detection of surface defects based on the encoder-decoder network. JAFFNet mainly incorporates a joint attention-guided feature fusion (JAFF) module into decoding stages to adaptively fuse low-level and high-level features. The JAFF module learns to emphasize defect features and suppress background noise during feature fusion, which is beneficial for detecting low-contrast defects. In addition, JAFFNet introduces a dense receptive field (DRF) module following the encoder to capture features with rich context information, which helps detect defects of different scales. The JAFF module mainly utilizes a learned joint channel-spatial attention map provided by high-level semantic features to guide feature fusion. The attention map makes the model pay more attention to defect features. The DRF module utilizes a sequence of multi-receptive-field (MRF) units with each taking as inputs all the preceding MRF feature maps and the original input. The obtained DRF features capture rich context information with a large range of receptive fields. Extensive experiments conducted on SD-saliency-900, Magnetic tile, and DAGM 2007 indicate that our method achieves promising performance in comparison with other state-of-the-art methods. Meanwhile, our method reaches a real-time defect detection speed of 66 FPS.

Surface defect inspection is a very challenging task in which surface defects usually show weak appearances or exist under complex backgrounds. Most high-accuracy defect detection methods require expensive computation and storage overhead, making them less practical in some resource-constrained defect detection applications. Although some lightweight methods have achieved real-time inference speed with fewer parameters, they show poor detection accuracy in complex defect scenarios. To this end, we develop a Global Context Aggregation Network (GCANet) for lightweight saliency detection of surface defects on the encoder-decoder structure. First, we introduce a novel transformer encoder on the top layer of the lightweight backbone, which captures global context information through a novel Depth-wise Self-Attention (DSA) module. The proposed DSA performs element-wise similarity in channel dimension while maintaining linear complexity. In addition, we introduce a novel Channel Reference Attention (CRA) module before each decoder block to strengthen the representation of multi-level features in the bottom-up path. The proposed CRA exploits the channel correlation between features at different layers to adaptively enhance feature representation. The experimental results on three public defect datasets demonstrate that the proposed network achieves a better trade-off between accuracy and running efficiency compared with other 17 state-of-the-art methods. Specifically, GCANet achieves competitive accuracy (91.79% $F_{\beta}^{w}$, 93.55% $S_\alpha$, and 97.35% $E_\phi$) on SD-saliency-900 while running 272fps on a single gpu.

Surface defect inspection is of great importance for industrial manufacture and production. Though defect inspection methods based on deep learning have made significant progress, there are still some challenges for these methods, such as indistinguishable weak defects and defect-like interference in the background. To address these issues, we propose a transformer network with multi-stage CNN (Convolutional Neural Network) feature injection for surface defect segmentation, which is a UNet-like structure named CINFormer. CINFormer presents a simple yet effective feature integration mechanism that injects the multi-level CNN features of the input image into different stages of the transformer network in the encoder. This can maintain the merit of CNN capturing detailed features and that of transformer depressing noises in the background, which facilitates accurate defect detection. In addition, CINFormer presents a Top-K self-attention module to focus on tokens with more important information about the defects, so as to further reduce the impact of the redundant background. Extensive experiments conducted on the surface defect datasets DAGM 2007, Magnetic tile, and NEU show that the proposed CINFormer achieves state-of-the-art performance in defect detection.

Surface defect inspection is an important task in industrial inspection. Deep learning-based methods have demonstrated promising performance in this domain. Nevertheless, these methods still suffer from misjudgment when encountering challenges such as low-contrast defects and complex backgrounds. To overcome these issues, we present a decision fusion network (DFNet) that incorporates the semantic decision with the feature decision to strengthen the decision ability of the network. In particular, we introduce a decision fusion module (DFM) that extracts a semantic vector from the semantic decision branch and a feature vector for the feature decision branch and fuses them to make the final classification decision. In addition, we propose a perception fine-tuning module (PFM) that fine-tunes the foreground and background during the segmentation stage. PFM generates the semantic and feature outputs that are sent to the classification decision stage. Furthermore, we present an inner-outer separation weight matrix to address the impact of label edge uncertainty during segmentation supervision. Our experimental results on the publicly available datasets including KolektorSDD2 (96.1% AP) and Magnetic-tile-defect-datasets (94.6% mAP) demonstrate the effectiveness of the proposed method.

Visible-infrared person re-identification (VI-ReID) aims to match specific pedestrian images from different modalities. Although suffering an extra modality discrepancy, existing methods still follow the softmax loss training paradigm, which is widely used in single-modality classification tasks. The softmax loss lacks an explicit penalty for the apparent modality gap, which adversely limits the performance upper bound of the VI-ReID task. In this paper, we propose the spectral-aware softmax (SA-Softmax) loss, which can fully explore the embedding space with the modality information and has clear interpretability. Specifically, SA-Softmax loss utilizes an asynchronous optimization strategy based on the modality prototype instead of the synchronous optimization based on the identity prototype in the original softmax loss. To encourage a high overlapping between two modalities, SA-Softmax optimizes each sample by the prototype from another spectrum. Based on the observation and analysis of SA-Softmax, we modify the SA-Softmax with the Feature Mask and Absolute-Similarity Term to alleviate the ambiguous optimization during model training. Extensive experimental evaluations conducted on RegDB and SYSU-MM01 demonstrate the superior performance of the SA-Softmax over the state-of-the-art methods in such a cross-modality condition.

Quantization approximates a deep network model with floating-point numbers by the one with low bit width numbers, in order to accelerate inference and reduce computation. Quantizing a model without access to the original data, zero-shot quantization can be accomplished by fitting the real data distribution by data synthesis. However, zero-shot quantization achieves inferior performance compared to the post-training quantization with real data. We find it is because: 1) a normal generator is hard to obtain high diversity of synthetic data, since it lacks long-range information to allocate attention to global features; 2) the synthetic images aim to simulate the statistics of real data, which leads to weak intra-class heterogeneity and limited feature richness. To overcome these problems, we propose a novel deep network quantizer, dubbed Long-Range Zero-Shot Generative Deep Network Quantization (LRQ). Technically, we propose a long-range generator to learn long-range information instead of simple local features. In order for the synthetic data to contain more global features, long-range attention using large kernel convolution is incorporated into the generator. In addition, we also present an Adversarial Margin Add (AMA) module to force intra-class angular enlargement between feature vector and class center. As AMA increases the convergence difficulty of the loss function, which is opposite to the training objective of the original loss function, it forms an adversarial process. Furthermore, in order to transfer knowledge from the full-precision network, we also utilize a decoupled knowledge distillation. Extensive experiments demonstrate that LRQ obtains better performance than other competitors.

In this paper, we present an embarrassingly simple yet effective solution to a seemingly impossible mission, low-light image enhancement (LLIE) without access to any task-related data. The proposed solution, Noise SElf-Regression (NoiSER), simply learns a convolutional neural network equipped with a instance-normalization layer by taking a random noise image, $\mathcal{N}(0,\sigma^2)$ for each pixel, as both input and output for each training pair, and then the low-light image is fed to the learned network for predicting the normal-light image. Technically, an intuitive explanation for its effectiveness is as follows: 1) the self-regression reconstructs the contrast between adjacent pixels of the input image, 2) the instance-normalization layers may naturally remediate the overall magnitude/lighting of the input image, and 3) the $\mathcal{N}(0,\sigma^2)$ assumption for each pixel enforces the output image to follow the well-known gray-world hypothesis \cite{Gary-world_Hypothesis} when the image size is big enough, namely, the averages of three RGB components of an image converge to the same value. Compared to existing SOTA LLIE methods with access to different task-related data, NoiSER is surprisingly highly competitive in enhancement quality, yet with a much smaller model size, and much lower training and inference cost. With only $\sim$ 1K parameters, NoiSER realizes about 1 minute for training and 1.2 ms for inference with 600x400 resolution on RTX 2080 Ti. As a bonus, NoiSER possesses automated over-exposure suppression ability and shows excellent performance on over-exposed photos.

Mainstream image caption models are usually two-stage captioners, i.e., calculating object features by pre-trained detector, and feeding them into a language model to generate text descriptions. However, such an operation will cause a task-based information gap to decrease the performance, since the object features in detection task are suboptimal representation and cannot provide all necessary information for subsequent text generation. Besides, object features are usually represented by the last layer features that lose the local details of input images. In this paper, we propose a novel One-Stage Image Captioner (OSIC) with dynamic multi-sight learning, which directly transforms input image into descriptive sentences in one stage. As a result, the task-based information gap can be greatly reduced. To obtain rich features, we use the Swin Transformer to calculate multi-level features, and then feed them into a novel dynamic multi-sight embedding module to exploit both global structure and local texture of input images. To enhance the global modeling of encoder for caption, we propose a new dual-dimensional refining module to non-locally model the interaction of the embedded features. Finally, OSIC can obtain rich and useful information to improve the image caption task. Extensive comparisons on benchmark MS-COCO dataset verified the superior performance of our method.

Despite great progress achieved by transformer in various vision tasks, it is still underexplored for skeleton-based action recognition with only a few attempts. Besides, these methods directly calculate the pair-wise global self-attention equally for all the joints in both the spatial and temporal dimensions, undervaluing the effect of discriminative local joints and the short-range temporal dynamics. In this work, we propose a novel Focal and Global Spatial-Temporal Transformer network (FG-STFormer), that is equipped with two key components: (1) FG-SFormer: focal joints and global parts coupling spatial transformer. It forces the network to focus on modelling correlations for both the learned discriminative spatial joints and human body parts respectively. The selective focal joints eliminate the negative effect of non-informative ones during accumulating the correlations. Meanwhile, the interactions between the focal joints and body parts are incorporated to enhance the spatial dependencies via mutual cross-attention. (2) FG-TFormer: focal and global temporal transformer. Dilated temporal convolution is integrated into the global self-attention mechanism to explicitly capture the local temporal motion patterns of joints or body parts, which is found to be vital important to make temporal transformer work. Extensive experimental results on three benchmarks, namely NTU-60, NTU-120 and NW-UCLA, show our FG-STFormer surpasses all existing transformer-based methods, and compares favourably with state-of-the art GCN-based methods., Comment: Accepted by ACCV2022

Low-light image enhancement (LLIE) aims at improving the illumination and visibility of dark images with lighting noise. To handle the real-world low-light images often with heavy and complex noise, some efforts have been made for joint LLIE and denoising, which however only achieve inferior restoration performance. We attribute it to two challenges: 1) in real-world low-light images, noise is somewhat covered by low-lighting and the left noise after denoising would be inevitably amplified during enhancement; 2) conversion of raw data to sRGB would cause information loss and also more noise, and hence prior LLIE methods trained on raw data are unsuitable for more common sRGB images. In this work, we propose a novel Low-light Enhancement & Denoising Network for real-world low-light images (RLED-Net) in the sRGB color space. In RLED-Net, we apply a plug-and-play differentiable Latent Subspace Reconstruction Block (LSRB) to embed the real-world images into low-rank subspaces to suppress the noise and rectify the errors, such that the impact of noise during enhancement can be effectively shrunk. We then present an efficient Crossed-channel & Shift-window Transformer (CST) layer with two branches to calculate the window and channel attentions to resist the degradation (e.g., speckle noise and blur) caused by the noise in input images. Based on the CST layers, we further present a U-structure network CSTNet as backbone for deep feature recovery, and construct a feature refine block to refine the final features. Extensive experiments on both real noisy images and public image databases well verify the effectiveness of the proposed RLED-Net for RLLIE and denoising simultaneously.

Analysis of human interaction is one important research topic of human motion analysis. It has been studied either using first person vision (FPV) or third person vision (TPV). However, the joint learning of both types of vision has so far attracted little attention. One of the reasons is the lack of suitable datasets that cover both FPV and TPV. In addition, existing benchmark datasets of either FPV or TPV have several limitations, including the limited number of samples, participant subjects, interaction categories, and modalities. In this work, we contribute a large-scale human interaction dataset, namely, FT-HID dataset. FT-HID contains pair-aligned samples of first person and third person visions. The dataset was collected from 109 distinct subjects and has more than 90K samples for three modalities. The dataset has been validated by using several existing action recognition methods. In addition, we introduce a novel multi-view interaction mechanism for skeleton sequences, and a joint learning multi-stream framework for first person and third person visions. Both methods yield promising results on the FT-HID dataset. It is expected that the introduction of this vision-aligned large-scale dataset will promote the development of both FPV and TPV, and their joint learning techniques for human action analysis. The dataset and code are available at \href{https://github.com/ENDLICHERE/FT-HID}{here}.

A profound understanding of inter-agent relationships and motion behaviors is important to achieve high-quality planning when navigating in complex scenarios, especially at urban traffic intersections. We present a trajectory prediction approach with respect to traffic lights, D2-TPred, which uses a spatial dynamic interaction graph (SDG) and a behavior dependency graph (BDG) to handle the problem of discontinuous dependency in the spatial-temporal space. Specifically, the SDG is used to capture spatial interactions by reconstructing sub-graphs for different agents with dynamic and changeable characteristics during each frame. The BDG is used to infer motion tendency by modeling the implicit dependency of the current state on priors behaviors, especially the discontinuous motions corresponding to acceleration, deceleration, or turning direction. Moreover, we present a new dataset for vehicle trajectory prediction under traffic lights called VTP-TL. Our experimental results show that our model achieves more than {20.45% and 20.78% }improvement in terms of ADE and FDE, respectively, on VTP-TL as compared to other trajectory prediction algorithms. The dataset and code are available at: https://github.com/VTP-TL/D2-TPred., Comment: Accepted to ECCV2022, 17 pages, 6 figures. Project page: https://github.com/VTP-TL/D2-TPred

Blind image deblurring (BID) remains a challenging and significant task. Benefiting from the strong fitting ability of deep learning, paired data-driven supervised BID method has obtained great progress. However, paired data are usually synthesized by hand, and the realistic blurs are more complex than synthetic ones, which makes the supervised methods inept at modeling realistic blurs and hinders their real-world applications. As such, unsupervised deep BID method without paired data offers certain advantages, but current methods still suffer from some drawbacks, e.g., bulky model size, long inference time, and strict image resolution and domain requirements. In this paper, we propose a lightweight and real-time unsupervised BID baseline, termed Frequency-domain Contrastive Loss Constrained Lightweight CycleGAN (shortly, FCL-GAN), with attractive properties, i.e., no image domain limitation, no image resolution limitation, 25x lighter than SOTA, and 5x faster than SOTA. To guarantee the lightweight property and performance superiority, two new collaboration units called lightweight domain conversion unit(LDCU) and parameter-free frequency-domain contrastive unit(PFCU) are designed. LDCU mainly implements inter-domain conversion in lightweight manner. PFCU further explores the similarity measure, external difference and internal connection between the blurred domain and sharp domain images in frequency domain, without involving extra parameters. Extensive experiments on several image datasets demonstrate the effectiveness of our FCL-GAN in terms of performance, model size and reference time., Comment: Please cite this work as: Suiyi Zhao, Zhao Zhang, Richang Hong, Mingliang Xu, Yi Yang and Meng Wang, "FCL-GAN: A Lightweight and Real-Time Baseline for Unsupervised Blind Image Deblurring," In: Proceedings of the 30th ACM International Conference on Multimedia (ACM MM), Lisbon, Portugal, June 2022

Recent advances in Transformer architectures [1] have brought remarkable improvements to visual question answering (VQA). Nevertheless, Transformer-based VQA models are usually deep and wide to guarantee good performance, so they can only run on powerful GPU servers and cannot run on capacity-restricted platforms such as mobile phones. Therefore, it is desirable to learn an elastic VQA model that supports adaptive pruning at runtime to meet the efficiency constraints of different platforms. To this end, we present the bilaterally slimmable Transformer (BST), a general framework that can be seamlessly integrated into arbitrary Transformer-based VQA models to train a single model once and obtain various slimmed submodels of different widths and depths. To verify the effectiveness and generality of this method, we integrate the proposed BST framework with three typical Transformer-based VQA approaches, namely MCAN [2], UNITER [3], and CLIP-ViL [4], and conduct extensive experiments on two commonly-used benchmark datasets. In particular, one slimmed MCAN-BST submodel achieves comparable accuracy on VQA-v2, while being 0.38x smaller in model size and having 0.27x fewer FLOPs than the reference MCAN model. The smallest MCAN-BST submodel only has 9M parameters and 0.16G FLOPs during inference, making it possible to deploy it on a mobile device with less than 60 ms latency., Comment: Accepted at IEEE Transactions on Multimedia, 2023. Code available at https://github.com/MILVLG/bst

Graph convolutional networks (GCNs) based methods have achieved advanced performance on skeleton-based action recognition task. However, the skeleton graph cannot fully represent the motion information contained in skeleton data. In addition, the topology of the skeleton graph in the GCN-based methods is manually set according to natural connections, and it is fixed for all samples, which cannot well adapt to different situations. In this work, we propose a novel dynamic hypergraph convolutional networks (DHGCN) for skeleton-based action recognition. DHGCN uses hypergraph to represent the skeleton structure to effectively exploit the motion information contained in human joints. Each joint in the skeleton hypergraph is dynamically assigned the corresponding weight according to its moving, and the hypergraph topology in our model can be dynamically adjusted to different samples according to the relationship between the joints. Experimental results demonstrate that the performance of our model achieves competitive performance on three datasets: Kinetics-Skeleton 400, NTU RGB+D 60, and NTU RGB+D 120., Comment: 12 pages, 6 figures

Pedestrian trajectory prediction is an important technique of autonomous driving, which has become a research hot-spot in recent years. Previous methods mainly rely on the position relationship of pedestrians to model social interaction, which is obviously not enough to represent the complex cases in real situations. In addition, most of existing work usually introduce the scene interaction module as an independent branch and embed the social interaction features in the process of trajectory generation, rather than simultaneously carrying out the social interaction and scene interaction, which may undermine the rationality of trajectory prediction. In this paper, we propose one new prediction model named Social Soft Attention Graph Convolution Network (SSAGCN) which aims to simultaneously handle social interactions among pedestrians and scene interactions between pedestrians and environments. In detail, when modeling social interaction, we propose a new \emph{social soft attention function}, which fully considers various interaction factors among pedestrians. And it can distinguish the influence of pedestrians around the agent based on different factors under various situations. For the physical interaction, we propose one new \emph{sequential scene sharing mechanism}. The influence of the scene on one agent at each moment can be shared with other neighbors through social soft attention, therefore the influence of the scene is expanded both in spatial and temporal dimension. With the help of these improvements, we successfully obtain socially and physically acceptable predicted trajectories. The experiments on public available datasets prove the effectiveness of SSAGCN and have achieved state-of-the-art results., Comment: 14 pages, 8 figures

This paper proposes a new graph convolutional operator called central difference graph convolution (CDGC) for skeleton based action recognition. It is not only able to aggregate node information like a vanilla graph convolutional operation but also gradient information. Without introducing any additional parameters, CDGC can replace vanilla graph convolution in any existing Graph Convolutional Networks (GCNs). In addition, an accelerated version of the CDGC is developed which greatly improves the speed of training. Experiments on two popular large-scale datasets NTU RGB+D 60 & 120 have demonstrated the efficacy of the proposed CDGC. Code is available at https://github.com/iesymiao/CD-GCN., Comment: Accepted by IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)

The manual annotation for large-scale point clouds costs a lot of time and is usually unavailable in harsh real-world scenarios. Inspired by the great success of the pre-training and fine-tuning paradigm in both vision and language tasks, we argue that pre-training is one potential solution for obtaining a scalable model to 3D point cloud downstream tasks as well. In this paper, we, therefore, explore a new self-supervised learning method, called Mixing and Disentangling (MD), for 3D point cloud representation learning. As the name implies, we mix two input shapes and demand the model learning to separate the inputs from the mixed shape. We leverage this reconstruction task as the pretext optimization objective for self-supervised learning. There are two primary advantages: 1) Compared to prevailing image datasets, eg, ImageNet, point cloud datasets are de facto small. The mixing process can provide a much larger online training sample pool. 2) On the other hand, the disentangling process motivates the model to mine the geometric prior knowledge, eg, key points. To verify the effectiveness of the proposed pretext task, we build one baseline network, which is composed of one encoder and one decoder. During pre-training, we mix two original shapes and obtain the geometry-aware embedding from the encoder, then an instance-adaptive decoder is applied to recover the original shapes from the embedding. Albeit simple, the pre-trained encoder can capture the key points of an unseen point cloud and surpasses the encoder trained from scratch on downstream tasks. The proposed method has improved the empirical performance on both ModelNet-40 and ShapeNet-Part datasets in terms of point cloud classification and segmentation tasks. We further conduct ablation studies to explore the effect of each component and verify the generalization of our proposed strategy by harnessing different backbones.

Defect detection and classification technology has changed from traditional artificial visual inspection to current intelligent automated inspection, but most of the current defect detection methods are training related detection models based on a data-driven approach, taking into account the difficulty of collecting some sample data in the industrial field. We apply zero-shot learning technology to the industrial field. Aiming at the problem of the existing "Latent Feature Guide Attribute Attention" (LFGAA) zero-shot image classification network, the output latent attributes and artificially defined attributes are different in the semantic space, which leads to the problem of model performance degradation, proposed an LGFAA network based on semantic feedback, and improved model performance by constructing semantic embedded modules and feedback mechanisms. At the same time, for the common domain shift problem in zero-shot learning, based on the idea of co-training algorithm using the difference information between different views of data to learn from each other, we propose an Ensemble Co-training algorithm, which adaptively reduces the prediction error in image tag embedding from multiple angles. Various experiments conducted on the zero-shot dataset and the cylinder liner dataset in the industrial field provide competitive results., Comment: 28 pages 10 figures

Personalized image aesthetic assessment (PIAA) has recently become a hot topic due to its usefulness in a wide variety of applications such as photography, film and television, e-commerce, fashion design and so on. This task is more seriously affected by subjective factors and samples provided by users. In order to acquire precise personalized aesthetic distribution by small amount of samples, we propose a novel user-guided personalized image aesthetic assessment framework. This framework leverages user interactions to retouch and rank images for aesthetic assessment based on deep reinforcement learning (DRL), and generates personalized aesthetic distribution that is more in line with the aesthetic preferences of different users. It mainly consists of two stages. In the first stage, personalized aesthetic ranking is generated by interactive image enhancement and manual ranking, meanwhile two policy networks will be trained. The images will be pushed to the user for manual retouching and simultaneously to the enhancement policy network. The enhancement network utilizes the manual retouching results as the optimization goals of DRL. After that, the ranking process performs the similar operations like the retouching mentioned before. These two networks will be trained iteratively and alternatively to help to complete the final personalized aesthetic assessment automatically. In the second stage, these modified images are labeled with aesthetic attributes by one style-specific classifier, and then the personalized aesthetic distribution is generated based on the multiple aesthetic attributes of these images, which conforms to the aesthetic preference of users better., Comment: 12 pages, 8 figures

With the development of deep learning, the single super-resolution image reconstruction network models are becoming more and more complex. Small changes in hyperparameters of the models have a greater impact on model performance. In the existing works, experts have gradually explored a set of optimal model parameters based on empirical values or performing brute-force search. In this paper, we introduce a new super-resolution image reconstruction generative adversarial network framework, and a Bayesian optimization method used to optimizing the hyperparameters of the generator and discriminator. The generator is made by self-calibrated convolution, and discriminator is made by convolution lays. We have defined the hyperparameters such as the number of network layers and the number of neurons. Our method adopts Bayesian optimization as a optimization policy of GAN in our model. Not only can find the optimal hyperparameter solution automatically, but also can construct a super-resolution image reconstruction network, reducing the manual workload. Experiments show that Bayesian optimization can search the optimal solution earlier than the other two optimization algorithms., Comment: 9 pages, 6 figures

With the effective application of deep learning in computer vision, breakthroughs have been made in the research of super-resolution images reconstruction. However, many researches have pointed out that the insufficiency of the neural network extraction on image features may bring the deteriorating of newly reconstructed image. On the other hand, the generated pictures are sometimes too artificial because of over-smoothing. In order to solve the above problems, we propose a novel self-calibrated convolutional generative adversarial networks. The generator consists of feature extraction and image reconstruction. Feature extraction uses self-calibrated convolutions, which contains four portions, and each portion has specific functions. It can not only expand the range of receptive fields, but also obtain long-range spatial and inter-channel dependencies. Then image reconstruction is performed, and finally a super-resolution image is reconstructed. We have conducted thorough experiments on different datasets including set5, set14 and BSD100 under the SSIM evaluation method. The experimental results prove the effectiveness of the proposed network., Comment: 8 pages, 3 figures

Few-shot classification studies the problem of quickly adapting a deep learner to understanding novel classes based on few support images. In this context, recent research efforts have been aimed at designing more and more complex classifiers that measure similarities between query and support images, but left the importance of feature embeddings seldom explored. We show that the reliance on sophisticated classifiers is not necessary, and a simple classifier applied directly to improved feature embeddings can instead outperform most of the leading methods in the literature. To this end, we present a new method named \textbf{DCAP} for few-shot classification, in which we investigate how one can improve the quality of embeddings by leveraging \textbf{D}ense \textbf{C}lassification and \textbf{A}ttentive \textbf{P}ooling. Specifically, we propose to train a learner on base classes with abundant samples to solve dense classification problem first and then meta-train the learner on a bunch of randomly sampled few-shot tasks to adapt it to few-shot scenario or the test time scenario. During meta-training, we suggest to pool feature maps by applying attentive pooling instead of the widely used global average pooling (GAP) to prepare embeddings for few-shot classification. Attentive pooling learns to reweight local descriptors, explaining what the learner is looking for as evidence for decision making. Experiments on two benchmark datasets show the proposed method to be superior in multiple few-shot settings while being simpler and more explainable. Code is available at: \url{https://github.com/Ukeyboard/dcap/}., Comment: 23 pages, 7 figures, 7 tables

Trajectory prediction is a fundamental and challenging task for numerous applications, such as autonomous driving and intelligent robots. Currently, most of existing work treat the pedestrian trajectory as a series of fixed two-dimensional coordinates. However, in real scenarios, the trajectory often exhibits randomness, and has its own probability distribution. Inspired by this observed fact, also considering other movement characteristics of pedestrians, we propose one simple and intuitive movement description, probability trajectory, which maps the coordinate points of pedestrian trajectory into two-dimensional Gaussian distribution in images. Based on this unique description, we develop one novel trajectory prediction method, called social probability. The method combines the new probability trajectory and powerful convolution recurrent neural networks together. Both the input and output of our method are probability trajectories, which provide the recurrent neural network with sufficient spatial and random information of moving pedestrians. And the social probability extracts spatio-temporal features directly on the new movement description to generate robust and accurate predicted results. The experiments on public benchmark datasets show the effectiveness of the proposed method., Comment: 9 pages

In this paper, we propose a \textbf{Tr}ansformer-based RGB-D \textbf{e}gocentric \textbf{a}ction \textbf{r}ecognition framework, called Trear. It consists of two modules, inter-frame attention encoder and mutual-attentional fusion block. Instead of using optical flow or recurrent units, we adopt self-attention mechanism to model the temporal structure of the data from different modalities. Input frames are cropped randomly to mitigate the effect of the data redundancy. Features from each modality are interacted through the proposed fusion block and combined through a simple yet effective fusion operation to produce a joint RGB-D representation. Empirical experiments on two large egocentric RGB-D datasets, THU-READ and FPHA, and one small dataset, WCVS, have shown that the proposed method outperforms the state-of-the-art results by a large margin., Comment: Accepted by IEEE Transactions

Existing unsupervised visual odometry (VO) methods either match pairwise images or integrate the temporal information using recurrent neural networks over a long sequence of images. They are either not accurate, time-consuming in training or error accumulative. In this paper, we propose a method consisting of two camera pose estimators that deal with the information from pairwise images and a short sequence of images respectively. For image sequences, a Transformer-like structure is adopted to build a geometry model over a local temporal window, referred to as Transformer-based Auxiliary Pose Estimator (TAPE). Meanwhile, a Flow-to-Flow Pose Estimator (F2FPE) is proposed to exploit the relationship between pairwise images. The two estimators are constrained through a simple yet effective consistency loss in training. Empirical evaluation has shown that the proposed method outperforms the state-of-the-art unsupervised learning-based methods by a large margin and performs comparably to supervised and traditional ones on the KITTI and Malaga dataset.

Quick Response (QR) code is one of the most worldwide used two-dimensional codes.~Traditional QR codes appear as random collections of black-and-white modules that lack visual semantics and aesthetic elements, which inspires the recent works to beautify the appearances of QR codes. However, these works adopt fixed generation algorithms and therefore can only generate QR codes with a pre-defined style. In this paper, combining the Neural Style Transfer technique, we propose a novel end-to-end method, named ArtCoder, to generate the stylized QR codes that are personalized, diverse, attractive, and scanning-robust.~To guarantee that the generated stylized QR codes are still scanning-robust, we propose a Sampling-Simulation layer, a module-based code loss, and a competition mechanism. The experimental results show that our stylized QR codes have high-quality in both the visual effect and the scanning-robustness, and they are able to support the real-world application., Comment: 11 pages, 16 figures

The quality of learned features by representation learning determines the performance of learning algorithms and the related application tasks (such as high-dimensional data clustering). As a relatively new paradigm for representation learning, Concept Factorization (CF) has attracted a great deal of interests in the areas of machine learning and data mining for over a decade. Lots of effective CF based methods have been proposed based on different perspectives and properties, but note that it still remains not easy to grasp the essential connections and figure out the underlying explanatory factors from exiting studies. In this paper, we therefore survey the recent advances on CF methodologies and the potential benchmarks by categorizing and summarizing the current methods. Specifically, we first re-view the root CF method, and then explore the advancement of CF-based representation learning ranging from shallow to deep/multilayer cases. We also introduce the potential application areas of CF-based methods. Finally, we point out some future directions for studying the CF-based representation learning. Overall, this survey provides an insightful overview of both theoretical basis and current developments in the field of CF, which can also help the interested researchers to understand the current trends of CF and find the most appropriate CF techniques to deal with particular applications., Comment: Please cite this work as: Zhao Zhang, Yan Zhang, Mingliang Xu, Li Zhang, Yi Yang and Shuicheng Yan, "A Survey on Concept Factorization: From Shallow to Deep Representation Learning," Information Processing and Management (IPM), Jan 2021

Metric-based few-shot learning methods concentrate on learning transferable feature embedding that generalizes well from seen categories to unseen categories under the supervision of limited number of labelled instances. However, most of them treat each individual instance in the working context separately without considering its relationships with the others. In this work, we investigate a new metric-learning method, Memory-Augmented Relation Network (MRN), to explicitly exploit these relationships. In particular, for an instance, we choose the samples that are visually similar from the working context, and perform weighted information propagation to attentively aggregate helpful information from the chosen ones to enhance its representation. In MRN, we also formulate the distance metric as a learnable relation module which learns to compare for similarity measurement, and augment the working context with memory slots, both contributing to its generality. We empirically demonstrate that MRN yields significant improvement over its ancestor and achieves competitive or even better performance when compared with other few-shot learning approaches on the two major benchmark datasets, i.e. miniImagenet and tieredImagenet., Comment: To be submitted to ACM Multimedia 2020

Panoptic segmentation aims to perform instance segmentation for foreground instances and semantic segmentation for background stuff simultaneously. The typical top-down pipeline concentrates on two key issues: 1) how to effectively model the intrinsic interaction between semantic segmentation and instance segmentation, and 2) how to properly handle occlusion for panoptic segmentation. Intuitively, the complementarity between semantic segmentation and instance segmentation can be leveraged to improve the performance. Besides, we notice that using detection/mask scores is insufficient for resolving the occlusion problem. Motivated by these observations, we propose a novel deep panoptic segmentation scheme based on a bidirectional learning pipeline. Moreover, we introduce a plug-and-play occlusion handling algorithm to deal with the occlusion between different object instances. The experimental results on COCO panoptic benchmark validate the effectiveness of our proposed method. Codes will be released soon at https://github.com/Mooonside/BANet., Comment: to be published in CVPR2020, oral paper

Removing the rain streaks from single image is still a challenging task, since the shapes and directions of rain streaks in the synthetic datasets are very different from real images. Although supervised deep deraining networks have obtained impressive results on synthetic datasets, they still cannot obtain satisfactory results on real images due to weak generalization of rain removal capacity, i.e., the pre-trained models usually cannot handle new shapes and directions that may lead to over-derained/under-derained results. In this paper, we propose a new semi-supervised GAN-based deraining network termed Semi-DerainGAN, which can use both synthetic and real rainy images in a uniform network using two supervised and unsupervised processes. Specifically, a semi-supervised rain streak learner termed SSRML sharing the same parameters of both processes is derived, which makes the real images contribute more rain streak information. To deliver better deraining results, we design a paired discriminator for distinguishing the real pairs from fake pairs. Note that we also contribute a new real-world rainy image dataset Real200 to alleviate the difference between the synthetic and real image do-mains. Extensive results on public datasets show that our model can obtain competitive performance, especially on real images., Comment: Please cite this work as: Yanyan Wei, Zhao Zhang, Yang Wang, Haijun Zhang, Mingbo Zhao, Mingliang Xu and Meng Wang, "Semi-DerainGAN: A New Semi-supervised Single Image Deraining Network," In: Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), July 2021

Single image deraining (SID) is an important and challenging topic in emerging vision applications, and most of emerged deraining methods are supervised relying on the ground truth (i.e., paired images) in recent years. However, in practice it is rather common to have no un-paired images in real deraining task, in such cases how to remove the rain streaks in an unsupervised way will be a very challenging task due to lack of constraints between images and hence suffering from low-quality recovery results. In this paper, we explore the unsupervised SID task using unpaired data and propose a novel net called Attention-guided Deraining by Constrained CycleGAN (or shortly, DerainCycleGAN), which can fully utilize the constrained transfer learning abilitiy and circulatory structure of CycleGAN. Specifically, we design an unsu-pervised attention guided rain streak extractor (U-ARSE) that utilizes a memory to extract the rain streak masks with two constrained cycle-consistency branches jointly by paying attention to both the rainy and rain-free image domains. As a by-product, we also contribute a new paired rain image dataset called Rain200A, which is constructed by our network automatically. Compared with existing synthesis datasets, the rainy streaks in Rain200A contains more obvious and diverse shapes and directions. As a result, existing supervised methods trained on Rain200A can perform much better for processing real rainy images. Extensive experiments on synthesis and real datasets show that our net is superior to existing unsupervised deraining networks, and is also very competitive to other related supervised networks.

Localizing objects with weak supervision in an image is a key problem of the research in computer vision community. Many existing Weakly-Supervised Object Localization (WSOL) approaches tackle this problem by estimating the most discriminative regions with feature maps (activation maps) obtained by Deep Convolutional Neural Network, that is, only the objects or parts of them with the most discriminative response will be located. However, the activation maps often display different local maximum responses or relatively weak response when one image contains multiple objects with the same type or small objects. In this paper, we propose a simple yet effective multi-scale discriminative region discovery method to localize not only more integral objects but also as many as possible with only image-level class labels. The gradient weights flowing into different convolutional layers of CNN are taken as the input of our method, which is different from previous methods only considering that of the final convolutional layer. To mine more discriminative regions for the task of object localization, the multiple local maximum from the gradient weight maps are leveraged to generate the localization map with a parallel sliding window. Furthermore, multi-scale localization maps from different convolutional layers are fused to produce the final result. We evaluate the proposed method with the foundation of VGGnet on the ILSVRC 2016, CUB-200-2011 and PASCAL VOC 2012 datasets. On ILSVRC 2016, the proposed method yields the Top-1 localization error of 48.65\%, which outperforms previous results by 2.75\%. On PASCAL VOC 2012, our approach achieve the highest localization accuracy of 0.43. Even for CUB-200-2011 dataset, our method still achieves competitive results., Comment: 12 pages,7 figures

Due to domain bias, directly deploying a deep person re-identification (re-ID) model trained on one dataset often achieves considerably poor accuracy on another dataset. In this paper, we propose an Adaptive Exploration (AE) method to address the domain-shift problem for re-ID in an unsupervised manner. Specifically, in the target domain, the re-ID model is inducted to 1) maximize distances between all person images and 2) minimize distances between similar person images. In the first case, by treating each person image as an individual class, a non-parametric classifier with a feature memory is exploited to encourage person images to move far away from each other. In the second case, according to a similarity threshold, our method adaptively selects neighborhoods for each person image in the feature space. By treating these similar person images as the same class, the non-parametric classifier forces them to stay closer. However, a problem of the adaptive selection is that, when an image has too many neighborhoods, it is more likely to attract other images as its neighborhoods. As a result, a minority of images may select a large number of neighborhoods while a majority of images have only a few neighborhoods. To address this issue, we additionally integrate a balance strategy into the adaptive selection. We evaluate our methods with two protocols. The first one is called "target-only re-ID", in which only the unlabeled target data is used for training. The second one is called "domain adaptive re-ID", in which both the source data and the target data are used during training. Experimental results on large-scale re-ID datasets demonstrate the effectiveness of our method. Our code has been released at https://github.com/dyh127/Adaptive-Exploration-for-Unsupervised-Person-Re-Identification., Comment: ACM Transactions on Multimedia Computing, Communications and Application (TOMCCAP)

This paper proposes a method based on repulsive forces and sparse reconstruction for the detection and location of abnormal events in crowded scenes. In order to avoid the challenging problem of accurately tracking each specific individual in a dense or complex scene, we divide each frame of the surveillance video into a fixed number of grids and select a single representative point in each grid as the individual to track. The repulsive force model, which can accurately reflect interactive behaviors of crowds, is used to calculate the interactive forces between grid particles in crowded scenes and to construct a force flow matrix using these discrete forces from a fixed number of continuous frames. The force flow matrix, which contains spatial and temporal information, is adopted to train a group of visual dictionaries by sparse coding. To further improve the detection efficiency and avoid concept drift, we propose a fully unsupervised global and local dynamic updating algorithm, based on sparse reconstruction and a group of word pools. For anomaly location, since our method is based on a fixed grid, we can judge whether anomalies occur in a region intuitively according to the reconstruction error of the corresponding visual words. We experimentally verify the proposed method using the UMN dataset, the UCSD dataset and the Web dataset separately. The results indicate that our method can not only detect abnormal events accurately, but can also pinpoint the location of anomalies.

For most of the object detectors based on multi-scale feature maps, the shallow layers are rich in fine spatial information and thus mainly responsible for small object detection. The performance of small object detection, however, is still less than satisfactory because of the deficiency of semantic information on shallow feature maps. In this paper, we design a Multi-scale Deconvolutional Single Shot Detector (MDSSD), especially for small object detection. In MDSSD, multiple high-level feature maps at different scales are upsampled simultaneously to increase the spatial resolution. Afterwards, we implement the skip connections with low-level feature maps via Fusion Block. The fusion feature maps, named Fusion Module, are of strong feature representational power of small instances. It is noteworthy that these high-level feature maps utilized in Fusion Block preserve both strong semantic information and some fine details of small instances, rather than the top-most layer where the representation of fine details for small objects are potentially wiped out. The proposed framework achieves 77.6% mAP for small object detection on the challenging dataset TT100K with 512 x 512 input, outperforming other detectors with a large margin. Moreover, it can also achieve state-of-the-art results for general object detection on PASCAL VOC2007 test and MS COCO test-dev2015, especially achieving 2 to 5 points improvement on small object categories.

When assessing whether an image is of high or low quality, it is indispensable to take personal preference into account. Existing aesthetic models lay emphasis on hand-crafted features or deep features commonly shared by high quality images, but with limited or no consideration for personal preference and user interaction. To that end, we propose a novel and user-friendly aesthetic ranking framework via powerful deep neural network and a small amount of user interaction, which can automatically estimate and rank the aesthetic characteristics of images in accordance with users' preference. Our framework takes as input a series of photos that users prefer, and produces as output a reliable, user-specific aesthetic ranking model matching with users' preference. Considering the subjectivity of personal preference and the uncertainty of user's single selection, a unique and exclusive dataset will be constructed interactively to describe the preference of one individual by retrieving the most similar images with regard to those specified by users. Based on this unique user-specific dataset and sufficient well-designed aesthetic attributes, a customized aesthetic distribution model can be learned, which concatenates both personalized preference and aesthetic rules. We conduct extensive experiments and user studies on two large-scale public datasets, and demonstrate that our framework outperforms those work based on conventional aesthetic assessment or ranking model.

In this paper, we propose a novel multi-stage network architecture with two branches in each stage to estimate multi-person poses in images. The first branch predicts the confidence maps of joints and uses a geometrical transform kernel to propagate information between neighboring joints at the confidence level. The second branch proposes a bi-directional graph structure information model (BGSIM) to encode rich contextual information and to infer the occlusion relationship among different joints. We dynamically determine the joint point with highest response of the confidence maps as base point of passing message in BGSIM. Based on the proposed network structure, we achieve an average precision of 62.9 on the COCO Keypoint Challenge dataset and 77.6 on the MPII (multi-person) dataset. Compared with other state-of-art methods, our method can achieve highly promising results on our selected multi-person dataset without extra training.

It is important to monitor and analyze crowd events for the sake of city safety. In an EDOF (extended depth of field) image with a crowded scene, the distribution of people is highly imbalanced. People far away from the camera look much smaller and often occlude each other heavily, while people close to the camera look larger. In such a case, it is difficult to accurately estimate the number of people by using one technique. In this paper, we propose a Depth Information Guided Crowd Counting (DigCrowd) method to deal with crowded EDOF scenes. DigCrowd first uses the depth information of an image to segment the scene into a far-view region and a near-view region. Then Digcrowd maps the far-view region to its crowd density map and uses a detection method to count the people in the near-view region. In addition, we introduce a new crowd dataset that contains 1000 images. Experimental results demonstrate the effectiveness of our DigCrowd method, Comment: 9 pages, 8 figures. The paper is under consideration at Pattern Recognition Letters

Matching images and sentences demands a fine understanding of both modalities. In this paper, we propose a new system to discriminatively embed the image and text to a shared visual-textual space. In this field, most existing works apply the ranking loss to pull the positive image / text pairs close and push the negative pairs apart from each other. However, directly deploying the ranking loss is hard for network learning, since it starts from the two heterogeneous features to build inter-modal relationship. To address this problem, we propose the instance loss which explicitly considers the intra-modal data distribution. It is based on an unsupervised assumption that each image / text group can be viewed as a class. So the network can learn the fine granularity from every image/text group. The experiment shows that the instance loss offers better weight initialization for the ranking loss, so that more discriminative embeddings can be learned. Besides, existing works usually apply the off-the-shelf features, i.e., word2vec and fixed visual feature. So in a minor contribution, this paper constructs an end-to-end dual-path convolutional network to learn the image and text representations. End-to-end learning allows the system to directly learn from the data and fully utilize the supervision. On two generic retrieval datasets (Flickr30k and MSCOCO), experiments demonstrate that our method yields competitive accuracy compared to state-of-the-art methods. Moreover, in language based person retrieval, we improve the state of the art by a large margin. The code has been made publicly available., Comment: 15pages, 15 figures, 8 tables

This paper addresses the problem of handling spatial misalignments due to camera-view changes or human-pose variations in person re-identification. We first introduce a boosting-based approach to learn a correspondence structure which indicates the patch-wise matching probabilities between images from a target camera pair. The learned correspondence structure can not only capture the spatial correspondence pattern between cameras but also handle the viewpoint or human-pose variation in individual images. We further introduce a global constraint-based matching process. It integrates a global matching constraint over the learned correspondence structure to exclude cross-view misalignments during the image patch matching process, hence achieving a more reliable matching score between images. Finally, we also extend our approach by introducing a multi-structure scheme, which learns a set of local correspondence structures to capture the spatial correspondence sub-patterns between a camera pair, so as to handle the spatial misalignments between individual images in a more precise way. Experimental results on various datasets demonstrate the effectiveness of our approach., Comment: IEEE Trans. Image Processing, vol. 26, no. 5, pp. 2438-2453, 2017. The project page for this paper is available at http://min.sjtu.edu.cn/lwydemo/personReID.htm arXiv admin note: text overlap with arXiv:1504.06243

Trajectory analysis is essential in many applications. In this paper, we address the problem of representing motion trajectories in a highly informative way, and consequently utilize it for analyzing trajectories. Our approach first leverages the complete information from given trajectories to construct a thermal transfer field which provides a context-rich way to describe the global motion pattern in a scene. Then, a 3D tube is derived which depicts an input trajectory by integrating its surrounding motion patterns contained in the thermal transfer field. The 3D tube effectively: 1) maintains the movement information of a trajectory, 2) embeds the complete contextual motion pattern around a trajectory, 3) visualizes information about a trajectory in a clear and unified way. We further introduce a droplet-based process. It derives a droplet vector from a 3D tube, so as to characterize the high-dimensional 3D tube information in a simple but effective way. Finally, we apply our tube-and-droplet representation to trajectory analysis applications including trajectory clustering, trajectory classification & abnormality detection, and 3D action recognition. Experimental comparisons with state-of-the-art algorithms demonstrate the effectiveness of our approach., Comment: IEEE Transactions on Pattern Analysis and Machine Intelligence, DOI: 10.1109/TPAMI.2016.2608884, 2016. Code for our work is available at http://min.sjtu.edu.cn/lwydemo/Trajectory%20analysis.htm

The visualization of an image collection is the process of displaying a collection of images on a screen under some specific layout requirements. This paper focuses on an important problem that is not well addressed by the previous methods: visualizing image collections into arbitrary layout shapes while arranging images according to user-defined semantic or visual correlations (e.g., color or object category). To this end, we first propose a property-based tree construction scheme to organize images of a collection into a tree structure according to user-defined properties. In this way, images can be adaptively placed with the desired semantic or visual correlations in the final visualization layout. Then, we design a two-step visualization optimization scheme to further optimize image layouts. As a result, multiple layout effects including layout shape and image overlap ratio can be effectively controlled to guarantee a satisfactory visualization. Finally, we also propose a tree-transfer scheme such that visualization layouts can be adaptively changed when users select different "images of interest". We demonstrate the effectiveness of our proposed approach through the comparisons with state-of-the-art visualization techniques., Comment: This manuscript is the accepted version for T-CYB (IEEE Transactions on Cybernetics) IEEE Trans. Cybernetics, 2015

This paper addresses the problem of handling spatial misalignments due to camera-view changes or human-pose variations in person re-identification. We first introduce a boosting-based approach to learn a correspondence structure which indicates the patch-wise matching probabilities between images from a target camera pair. The learned correspondence structure can not only capture the spatial correspondence pattern between cameras but also handle the viewpoint or human-pose variation in individual images. We further introduce a global-based matching process. It integrates a global matching constraint over the learned correspondence structure to exclude cross-view misalignments during the image patch matching process, hence achieving a more reliable matching score between images. Experimental results on various datasets demonstrate the effectiveness of our approach.