Yongjie Li

Fu-Ya Luo, Shu-Lin Liu, Yi-Jun Cao et al.

Stable imaging in adverse environments (e.g., total darkness) makes thermal infrared (TIR) cameras a prevalent option for night scene perception. However, the low contrast and lack of chromaticity of TIR images are detrimental to human interpretation and subsequent deployment of RGB-based vision algorithms. Therefore, it makes sense to colorize the nighttime TIR images by translating them into the corresponding daytime color images (NTIR2DC). Despite the impressive progress made in the NTIR2DC task, how to improve the translation performance of small object classes is under-explored. To address this problem, we propose a generative adversarial network incorporating feedback-based object appearance learning (FoalGAN). Specifically, an occlusion-aware mixup module and corresponding appearance consistency loss are proposed to reduce the context dependence of object translation. As a representative example of small objects in nighttime street scenes, we illustrate how to enhance the realism of traffic light by designing a traffic light appearance loss. To further improve the appearance learning of small objects, we devise a dual feedback learning strategy to selectively adjust the learning frequency of different samples. In addition, we provide pixel-level annotation for a subset of the Brno dataset, which can facilitate the research of NTIR image understanding under multiple weather conditions. Extensive experiments illustrate that the proposed FoalGAN is not only effective for appearance learning of small objects, but also outperforms other image translation methods in terms of semantic preservation and edge consistency for the NTIR2DC task.

Kai-Fu Yang, Fu-Ya Luo, Yong-Jie Li

Color constancy is a fundamental ability of many biological visual systems and a crucial step in computer imaging systems. Bio-inspired modeling offers a promising way to elucidate the computational principles underlying color constancy and to develop efficient computational methods. However, bio-inspired methods for color constancy remain underexplored and lack a comprehensive analysis. This paper presents a comprehensive technical framework that integrates biological mechanisms, computational theory, and algorithmic implementation for bio-inspired color constancy. Specifically, we systematically revisit the computational theory of biological color constancy, which shows that illuminant estimation can be reduced to the task of gray-anchor (pixel or surface) detection in early vision. Subsequently, typical gray-pixel detection methods, including Gray-Pixel and Grayness-Index, are reinterpreted within a unified theoretical framework with the Lambertian reflection model and biological color-opponent mechanisms. Finally, we propose a simple learning-based method that couples reflection-model constraints with feature learning to explore the potential of bio-inspired color constancy based on gray-pixel detection. Extensive experiments confirm the effectiveness of gray-pixel detection for color constancy and demonstrate the potential of bio-inspired methods.

Fu-Ya Luo, Yi-Jun Cao, Kai-Fu Yang et al.

Nighttime thermal infrared (NTIR) image colorization, also known as translation of NTIR images into daytime color images (NTIR2DC), is a promising research direction to facilitate nighttime scene perception for humans and intelligent systems under unfavorable conditions (e.g., complete darkness). However, previously developed methods have poor colorization performance for small sample classes. Moreover, reducing the high confidence noise in pseudo-labels and addressing the problem of image gradient disappearance during translation are still under-explored, and keeping edges from being distorted during translation is also challenging. To address the aforementioned issues, we propose a novel learning framework called Memory-guided cOllaboRative atteNtion Generative Adversarial Network (MornGAN), which is inspired by the analogical reasoning mechanisms of humans. Specifically, a memory-guided sample selection strategy and adaptive collaborative attention loss are devised to enhance the semantic preservation of small sample categories. In addition, we propose an online semantic distillation module to mine and refine the pseudo-labels of NTIR images. Further, conditional gradient repair loss is introduced for reducing edge distortion during translation. Extensive experiments on the NTIR2DC task show that the proposed MornGAN significantly outperforms other image-to-image translation methods in terms of semantic preservation and edge consistency, which helps improve the object detection accuracy remarkably.

Shuquan Lian, Yuhang Wu, Jia Ma et al.

The emergence of Multimodal Large Language Models (MLLMs) has driven significant advances in Graphical User Interface (GUI) agent capabilities. Nevertheless, existing GUI agent training and inference techniques still suffer from a dilemma for reasoning designs, ineffective reward, and visual noise. To address these issues, we introduce UI-AGILE for enhancing GUI agents at both training and inference. For training, we propose a suite of improvements to the Supervised Fine-Tuning (SFT) process: 1) a continuous reward function to incentivize high-precision grounding; 2) a ``Simple Thinking'' reward to balance planning with speed and grounding accuracy; and 3) a cropping-based resampling strategy to mitigate the sparse reward problem and improve learning on complex tasks. For inference, we present decomposed grounding with selection to dramatically improve grounding accuracy on high-resolution displays by breaking the image into smaller, manageable parts. Experiments show that UI-AGILE achieves the state-of-the-art grounding performance on two benchmarks ScreenSpot-Pro and ScreenSpot-v2 while it also exhibits strong general agent capabilities. For instance, using both our training and inference enhancement methods brings 23\% grounding accuracy improvement over the best baseline on ScreenSpot-Pro. We provide the code in https://github.com/KDEGroup/UI-AGILE.

Haolong Ma, Hui Li, Chunyang Cheng et al.

All-in-One Degradation-Aware Fusion Models (ADFMs) as one of multi-modal image fusion models, which aims to address complex scenes by mitigating degradations from source images and generating high-quality fused images. Mainstream ADFMs rely on end-to-end learning and heavily synthesized datasets to achieve degradation awareness and fusion. This rough learning strategy and non-real world scenario dataset dependence often limit their upper-bound performance, leading to low-quality results. To address these limitations, we present LURE, a Learning-driven Unified REpresentation model for infrared and visible image fusion, which is degradation-aware. LURE learns a Unified Latent Feature Space (ULFS) to avoid the dependency on complex data formats inherent in previous end-to-end learning pipelines. It further improves image fusion quality by leveraging the intrinsic relationships between multi-modalities. A novel loss function is also proposed to drive the learning of unified latent representations more stable.More importantly, LURE seamlessly incorporates existing high-quality real-world image restoration datasets. To further enhance the model's representation capability, we design a simple yet effective structure, termed internal residual block, to facilitate the learning of latent features. Experiments show our method outperforms state-of-the-art (SOTA) methods across general fusion, degradation-aware fusion, and downstream tasks. The code is available in the supplementary materials.

Xinxu Wei, Xi Lin, Haiyun Liu et al.

Effective retinal vessel segmentation requires a sophisticated integration of global contextual awareness and local vessel continuity. To address this challenge, we propose the Graph Capsule Convolution Network (GCC-UNet), which merges capsule convolutions with CNNs to capture both local and global features. The Graph Capsule Convolution operator is specifically designed to enhance the representation of global context, while the Selective Graph Attention Fusion module ensures seamless integration of local and global information. To further improve vessel continuity, we introduce the Bottleneck Graph Attention module, which incorporates Channel-wise and Spatial Graph Attention mechanisms. The Multi-Scale Graph Fusion module adeptly combines features from various scales. Our approach has been rigorously validated through experiments on widely used public datasets, with ablation studies confirming the efficacy of each component. Comparative results highlight GCC-UNet's superior performance over existing methods, setting a new benchmark in retinal vessel segmentation. Notably, this work represents the first integration of vanilla, graph, and capsule convolutional techniques in the domain of medical image segmentation.

Hui Li, Xiaoyu Ren, Hongjiu Yu et al.

Facial attractiveness prediction (FAP) has long been an important computer vision task, which could be widely applied in live streaming for facial retouching, content recommendation, etc. However, previous FAP datasets are either small, closed-source, or lack diversity. Moreover, the corresponding FAP models exhibit limited generalization and adaptation ability. To overcome these limitations, in this paper we present LiveBeauty, the first large-scale live-specific FAP dataset, in a more challenging application scenario, i.e., live streaming. 10,000 face images are collected from a live streaming platform directly, with 200,000 corresponding attractiveness annotations obtained from a well-devised subjective experiment, making LiveBeauty the largest open-access FAP dataset in the challenging live scenario. Furthermore, a multi-modal FAP method is proposed to measure the facial attractiveness in live streaming. Specifically, we first extract holistic facial prior knowledge and multi-modal aesthetic semantic features via a Personalized Attractiveness Prior Module (PAPM) and a Multi-modal Attractiveness Encoder Module (MAEM), respectively, then integrate the extracted features through a Cross-Modal Fusion Module (CMFM). Extensive experiments conducted on both LiveBeauty and other open-source FAP datasets demonstrate that our proposed method achieves state-of-the-art performance. Dataset will be available soon.

Xinxu Wei, Xianshi Zhang, Shisen Wang et al.

Images obtained in real-world low-light conditions are not only low in brightness, but they also suffer from many other types of degradation, such as color bias, unknown noise, detail loss and halo artifacts. In this paper, we propose a very fast deep learning framework called Bringing the Lightness (denoted as BLNet) that consists of two U-Nets with a series of well-designed loss functions to tackle all of the above degradations. Based on Retinex Theory, the decomposition net in our model can decompose low-light images into reflectance and illumination and remove noise in the reflectance during the decomposition phase. We propose a Noise and Color Bias Control module (NCBC Module) that contains a convolutional neural network and two loss functions (noise loss and color loss). This module is only used to calculate the loss functions during the training phase, so our method is very fast during the test phase. This module can smooth the reflectance to achieve the purpose of noise removal while preserving details and edge information and controlling color bias. We propose a network that can be trained to learn the mapping between low-light and normal-light illumination and enhance the brightness of images taken in low-light illumination. We train and evaluate the performance of our proposed model over the real-world Low-Light (LOL) dataset), and we also test our model over several other frequently used datasets (LIME, DICM and MEF datasets). We conduct extensive experiments to demonstrate that our approach achieves a promising effect with good rubustness and generalization and outperforms many other state-of-the-art methods qualitatively and quantitatively. Our method achieves high speed because we use loss functions instead of introducing additional denoisers for noise removal and color correction. The code and model are available at https://github.com/weixinxu666/BLNet.

Fuya Luo, Yunhan Li, Guang Zeng et al.

Benefitting from insensitivity to light and high penetration of foggy environments, infrared cameras are widely used for sensing in nighttime traffic scenes. However, the low contrast and lack of chromaticity of thermal infrared (TIR) images hinder the human interpretation and portability of high-level computer vision algorithms. Colorization to translate a nighttime TIR image into a daytime color (NTIR2DC) image may be a promising way to facilitate nighttime scene perception. Despite recent impressive advances in image translation, semantic encoding entanglement and geometric distortion in the NTIR2DC task remain under-addressed. Hence, we propose a toP-down attEntion And gRadient aLignment based GAN, referred to as PearlGAN. A top-down guided attention module and an elaborate attentional loss are first designed to reduce the semantic encoding ambiguity during translation. Then, a structured gradient alignment loss is introduced to encourage edge consistency between the translated and input images. In addition, pixel-level annotation is carried out on a subset of FLIR and KAIST datasets to evaluate the semantic preservation performance of multiple translation methods. Furthermore, a new metric is devised to evaluate the geometric consistency in the translation process. Extensive experiments demonstrate the superiority of the proposed PearlGAN over other image translation methods for the NTIR2DC task. The source code and labeled segmentation masks will be available at \url{https://github.com/FuyaLuo/PearlGAN/}.

Liheng Zhang, Jin Wang, Hui Li et al.

3D understanding has drawn significant attention recently, leveraging Vision-Language Models (VLMs) to enable multi-modal reasoning between point cloud and text data. Current 3D-VLMs directly embed the 3D point clouds into 3D tokens, following large 2D-VLMs with powerful reasoning capabilities. However, this framework has a great computational cost limiting its application, where we identify that the bottleneck lies in processing all 3D tokens in the Large Language Model (LLM) part. This raises the question: how can we reduce the computational overhead introduced by 3D tokens while preserving the integrity of their essential information? To address this question, we introduce Hierarchical Compensatory Compression (HCC-3D) to efficiently compress 3D tokens while maintaining critical detail retention. Specifically, we first propose a global structure compression (GSC), in which we design global queries to compress all 3D tokens into a few key tokens while keeping overall structural information. Then, to compensate for the information loss in GSC, we further propose an adaptive detail mining (ADM) module that selectively recompresses salient but under-attended features through complementary scoring. Extensive experiments demonstrate that HCC-3D not only achieves extreme compression ratios (approximately 98%) compared to previous 3D-VLMs, but also achieves new state-of-the-art performance, showing the great improvements on both efficiency and performance.

Tianyu Huang, Wangguandong Zheng, Tengfei Wang et al.

Real-world applications like video gaming and virtual reality often demand the ability to model 3D scenes that users can explore along custom camera trajectories. While significant progress has been made in generating 3D objects from text or images, creating long-range, 3D-consistent, explorable 3D scenes remains a complex and challenging problem. In this work, we present Voyager, a novel video diffusion framework that generates world-consistent 3D point-cloud sequences from a single image with user-defined camera path. Unlike existing approaches, Voyager achieves end-to-end scene generation and reconstruction with inherent consistency across frames, eliminating the need for 3D reconstruction pipelines (e.g., structure-from-motion or multi-view stereo). Our method integrates three key components: 1) World-Consistent Video Diffusion: A unified architecture that jointly generates aligned RGB and depth video sequences, conditioned on existing world observation to ensure global coherence 2) Long-Range World Exploration: An efficient world cache with point culling and an auto-regressive inference with smooth video sampling for iterative scene extension with context-aware consistency, and 3) Scalable Data Engine: A video reconstruction pipeline that automates camera pose estimation and metric depth prediction for arbitrary videos, enabling large-scale, diverse training data curation without manual 3D annotations. Collectively, these designs result in a clear improvement over existing methods in visual quality and geometric accuracy, with versatile applications.

Yijun Cao, Fuya Luo, Yongjie Li

Unsupervised monocular depth learning generally relies on the photometric relation among temporally adjacent images. Most of previous works use both mean absolute error (MAE) and structure similarity index measure (SSIM) with conventional form as training loss. However, they ignore the effect of different components in the SSIM function and the corresponding hyperparameters on the training. To address these issues, this work proposes a new form of SSIM. Compared with original SSIM function, the proposed new form uses addition rather than multiplication to combine the luminance, contrast, and structural similarity related components in SSIM. The loss function constructed with this scheme helps result in smoother gradients and achieve higher performance on unsupervised depth estimation. We conduct extensive experiments to determine the relatively optimal combination of parameters for our new SSIM. Based on the popular MonoDepth approach, the optimized SSIM loss function can remarkably outperform the baseline on the KITTI-2015 outdoor dataset.

Hongzhi You, Yijun Cao, Wei Yuan et al.

From a perspective of feature matching, optical flow estimation for event cameras involves identifying event correspondences by comparing feature similarity across accompanying event frames. In this work, we introduces an effective and robust high-dimensional (HD) feature descriptor for event frames, utilizing Vector Symbolic Architectures (VSA). The topological similarity among neighboring variables within VSA contributes to the enhanced representation similarity of feature descriptors for flow-matching points, while its structured symbolic representation capacity facilitates feature fusion from both event polarities and multiple spatial scales. Based on this HD feature descriptor, we propose a novel feature matching framework for event-based optical flow, encompassing both model-based (VSA-Flow) and self-supervised learning (VSA-SM) methods. In VSA-Flow, accurate optical flow estimation validates the effectiveness of HD feature descriptors. In VSA-SM, a novel similarity maximization method based on the HD feature descriptor is proposed to learn optical flow in a self-supervised way from events alone, eliminating the need for auxiliary grayscale images. Evaluation results demonstrate that our VSA-based method achieves superior accuracy in comparison to both model-based and self-supervised learning methods on the DSEC benchmark, while remains competitive among both methods on the MVSEC benchmark. This contribution marks a significant advancement in event-based optical flow within the feature matching methodology.

Wang-Wang Yu, Xian-Shi Zhang, Fu-Ya Luo et al.

Frame-level micro- and macro-expression spotting methods require time-consuming frame-by-frame observation during annotation. Meanwhile, video-level spotting lacks sufficient information about the location and number of expressions during training, resulting in significantly inferior performance compared with fully-supervised spotting. To bridge this gap, we propose a point-level weakly-supervised expression spotting (PWES) framework, where each expression requires to be annotated with only one random frame (i.e., a point). To mitigate the issue of sparse label distribution, the prevailing solution is pseudo-label mining, which, however, introduces new problems: localizing contextual background snippets results in inaccurate boundaries and discarding foreground snippets leads to fragmentary predictions. Therefore, we design the strategies of multi-refined pseudo label generation (MPLG) and distribution-guided feature contrastive learning (DFCL) to address these problems. Specifically, MPLG generates more reliable pseudo labels by merging class-specific probabilities, attention scores, fused features, and point-level labels. DFCL is utilized to enhance feature similarity for the same categories and feature variability for different categories while capturing global representations across the entire datasets. Extensive experiments on the CAS(ME)^2, CAS(ME)^3, and SAMM-LV datasets demonstrate PWES achieves promising performance comparable to that of recent fully-supervised methods.

Zhangyong Tang, Tianyang Xu, Xuefeng Zhu et al.

The development of smart cities has led to the generation of massive amounts of multi-modal data in the context of a range of tasks that enable a comprehensive monitoring of the smart city infrastructure and services. This paper surveys one of the most critical tasks, multi-modal visual object tracking (MMVOT), from the perspective of multimodality analysis. Generally, MMVOT differs from single-modal tracking in four key aspects, data collection, modality alignment and annotation, model designing, and evaluation. Accordingly, we begin with an introduction to the relevant data modalities, laying the groundwork for their integration. This naturally leads to a discussion of challenges of multi-modal data collection, alignment, and annotation. Subsequently, existing MMVOT methods are categorised, based on different ways to deal with visible (RGB) and X modalities: programming the auxiliary X branch with replicated or non-replicated experimental configurations from the RGB branch. Here X can be thermal infrared (T), depth (D), event (E), near infrared (NIR), language (L), or sonar (S). The final part of the paper addresses evaluation and benchmarking. In summary, we undertake an omni survey of all aspects of multi-modal visual object tracking (VOT), covering six MMVOT tasks and featuring 338 references in total. In addition, we discuss the fundamental rhetorical question: Is multi-modal tracking always guaranteed to provide a superior solution to unimodal tracking with the help of information fusion, and if not, in what circumstances its application is beneficial. Furthermore, for the first time in this field, we analyse the distributions of the object categories in the existing MMVOT datasets, revealing their pronounced long-tail nature and a noticeable lack of animal categories when compared with RGB datasets.

Zhong-Hua Sun, Ru-Yuan Zhang, Zonglei Zhen et al.

In abstract visual reasoning, monolithic deep learning models suffer from limited interpretability and generalization, while existing neuro-symbolic approaches fall short in capturing the diversity and systematicity of attributes and relation representations. To address these challenges, we propose a Systematic Abductive Reasoning model with diverse relation representations (Rel-SAR) in Vector-symbolic Architecture (VSA) to solve Raven's Progressive Matrices (RPM). To derive attribute representations with symbolic reasoning potential, we introduce not only various types of atomic vectors that represent numeric, periodic and logical semantics, but also the structured high-dimentional representation (SHDR) for the overall Grid component. For systematic reasoning, we propose novel numerical and logical relation functions and perform rule abduction and execution in a unified framework that integrates these relation representations. Experimental results demonstrate that Rel-SAR achieves significant improvement on RPM tasks and exhibits robust out-of-distribution generalization. Rel-SAR leverages the synergy between HD attribute representations and symbolic reasoning to achieve systematic abductive reasoning with both interpretable and computable semantics.

Xiang Zhao, Ruijie Li, Qiao Ning et al.

The identification of drug-target interactions (DTI) is critical for drug discovery and repositioning, as it reveals potential therapeutic uses of existing drugs, accelerating development and reducing costs. However, most existing models focus only on direct similarity in homogeneous graphs, failing to exploit the rich similarity in heterogeneous graphs. To address this gap, inspired by real-world social interaction behaviors, we propose SOC-DGL, which comprises two specialized modules: the Affinity-Driven Graph Learning (ADGL) module, learning global similarity through an affinity-enhanced drug-target graph, and the Equilibrium-Driven Graph Learning (EDGL) module, capturing higher-order similarity by amplifying the influence of even-hop neighbors using an even-polynomial graph filter based on balance theory. This dual approach enables SOC-DGL to effectively capture similarity information across multiple interaction scales within affinity and association matrices. To address the issue of imbalance in DTI datasets, we propose an adjustable imbalance loss function that adjusts the weight of negative samples by the parameter. Extensive experiments on four benchmark datasets demonstrate that SOC-DGL consistently outperforms existing state-of-the-art methods across both balanced and imbalanced scenarios. Moreover, SOC-DGL successfully predicts the top 9 drugs known to bind ABL1, and further analyzed the 10th drug, which has not been experimentally confirmed to interact with ABL1, providing supporting evidence for its potential binding.

Kai-Fu Yang, Yong-Jie Li

Visual attention plays a critical role when our visual system executes active visual tasks by interacting with the physical scene. However, how to encode the visual object relationship in the psychological world of our brain deserves to be explored. In the field of computer vision, predicting visual fixations or scanpaths is a usual way to explore the visual attention and behaviors of human observers when viewing a scene. Most existing methods encode visual attention using individual fixations or scanpaths based on the raw gaze shift data collected from human observers. This may not capture the common attention pattern well, because without considering the semantic information of the viewed scene, raw gaze shift data alone contain high inter- and intra-observer variability. To address this issue, we propose a new attention representation, called Attention Graph, to simultaneously code the visual saliency and scanpath in a graph-based representation and better reveal the common attention behavior of human observers. In the attention graph, the semantic-based scanpath is defined by the path on the graph, while saliency of objects can be obtained by computing fixation density on each node. Systemic experiments demonstrate that the proposed attention graph combined with our new evaluation metrics provides a better benchmark for evaluating attention prediction methods. Meanwhile, extra experiments demonstrate the promising potentials of the proposed attention graph in assessing human cognitive states, such as autism spectrum disorder screening and age classification.

Shaobing Gao, Yongjie Li

Color constancy (CC) is an important ability of the human visual system to stably perceive the colors of objects despite considerable changes in the color of the light illuminating them. While increasing evidence from the field of neuroscience supports that multiple levels of the visual system contribute to the realization of CC, how the primary visual cortex (V1) plays role in CC is not fully resolved. In specific, double-opponent (DO) neurons in V1 have been thought to contribute to realizing a degree of CC, but the computational mechanism is not clear. We build an electrophysiologically based V1 neural model to learn the color of the light source from a natural image dataset with the ground truth illuminants as the labels. Based on the qualitative and quantitative analysis of the responsive properties of the learned model neurons, we found that both the spatial structures and color weights of the receptive fields of the learned model neurons are quite similar to those of the simple and DO neurons recorded in V1. Computationally, DO cells perform more robustly than the simple cells in V1 for illuminant prediction. Therefore, this work provides computational evidence supporting that V1 DO neurons serve to realize color constancy by encoding the illuminant,which is contradictory to the common hypothesis that V1 contributes to CC by discounting the illuminant using its DO cells. This evidence is expected to not only help resolve the visual mechanisms of CC, but also provide inspiration to develop more effective computer vision models.

Xi Lin, Shixuan Zhao, Xinxu Wei et al.

3D microscopic cerebrovascular images are characterized by their high resolution, presenting significant annotation challenges, large data volumes, and intricate variations in detail. Together, these factors make achieving high-quality, efficient whole-brain segmentation particularly demanding. In this paper, we propose a novel Vessel-Pattern-Based Semi-Supervised Distillation pipeline (VpbSD) to address the challenges of 3D microscopic cerebrovascular segmentation. This pipeline initially constructs a vessel-pattern codebook that captures diverse vascular structures from unlabeled data during the teacher model's pretraining phase. In the knowledge distillation stage, the codebook facilitates the transfer of rich knowledge from a heterogeneous teacher model to a student model, while the semi-supervised approach further enhances the student model's exposure to diverse learning samples. Experimental results on real-world data, including comparisons with state-of-the-art methods and ablation studies, demonstrate that our pipeline and its individual components effectively address the challenges inherent in microscopic cerebrovascular segmentation.

Wang-Wang Yu, Kai-Fu Yang, Xiangrui Hu et al.

The task of macro- and micro-expression spotting aims to precisely localize and categorize temporal expression instances within untrimmed videos. Given the sparse distribution and varying durations of expressions, existing anchor-based methods often represent instances by encoding their deviations from predefined anchors. Additionally, these methods typically slice the untrimmed videos into fixed-length sliding windows. However, anchor-based encoding often fails to capture all training intervals, and slicing the original video as sliding windows can result in valuable training intervals being discarded. To overcome these limitations, we introduce PESFormer, a simple yet effective model based on the vision transformer architecture to achieve point-to-interval expression spotting. PESFormer employs a direct timestamp encoding (DTE) approach to replace anchors, enabling binary classification of each timestamp instead of optimizing entire ground truths. Thus, all training intervals are retained in the form of discrete timestamps. To maximize the utilization of training intervals, we enhance the preprocessing process by replacing the short videos produced through the sliding window method.Instead, we implement a strategy that involves zero-padding the untrimmed training videos to create uniform, longer videos of a predetermined duration. This operation efficiently preserves the original training intervals and eliminates video slice enhancement.Extensive qualitative and quantitative evaluations on three datasets -- CAS(ME)^2, CAS(ME)^3 and SAMM-LV -- demonstrate that our PESFormer outperforms existing techniques, achieving the best performance.

Wang-Wang Yu, Kai-Fu Yang, Hong-Mei Yan et al.

Most micro- and macro-expression spotting methods in untrimmed videos suffer from the burden of video-wise collection and frame-wise annotation. Weakly-supervised expression spotting (WES) based on video-level labels can potentially mitigate the complexity of frame-level annotation while achieving fine-grained frame-level spotting. However, we argue that existing weakly-supervised methods are based on multiple instance learning (MIL) involving inter-modality, inter-sample, and inter-task gaps. The inter-sample gap is primarily from the sample distribution and duration. Therefore, we propose a novel and simple WES framework, MC-WES, using multi-consistency collaborative mechanisms that include modal-level saliency, video-level distribution, label-level duration and segment-level feature consistency strategies to implement fine frame-level spotting with only video-level labels to alleviate the above gaps and merge prior knowledge. The modal-level saliency consistency strategy focuses on capturing key correlations between raw images and optical flow. The video-level distribution consistency strategy utilizes the difference of sparsity in temporal distribution. The label-level duration consistency strategy exploits the difference in the duration of facial muscles. The segment-level feature consistency strategy emphasizes that features under the same labels maintain similarity. Experimental results on three challenging datasets -- CAS(ME)$^2$, CAS(ME)$^3$, and SAMM-LV -- demonstrate that MC-WES is comparable to state-of-the-art fully-supervised methods.

Yijun Cao, Xianshi Zhang, Fuya Luo et al.

Recent visual odometry (VO) methods incorporating geometric algorithm into deep-learning architecture have shown outstanding performance on the challenging monocular VO task. Despite encouraging results are shown, previous methods ignore the requirement of generalization capability under noisy environment and various scenes. To address this challenging issue, this work first proposes a novel optical flow network (PANet). Compared with previous methods that predict optical flow as a direct regression task, our PANet computes optical flow by predicting it into the discrete position space with optical flow probability volume, and then converting it to optical flow. Next, we improve the bundle adjustment module to fit the self-supervised training pipeline by introducing multiple sampling, ego-motion initialization, dynamic damping factor adjustment, and Jacobi matrix weighting. In addition, a novel normalized photometric loss function is advanced to improve the depth estimation accuracy. The experiments show that the proposed system not only achieves comparable performance with other state-of-the-art self-supervised learning-based methods on the KITTI dataset, but also significantly improves the generalization capability compared with geometry-based, learning-based and hybrid VO systems on the noisy KITTI and the challenging outdoor (KAIST) scenes.

Xinxu Wei, Xianshi Zhang, Shisen Wang et al.

Low-light image enhancement is a challenging low-level computer vision task because after we enhance the brightness of the image, we have to deal with amplified noise, color distortion, detail loss, blurred edges, shadow blocks and halo artifacts. In this paper, we propose a Two-Stage Network with Channel Attention (denoted as TSN-CA) to enhance the brightness of the low-light image and restore the enhanced images from various kinds of degradation. In the first stage, we enhance the brightness of the low-light image in HSV space and use the information of H and S channels to help the recovery of details in V channel. In the second stage, we integrate Channel Attention (CA) mechanism into the skip connection of U-Net in order to restore the brightness-enhanced image from severe kinds of degradation in RGB space. We train and evaluate the performance of our proposed model on the LOL real-world and synthetic datasets. In addition, we test our model on several other commonly used datasets without Ground-Truth. We conduct extensive experiments to demonstrate that our method achieves excellent effect on brightness enhancement as well as denoising, details preservation and halo artifacts elimination. Our method outperforms many other state-of-the-art methods qualitatively and quantitatively.

Xinxu Wei, Xianshi Zhang, Shisen Wang et al.

Images obtained in real-world low-light conditions are not only low in brightness, but they also suffer from many other types of degradation, such as color distortion, unknown noise, detail loss and halo artifacts. In this paper, we propose a Degradation-Aware Deep Retinex Network (denoted as DA-DRN) for low-light image enhancement and tackle the above degradation. Based on Retinex Theory, the decomposition net in our model can decompose low-light images into reflectance and illumination maps and deal with the degradation in the reflectance during the decomposition phase directly. We propose a Degradation-Aware Module (DA Module) which can guide the training process of the decomposer and enable the decomposer to be a restorer during the training phase without additional computational cost in the test phase. DA Module can achieve the purpose of noise removal while preserving detail information into the illumination map as well as tackle color distortion and halo artifacts. We introduce Perceptual Loss to train the enhancement network to generate the brightness-improved illumination maps which are more consistent with human visual perception. We train and evaluate the performance of our proposed model over the LOL real-world and LOL synthetic datasets, and we also test our model over several other frequently used datasets without Ground-Truth (LIME, DICM, MEF and NPE datasets). We conduct extensive experiments to demonstrate that our approach achieves a promising effect with good rubustness and generalization and outperforms many other state-of-the-art methods qualitatively and quantitatively. Our method only takes 7 ms to process an image with 600x400 resolution on a TITAN Xp GPU.

Peng Peng, Yong-Jie Li

Salient object detection (SOD) has been well studied in recent years, especially using deep neural networks. However, SOD with RGB and RGB-D images is usually treated as two different tasks with different network structures that need to be designed specifically. In this paper, we proposed a unified and efficient structure with a cross-attention context extraction (CRACE) module to address both tasks of SOD efficiently. The proposed CRACE module receives and appropriately fuses two (for RGB SOD) or three (for RGB-D SOD) inputs. The simple unified feature pyramid network (FPN)-like structure with CRACE modules conveys and refines the results under the multi-level supervisions of saliency and boundaries. The proposed structure is simple yet effective; the rich context information of RGB and depth can be appropriately extracted and fused by the proposed structure efficiently. Experimental results show that our method outperforms other state-of-the-art methods in both RGB and RGB-D SOD tasks on various datasets and in terms of most metrics.

Kai-Fu Yang, Wen-Wen Jiang, Teng-Fei Zhan et al.

Visual search is an important strategy of the human visual system for fast scene perception. The guided search theory suggests that the global layout or other top-down sources of scenes play a crucial role in guiding object searching. In order to verify the specific roles of scene layout and regional cues in guiding visual attention, we executed a psychophysical experiment to record the human fixations on line drawings of natural scenes with an eye-tracking system in this work. We collected the human fixations of ten subjects from 498 natural images and of another ten subjects from the corresponding 996 human-marked line drawings of boundaries (two boundary maps per image) under free-viewing condition. The experimental results show that with the absence of some basic features like color and luminance, the distribution of the fixations on the line drawings has a high correlation with that on the natural images. Moreover, compared to the basic cues of regions, subjects pay more attention to the closed regions of line drawings which are usually related to the dominant objects of the scenes. Finally, we built a computational model to demonstrate that the fixation information on the line drawings can be used to significantly improve the performances of classical bottom-up models for fixation prediction in natural scenes. These results support that Gestalt features and scene layout are important cues for guiding fast visual object searching.

Shao-Bing Gao, Ming Zhang, Chao-Yi Li et al.

It is an ill-posed problem to recover the true scene colors from a color biased image by discounting the effects of scene illuminant and camera spectral sensitivity (CSS) at the same time. Most color constancy (CC) models have been designed to first estimate the illuminant color, which is then removed from the color biased image to obtain an image taken under white light, without the explicit consideration of CSS effect on CC. This paper first studies the CSS effect on illuminant estimation arising in the inter-dataset-based CC (inter-CC), i.e., training a CC model on one dataset and then testing on another dataset captured by a distinct CSS. We show the clear degradation of existing CC models for inter-CC application. Then a simple way is proposed to overcome such degradation by first learning quickly a transform matrix between the two distinct CSSs (CSS-1 and CSS-2). The learned matrix is then used to convert the data (including the illuminant ground truth and the color biased images) rendered under CSS-1 into CSS-2, and then train and apply the CC model on the color biased images under CSS-2, without the need of burdensome acquiring of training set under CSS-2. Extensive experiments on synthetic and real images show that our method can clearly improve the inter-CC performance for traditional CC algorithms. We suggest that by taking the CSS effect into account, it is more likely to obtain the truly color constant images invariant to the changes of both illuminant and camera sensors.

Teng Qiu, Yongjie Li

Most density-based clustering methods largely rely on how well the underlying density is estimated. However, density estimation itself is also a challenging problem, especially the determination of the kernel bandwidth. A large bandwidth could lead to the over-smoothed density estimation in which the number of density peaks could be less than the true clusters, while a small bandwidth could lead to the under-smoothed density estimation in which spurious density peaks, or called the "ripple noise", would be generated in the estimated density. In this paper, we propose a density-based hierarchical clustering method, called the Deep Nearest Neighbor Descent (D-NND), which could learn the underlying density structure layer by layer and capture the cluster structure at the same time. The over-smoothed density estimation could be largely avoided and the negative effect of the under-estimated cases could be also largely reduced. Overall, D-NND presents not only the strong capability of discovering the underlying cluster structure but also the remarkable reliability due to its insensitivity to parameters.

Teng Qiu, Yongjie Li

Previously in 2014, we proposed the Nearest Descent (ND) method, capable of generating an efficient Graph, called the in-tree (IT). Due to some beautiful and effective features, this IT structure proves well suited for data clustering. Although there exist some redundant edges in IT, they usually have salient features and thus it is not hard to remove them. Subsequently, in order to prevent the seemingly redundant edges from occurring, we proposed the Nearest Neighbor Descent (NND) by adding the "Neighborhood" constraint on ND. Consequently, clusters automatically emerged, without the additional requirement of removing the redundant edges. However, NND proved still not perfect, since it brought in a new yet worse problem, the "over-partitioning" problem. Now, in this paper, we propose a method, called the Hierarchical Nearest Neighbor Descent (H-NND), which overcomes the over-partitioning problem of NND via using the hierarchical strategy. Specifically, H-NND uses ND to effectively merge the over-segmented sub-graphs or clusters that NND produces. Like ND, H-NND also generates the IT structure, in which the redundant edges once again appear. This seemingly comes back to the situation that ND faces. However, compared with ND, the redundant edges in the IT structure generated by H-NND generally become more salient, thus being much easier and more reliable to be identified even by the simplest edge-removing method which takes the edge length as the only measure. In other words, the IT structure constructed by H-NND becomes more fitted for data clustering. We prove this on several clustering datasets of varying shapes, dimensions and attributes. Besides, compared with ND, H-NND generally takes less computation time to construct the IT data structure for the input data.

Teng Qiu, Yongjie Li

Previously, we proposed a physically-inspired method to construct data points into an effective in-tree (IT) structure, in which the underlying cluster structure in the dataset is well revealed. Although there are some edges in the IT structure requiring to be removed, such undesired edges are generally distinguishable from other edges and thus are easy to be determined. For instance, when the IT structures for the 2-dimensional (2D) datasets are graphically presented, those undesired edges can be easily spotted and interactively determined. However, in practice, there are many datasets that do not lie in the 2D Euclidean space, thus their IT structures cannot be graphically presented. But if we can effectively map those IT structures into a visualized space in which the salient features of those undesired edges are preserved, then the undesired edges in the IT structures can still be visually determined in a visualization environment. Previously, this purpose was reached by our method called IT-map. The outstanding advantage of IT-map is that clusters can still be found even with the so-called crowding problem in the embedding. In this paper, we propose another method, called IT-Dendrogram, to achieve the same goal through an effective combination of the IT structure and the single link hierarchical clustering (SLHC) method. Like IT-map, IT-Dendrogram can also effectively represent the IT structures in a visualization environment, whereas using another form, called the Dendrogram. IT-Dendrogram can serve as another visualization method to determine the undesired edges in the IT structures and thus benefit the IT-based clustering analysis. This was demonstrated on several datasets with different shapes, dimensions, and attributes. Unlike IT-map, IT-Dendrogram can always avoid the crowding problem, which could help users make more reliable cluster analysis in certain problems.

Teng Qiu, Yongjie Li

Previously, we proposed a physically inspired rule to organize the data points in a sparse yet effective structure, called the in-tree (IT) graph, which is able to capture a wide class of underlying cluster structures in the datasets, especially for the density-based datasets. Although there are some redundant edges or lines between clusters requiring to be removed by computer, this IT graph has a big advantage compared with the k-nearest-neighborhood (k-NN) or the minimal spanning tree (MST) graph, in that the redundant edges in the IT graph are much more distinguishable and thus can be easily determined by several methods previously proposed by us. In this paper, we propose a general framework to re-construct the IT graph, based on an initial neighborhood graph, such as the k-NN or MST, etc, and the corresponding graph distances. For this general framework, our previous way of constructing the IT graph turns out to be a special case of it. This general framework 1) can make the IT graph capture a wider class of underlying cluster structures in the datasets, especially for the manifolds, and 2) should be more effective to cluster the sparse or graph-based datasets.

Teng Qiu, Yongjie Li

In our physically inspired in-tree (IT) based clustering algorithm and the series after it, there is only one free parameter involved in computing the potential value of each point. In this work, based on the Delaunay Triangulation or its dual Voronoi tessellation, we propose a nonparametric process to compute potential values by the local information. This computation, though nonparametric, is relatively very rough, and consequently, many local extreme points will be generated. However, unlike those gradient-based methods, our IT-based methods are generally insensitive to those local extremes. This positively demonstrates the superiority of these parametric (previous) and nonparametric (in this work) IT-based methods.

Teng Qiu, Yongjie Li

In our previous works, we proposed a physically-inspired rule to organize the data points into an in-tree (IT) structure, in which some undesired edges are allowed to occur. By removing those undesired or redundant edges, this IT structure is divided into several separate parts, each representing one cluster. In this work, we seek to prevent the undesired edges from arising at the source. Before using the physically-inspired rule, data points are at first organized into a proximity graph which restricts each point to select the optimal directed neighbor just among its neighbors. Consequently, separated in-trees or clusters automatically arise, without redundant edges requiring to be removed.

Teng Qiu, Yongjie Li

Scientists in many fields have the common and basic need of dimensionality reduction: visualizing the underlying structure of the massive multivariate data in a low-dimensional space. However, many dimensionality reduction methods confront the so-called "crowding problem" that clusters tend to overlap with each other in the embedding. Previously, researchers expect to avoid that problem and seek to make clusters maximally separated in the embedding. However, the proposed in-tree (IT) based method, called IT-map, allows clusters in the embedding to be locally overlapped, while seeking to make them distinguishable by some small yet key parts. IT-map provides a simple, effective and novel solution to cluster-preserving mapping, which makes it possible to cluster the original data points interactively and thus should be of general meaning in science and engineering.

Teng Qiu, Yongjie Li

A recently proposed clustering method, called the Nearest Descent (ND), can organize the whole dataset into a sparsely connected graph, called the In-tree. This ND-based Intree structure proves able to reveal the clustering structure underlying the dataset, except one imperfect place, that is, there are some undesired edges in this In-tree which require to be removed. Here, we propose an effective way to automatically remove the undesired edges in In-tree via an effective combination of the In-tree structure with affinity propagation (AP). The key for the combination is to add edges between the reachable nodes in In-tree before using AP to remove the undesired edges. The experiments on both synthetic and real datasets demonstrate the effectiveness of the proposed method.

Teng Qiu, Kaifu Yang, Chaoyi Li et al.

In this paper, we propose a physically inspired graph-theoretical clustering method, which first makes the data points organized into an attractive graph, called In-Tree, via a physically inspired rule, called Nearest Descent (ND). In particular, the rule of ND works to select the nearest node in the descending direction of potential as the parent node of each node, which is in essence different from the classical Gradient Descent or Steepest Descent. The constructed In-Tree proves a very good candidate for clustering due to its particular features and properties. In the In-Tree, the original clustering problem is reduced to a problem of removing a very few of undesired edges from this graph. Pleasingly, the undesired edges in In-Tree are so distinguishable that they can be easily determined in either automatic or interactive way, which is in stark contrast to the cases in the widely used Minimal Spanning Tree and k-nearest-neighbor graph. The cluster number in the proposed method can be easily determined based on some intermediate plots, and the cluster assignment for each node is easily made by quickly searching its root node in each sub-graph (also an In-Tree). The proposed method is extensively evaluated on both synthetic and real-world datasets. Overall, the proposed clustering method is a density-based one, but shows significant differences and advantages in comparison to the traditional ones. The proposed method is simple yet efficient and reliable, and is applicable to various datasets with diverse shapes, attributes and any high dimensionality