Ronghua Liang

Guoyu Yang, Jie Lei, Zhikuan Zhu et al.

Multi-scale features are of great importance in encoding objects with scale variance in object detection tasks. A common strategy for multi-scale feature extraction is adopting the classic top-down and bottom-up feature pyramid networks. However, these approaches suffer from the loss or degradation of feature information, impairing the fusion effect of non-adjacent levels. This paper proposes an asymptotic feature pyramid network (AFPN) to support direct interaction at non-adjacent levels. AFPN is initiated by fusing two adjacent low-level features and asymptotically incorporates higher-level features into the fusion process. In this way, the larger semantic gap between non-adjacent levels can be avoided. Given the potential for multi-object information conflicts to arise during feature fusion at each spatial location, adaptive spatial fusion operation is further utilized to mitigate these inconsistencies. We incorporate the proposed AFPN into both two-stage and one-stage object detection frameworks and evaluate with the MS-COCO 2017 validation and test datasets. Experimental evaluation shows that our method achieves more competitive results than other state-of-the-art feature pyramid networks. The code is available at \href{https://github.com/gyyang23/AFPN}{https://github.com/gyyang23/AFPN}.

Xing Zhao, Haoran Liang, Peipei Li et al.

Previous methods based on 3DCNN, convLSTM, or optical flow have achieved great success in video salient object detection (VSOD). However, they still suffer from high computational costs or poor quality of the generated saliency maps. To solve these problems, we design a space-time memory (STM)-based network, which extracts useful temporal information of the current frame from adjacent frames as the temporal branch of VSOD. Furthermore, previous methods only considered single-frame prediction without temporal association. As a result, the model may not focus on the temporal information sufficiently. Thus, we initially introduce object motion prediction between inter-frame into VSOD. Our model follows standard encoder--decoder architecture. In the encoding stage, we generate high-level temporal features by using high-level features from the current and its adjacent frames. This approach is more efficient than the optical flow-based methods. In the decoding stage, we propose an effective fusion strategy for spatial and temporal branches. The semantic information of the high-level features is used to fuse the object details in the low-level features, and then the spatiotemporal features are obtained step by step to reconstruct the saliency maps. Moreover, inspired by the boundary supervision commonly used in image salient object detection (ISOD), we design a motion-aware loss for predicting object boundary motion and simultaneously perform multitask learning for VSOD and object motion prediction, which can further facilitate the model to extract spatiotemporal features accurately and maintain the object integrity. Extensive experiments on several datasets demonstrated the effectiveness of our method and can achieve state-of-the-art metrics on some datasets. The proposed model does not require optical flow or other preprocessing, and can reach a speed of nearly 100 FPS during inference.

Liang Xie, Yibo Yang, Wenxiao Wang et al.

Compared to 2D images, 3D point clouds are much more sensitive to rotations. We expect the point features describing certain patterns to keep invariant to the rotation transformation. There are many recent SOTA works dedicated to rotation-invariant learning for 3D point clouds. However, current rotation-invariant methods lack generalizability on the point clouds in the open scenes due to the reliance on the global distribution, \ie the global scene and backgrounds. Considering that the output activation is a function of the pattern and its orientation, we need to eliminate the effect of the orientation.In this paper, inspired by the idea that the network weights can be considered a set of points distributed in the same 3D space as the input points, we propose Weight-Feature Alignment (WFA) to construct a local Invariant Reference Frame (IRF) via aligning the features with the principal axes of the network weights. Our WFA algorithm provides a general solution for the point clouds of all scenes. WFA ensures the model achieves the target that the response activity is a necessary and sufficient condition of the pattern matching degree. Practically, we perform experiments on the point clouds of both single objects and open large-range scenes. The results suggest that our method almost bridges the gap between rotation invariance learning and normal methods.

Yunchao Wang, Guodao Sun, Zihang Fu et al.

With the advancement of natural language generation (NLG) technologies, creative story generation systems have gained increasing attention. However, current systems often fail to accurately translate user intent into satisfactory story outputs due to a lack of fine-grained control and unclear input specifications, limiting their applicability. To address this, we propose TaleFrame, a system that combines large language models (LLMs) with human-computer interaction (HCI) to generate stories through structured information, enabling precise control over the generation process. The innovation of TaleFrame lies in decomposing the story structure into four basic units: entities, events, relationships, and story outline. We leverage the Tinystories dataset, parsing and constructing a preference dataset consisting of 9,851 JSON-formatted entries, which is then used to fine-tune a local Llama model. By employing this JSON2Story approach, structured data is transformed into coherent stories. TaleFrame also offers an intuitive interface that supports users in creating and editing entities and events and generates stories through the structured framework. Users can control these units through simple interactions (e.g., drag-and-drop, attach, and connect), thus influencing the details and progression of the story. The generated stories can be evaluated across seven dimensions (e.g., creativity, structural integrity), with the system providing suggestions for refinement based on these evaluations. Users can iteratively adjust the story until a satisfactory result is achieved. Finally, we conduct quantitative evaluation and user studies that demonstrate the usefulness of TaleFrame. Dataset available at https://huggingface.co/datasets/guodaosun/tale-frame.

Binwei Xu, Haoran Liang, Weihua Gong et al.

Fully supervised salient object detection (SOD) methods have made considerable progress in performance, yet these models rely heavily on expensive pixel-wise labels. Recently, to achieve a trade-off between labeling burden and performance, scribble-based SOD methods have attracted increasing attention. Previous scribble-based models directly implement the SOD task only based on SOD training data with limited information, it is extremely difficult for them to understand the image and further achieve a superior SOD task. In this paper, we propose a simple yet effective framework guided by general visual representations with rich contextual semantic knowledge for scribble-based SOD. These general visual representations are generated by self-supervised learning based on large-scale unlabeled datasets. Our framework consists of a task-related encoder, a general visual module, and an information integration module to efficiently combine the general visual representations with task-related features to perform the SOD task based on understanding the contextual connections of images. Meanwhile, we propose a novel global semantic affinity loss to guide the model to perceive the global structure of the salient objects. Experimental results on five public benchmark datasets demonstrate that our method, which only utilizes scribble annotations without introducing any extra label, outperforms the state-of-the-art weakly supervised SOD methods. Specifically, it outperforms the previous best scribble-based method on all datasets with an average gain of 5.5% for max f-measure, 5.8% for mean f-measure, 24% for MAE, and 3.1% for E-measure. Moreover, our method achieves comparable or even superior performance to the state-of-the-art fully supervised models.

Binwei Xu, Haoran Liang, Ronghua Liang et al.

Fully supervised salient object detection (SOD) has made considerable progress based on expensive and time-consuming data with pixel-wise annotations. Recently, to relieve the labeling burden while maintaining performance, some scribble-based SOD methods have been proposed. However, learning precise boundary details from scribble annotations that lack edge information is still difficult. In this paper, we propose to learn precise boundaries from our designed synthetic images and labels without introducing any extra auxiliary data. The synthetic image creates boundary information by inserting synthetic concave regions that simulate the real concave regions of salient objects. Furthermore, we propose a novel self-consistent framework that consists of a global integral branch (GIB) and a boundary-aware branch (BAB) to train a saliency detector. GIB aims to identify integral salient objects, whose input is the original image. BAB aims to help predict accurate boundaries, whose input is the synthetic image. These two branches are connected through a self-consistent loss to guide the saliency detector to predict precise boundaries while identifying salient objects. Experimental results on five benchmarks demonstrate that our method outperforms the state-of-the-art weakly supervised SOD methods and further narrows the gap with the fully supervised methods.

Sujia Zhu, Yue Shen, Zihao Zhu et al.

Identifying causality behind complex systems plays a significant role in different domains, such as decision making, policy implementations, and management recommendations. However, existing causality studies on temporal event sequences data mainly focus on individual causal discovery, which is incapable of exploiting combined causality. To fill the absence of combined causes discovery on temporal event sequence data,eliminating and recruiting principles are defined to balance the effectiveness and controllability on cause combinations. We also leverage the Granger causality algorithm based on the reactive point processes to describe impelling or inhibiting behavior patterns among entities. In addition, we design an informative and aesthetic visual metaphor of "electrocircuit" to encode aggregated causality for ensuring our causality visualization is non-overlapping and non-intersecting. Diverse sorting strategies and aggregation layout are also embedded into our parallel-based, directed and weighted hypergraph for illustrating combined causality. Our developed combined causality visual analysis system can help users effectively explore combined causes as well as an individual cause. This interactive system supports multi-level causality exploration with diverse ordering strategies and a focus and context technique to help users obtain different levels of information abstraction. The usefulness and effectiveness of the system are further evaluated by conducting a pilot user study and two case studies on event sequence data.

Pan Liang, Danwei Ye, Zihao Zhu et al.

Large language models (LLMs), such as ChatGPT, have demonstrated outstanding performance in various fields, particularly in natural language understanding and generation tasks. In complex application scenarios, users tend to engage in multi-turn conversations with ChatGPT to keep contextual information and obtain comprehensive responses. However, human forgetting and model contextual forgetting remain prominent issues in multi-turn conversation scenarios, which challenge the users' conversation comprehension and contextual continuity for ChatGPT. To address these challenges, we propose an interactive conversation visualization system called C5, which includes Global View, Topic View, and Context-associated Q\&A View. The Global View uses the GitLog diagram metaphor to represent the conversation structure, presenting the trend of conversation evolution and supporting the exploration of locally salient features. The Topic View is designed to display all the question and answer nodes and their relationships within a topic using the structure of a knowledge graph, thereby display the relevance and evolution of conversations. The Context-associated Q\&A View consists of three linked views, which allow users to explore individual conversations deeply while providing specific contextual information when posing questions. The usefulness and effectiveness of C5 were evaluated through a case study and a user study.

Haohao Sun, Yilong Zhang, Peng Chen et al.

As a non-invasive optical imaging technique, optical coherence tomography (OCT) has proven promising for automatic fingerprint recognition system (AFRS) applications. Diverse approaches have been proposed for OCT-based fingerprint presentation attack detection (PAD). However, considering the complexity and variety of PA samples, it is extremely challenging to increase the generalization ability with the limited PA dataset. To solve the challenge, this paper presents a novel supervised learning-based PAD method, denoted as ISAPAD, which applies prior knowledge to guide network training and enhance the generalization ability. The proposed dual-branch architecture can not only learns global features from the OCT image, but also concentrate on layered structure feature which comes from the internal structure attention module (ISAM). The simple yet effective ISAM enables the proposed network to obtain layered segmentation features belonging only to Bonafide from noisy OCT volume data directly. Combined with effective training strategies and PAD score generation rules, ISAPAD obtains optimal PAD performance in limited training data. Domain generalization experiments and visualization analysis validate the effectiveness of the proposed method for OCT PAD.

Binwei Xu, Haoran Liang, Wentian Ni et al.

Recent deep learning-based video salient object detection (VSOD) has achieved some breakthrough, but these methods rely on expensive annotated videos with pixel-wise annotations, weak annotations, or part of the pixel-wise annotations. In this paper, based on the similarities and the differences between VSOD and image salient object detection (SOD), we propose a novel VSOD method via a progressive framework that locates and segments salient objects in sequence without utilizing any video annotation. To use the knowledge learned in the SOD dataset for VSOD efficiently, we introduce dynamic saliency to compensate for the lack of motion information of SOD during the locating process but retain the same fine segmenting process. Specifically, an algorithm for generating spatiotemporal location labels, which consists of generating high-saliency location labels and tracking salient objects in adjacent frames, is proposed. Based on these location labels, a two-stream locating network that introduces an optical flow branch for video salient object locating is presented. Although our method does not require labeled video at all, the experimental results on five public benchmarks of DAVIS, FBMS, ViSal, VOS, and DAVSOD demonstrate that our proposed method is competitive with fully supervised methods and outperforms the state-of-the-art weakly and unsupervised methods.

Zihang Fu, Yunchao Wang, Chenyu Huang et al.

Infographics are widely used to convey complex information, yet their affective dimensions remain underexplored due to the scarcity of data resources. We introduce a 3.5k-sample affect-annotated InfoAffect dataset, which combines textual content with real-world infographics. We first collect the raw data from six domains and aligned them via preprocessing, the accompanied-text-priority method, and three strategies to guarantee the quality and compliance. After that we construct an affect table and use it to constrain annotation. Five state-of-the-art multimodal large language models (MLLMs) then analyze both modalities, and their outputs are fused with Reciprocal Rank Fusion (RRF) algorithm to yield robust affects and confidences. We conducted a user study with two experiments to validate usability and assess InfoAffect dataset using the Composite Affect Consistency Index (CACI), achieving an overall score of 0.986, which indicates high accuracy.

Baofeng Chang, Sujia Zhu, Qi Jiang et al.

Dynamic graph visualization attracts researchers' concentration as it represents time-varying relationships between entities in multiple domains (e.g., social media analysis, academic cooperation analysis, team sports analysis). Integrating visual analytic methods is consequential in presenting, comparing, and reviewing dynamic graphs. Even though dynamic graph visualization is developed for many years, how to effectively visualize large-scale and time-intensive dynamic graph data with subtle changes is still challenging for researchers. To provide an effective analysis method for this type of dynamic graph data, we propose a snapshot generation algorithm involving Human-In-Loop to help users divide the dynamic graphs into multi-granularity and hierarchical snapshots for further analysis. In addition, we design a visual analysis prototype system (DGSVis) to assist users in accessing the dynamic graph insights effectively. DGSVis integrates a graphical operation interface to help users generate snapshots visually and interactively. It is equipped with the overview and details for visualizing hierarchical snapshots of the dynamic graph data. To illustrate the usability and efficiency of our proposed methods for this type of dynamic graph data, we introduce two case studies based on basketball player networks in a competition. In addition, we conduct an evaluation and receive exciting feedback from experienced visualization experts.

Guowei Zhong, Ruohong Huan, Mingzhen Wu et al.

Recent advancements in Multimodal Emotion Recognition (MER) face challenges in addressing both modality missing and Out-Of-Distribution (OOD) data simultaneously. Existing methods often rely on specific models or introduce excessive parameters, which limits their practicality. To address these issues, we propose a novel robust MER framework, Causal Inference Distiller (CIDer), and introduce a new task, Random Modality Feature Missing (RMFM), to generalize the definition of modality missing. CIDer integrates two key components: a Model-Specific Self-Distillation (MSSD) module and a Model-Agnostic Causal Inference (MACI) module. MSSD enhances robustness under the RMFM task through a weight-sharing self-distillation approach applied across low-level features, attention maps, and high-level representations. Additionally, a Word-level Self-aligned Attention Module (WSAM) reduces computational complexity, while a Multimodal Composite Transformer (MCT) facilitates efficient multimodal fusion. To tackle OOD challenges, MACI employs a tailored causal graph to mitigate label and language biases using a Multimodal Causal Module (MCM) and fine-grained counterfactual texts. Notably, MACI can independently enhance OOD generalization with minimal additional parameters. Furthermore, we also introduce the new repartitioned MER OOD datasets. Experimental results demonstrate that CIDer achieves robust performance in both RMFM and OOD scenarios, with fewer parameters and faster training compared to state-of-the-art methods. The implementation of this work is publicly accessible at https://github.com/gw-zhong/CIDer.

Yiming Wu, Hangfei Li, Fangfang Wang et al.

In the domain of language-based fashion image retrieval, pinpointing the desired fashion item using both a reference image and its accompanying textual description is an intriguing challenge. Existing approaches lean heavily on static fusion techniques, intertwining image and text. Despite their commendable advancements, these approaches are still limited by a deficiency in flexibility. In response, we propose a Self-distilled Dynamic Fusion Network to compose the multi-granularity features dynamically by considering the consistency of routing path and modality-specific information simultaneously. Two new modules are included in our proposed method: (1) Dynamic Fusion Network with Modality Specific Routers. The dynamic network enables a flexible determination of the routing for each reference image and modification text, taking into account their distinct semantics and distributions. (2) Self Path Distillation Loss. A stable path decision for queries benefits the optimization of feature extraction as well as routing, and we approach this by progressively refine the path decision with previous path information. Extensive experiments demonstrate the effectiveness of our proposed model compared to existing methods.

Yiming Wu, Qihe Pan, Zhen Zhao et al.

In this paper, we delve into a new task known as small object editing (SOE), which focuses on text-based image inpainting within a constrained, small-sized area. Despite the remarkable success have been achieved by current image inpainting approaches, their application to the SOE task generally results in failure cases such as Object Missing, Text-Image Mismatch, and Distortion. These failures stem from the limited use of small-sized objects in training datasets and the downsampling operations employed by U-Net models, which hinders accurate generation. To overcome these challenges, we introduce a novel training-based approach, SOEDiff, aimed at enhancing the capability of baseline models like StableDiffusion in editing small-sized objects while minimizing training costs. Specifically, our method involves two key components: SO-LoRA, which efficiently fine-tunes low-rank matrices, and Cross-Scale Score Distillation loss, which leverages high-resolution predictions from the pre-trained teacher diffusion model. Our method presents significant improvements on the test dataset collected from MSCOCO and OpenImage, validating the effectiveness of our proposed method in small object editing. In particular, when comparing SOEDiff with SD-I model on the OpenImage-f dataset, we observe a 0.99 improvement in CLIP-Score and a reduction of 2.87 in FID.

Qihe Pan, Zhen Zhao, Zicheng Wang et al.

A plethora of text-guided image editing methods has recently been developed by leveraging the impressive capabilities of large-scale diffusion-based generative models especially Stable Diffusion. Despite the success of diffusion models in producing high-quality images, their application to small object generation has been limited due to difficulties in aligning cross-modal attention maps between text and these objects. Our approach offers a training-free method that significantly mitigates this alignment issue with local and global attention guidance , enhancing the model's ability to accurately render small objects in accordance with textual descriptions. We detail the methodology in our approach, emphasizing its divergence from traditional generation techniques and highlighting its advantages. What's more important is that we also provide~\textit{SOEBench} (Small Object Editing), a standardized benchmark for quantitatively evaluating text-based small object generation collected from \textit{MSCOCO} and \textit{OpenImage}. Preliminary results demonstrate the effectiveness of our method, showing marked improvements in the fidelity and accuracy of small object generation compared to existing models. This advancement not only contributes to the field of AI and computer vision but also opens up new possibilities for applications in various industries where precise image generation is critical. We will release our dataset on our project page: \href{https://soebench.github.io/}{https://soebench.github.io/}.

Jitong Liao, Yulu Gao, Shaofei Huang et al.

Cross-view object correspondence involves matching objects between egocentric (first-person) and exocentric (third-person) views. It is a critical yet challenging task for visual understanding. In this work, we propose the Dense Object Matching and Refinement (DOMR) framework to establish dense object correspondences across views. The framework centers around the Dense Object Matcher (DOM) module, which jointly models multiple objects. Unlike methods that directly match individual object masks to image features, DOM leverages both positional and semantic relationships among objects to find correspondences. DOM integrates a proposal generation module with a dense matching module that jointly encodes visual, spatial, and semantic cues, explicitly constructing inter-object relationships to achieve dense matching among objects. Furthermore, we combine DOM with a mask refinement head designed to improve the completeness and accuracy of the predicted masks, forming the complete DOMR framework. Extensive evaluations on the Ego-Exo4D benchmark demonstrate that our approach achieves state-of-the-art performance with a mean IoU of 49.7% on Ego$\to$Exo and 55.2% on Exo$\to$Ego. These results outperform those of previous methods by 5.8% and 4.3%, respectively, validating the effectiveness of our integrated approach for cross-view understanding.

Jiazhou Chen, Yanghui Xu, Shufang Lu et al.

We present a novel 3D instance segmentation framework for Multi-View Stereo (MVS) buildings in urban scenes. Unlike existing works focusing on semantic segmentation of urban scenes, the emphasis of this work lies in detecting and segmenting 3D building instances even if they are attached and embedded in a large and imprecise 3D surface model. Multi-view RGB images are first enhanced to RGBH images by adding a heightmap and are segmented to obtain all roof instances using a fine-tuned 2D instance segmentation neural network. Instance masks from different multi-view images are then clustered into global masks. Our mask clustering accounts for spatial occlusion and overlapping, which can eliminate segmentation ambiguities among multi-view images. Based on these global masks, 3D roof instances are segmented out by mask back-projections and extended to the entire building instances through a Markov random field optimization. A new dataset that contains instance-level annotation for both 3D urban scenes (roofs and buildings) and drone images (roofs) is provided. To the best of our knowledge, it is the first outdoor dataset dedicated to 3D instance segmentation with much more annotations of attached 3D buildings than existing datasets. Quantitative evaluations and ablation studies have shown the effectiveness of all major steps and the advantages of our multi-view framework over the orthophoto-based method.

Chaoqing Xu, Tyson Neuroth, Takanori Fujiwara et al.

Diffusion tensor imaging (DTI) has been used to study the effects of neurodegenerative diseases on neural pathways, which may lead to more reliable and early diagnosis of these diseases as well as a better understanding of how they affect the brain. We introduce an intelligent visual analytics system for studying patient groups based on their labeled DTI fiber tract data and corresponding statistics. The system's AI-augmented interface guides the user through an organized and holistic analysis space, including the statistical feature space, the physical space, and the space of patients over different groups. We use a custom machine learning pipeline to help narrow down this large analysis space, and then explore it pragmatically through a range of linked visualizations. We conduct several case studies using real data from the research database of Parkinson's Progression Markers Initiative.