YHYaping Huang

Yaping Huang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Yaping Huang has a total of 133 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Cognitive parsing network for action quality assessment

    by Junyang Li, Yi Tian, Keyi Huang, Yi Jin, Yaping Huang

  • Open Access

    Generative Edge Detection with Stable Diffusion

    by Caixia Zhou, Yaping Huang, Mochu Xiang, Jiahui Ren, Haibin Ling, Jing Zhang

    Edge detection is typically viewed as a pixel-level classification problem mainly addressed by discriminative methods. Recently, generative edge detection methods, especially those based on diffusion models, are initialized in the edge detection task. Despite great potential, the retraining of task-specific designed modules and multi-step denoising inference limits their broader applications. Upon closer investigation, we speculate that part of the reason is the under-exploration of the rich discriminative information encoded in extensively pre-trained large models (e.g., stable diffusion models). Thus motivated, we propose a novel approach, named Generative Edge Detector (GED), by fully utilizing the potential of the pre-trained stable diffusion model. Our model can be trained and inferred efficiently without a specific network design due to the rich high-level and low-level prior knowledge empowered by the pre-trained stable diffusion. Specifically, we propose to finetune the denoising U-Net and predict latent edge maps directly, by taking the latent image feature maps as input. Additionally, due to the subjectivity and ambiguity of the edges, we also incorporate the granularity of the edges into the denoising U-Net model as one of the conditions to achieve controllable and diverse predictions. Furthermore, we devise a granularity regularization to ensure the relative granularity relationship of the multiple predictions. We conduct extensive experiments on multiple datasets and achieve competitive performance (e.g., 0.870 and 0.880 in terms of ODS and OIS on the BSDS test dataset). We will release the source code of GED upon the publication of the work.

  • Camera Exposure Control via Pairwise Human Feedback Learning

    by Bo Ding, Yaping Huang, Junbo Liu, Yuan Xiao

  • Motion and Spatiotemporal Aggregation Network for Occlusion Edge Detection From Videos

    by Liangyu Chen, Mengyang Pu, Zhihao Liu, Xiaohui Hou, Yaping Huang, Rong Zhou, Haibin Ling

    Detecting occlusion edges from videos is a critical yet under-explored task, with recent works focusing on single-image occlusion edge detection while ignoring dynamic patterns in videos. In videos, occlusion edges typically occur when a moving object occludes either the background or another object, resulting in two types of occlusion edges: object-background (OB) edges that are characterized by appearance contrast and motion, and object-object (OO) edges that face ambiguity. Inspired by these observations, we propose a novel Motion and Spatio-Temporal Aggregated Network (MaSTAN) and treat the two edge types differently for more effectively detecting occlusion edges in videos. Specifically, we first extract spatial semantics and motion patterns from the videos and propose a novel Temporal Feature Propagation module (TFP) for temporal cue aggregation. Next, we put forward a Dual-branch Gated-attention Decoder (DG-Decoder) to generate edge-specific features for predicting the final occlusion edge maps. Extensive experiments on the OVIS-OE benchmark, the first large benchmark dedicated to video occlusion edge detection, demonstrate that MaSTAN achieves state-of-the-art performance, significantly advancing the capability of occlusion edge detection in video. The source code and benchmark will be made publicly available.

  • Open Access

    VL4Gaze: Unleashing Vision-Language Models for Gaze Following

    by Shijing Wang, Chaoqun Cui, Yaping Huang, Hyung Jin Chang, Yihua Cheng

    Human gaze provides essential cues for interpreting attention, intention, and social interaction in visual scenes, yet gaze understanding remains largely unexplored in current vision-language models (VLMs). While recent VLMs achieve strong scene-level reasoning across a range of visual tasks, there exists no benchmark that systematically evaluates or trains them for gaze interpretation, leaving open the question of whether gaze understanding can emerge from general-purpose vision-language pre-training. To address this gap, we introduce VL4Gaze, the first large-scale benchmark designed to investigate, evaluate, and unlock the potential of VLMs for gaze understanding. VL4Gaze contains 489K automatically generated question-answer pairs across 124K images and formulates gaze understanding as a unified VQA problem through four complementary tasks: (1) gaze object description, (2) gaze direction description, (3) gaze point location, and (4) ambiguous question recognition. We comprehensively evaluate both commercial and open-source VLMs under in-context learning and fine-tuning settings. The results show that even large-scale VLMs struggle to reliably infer gaze semantics and spatial localization without task-specific supervision. In contrast, training on VL4Gaze brings substantial and consistent improvements across all tasks, highlighting the importance of targeted multi-task supervision for developing gaze understanding capabilities in VLMs. We will release the dataset and code to support further research and development in this direction.

  • Open Access

    Differential Contrastive Training for Gaze Estimation

    by Lin Zhang, Yi Tian, Xiyun Wang, Wanru Xu, Yi Jin, Yaping Huang


  • ‘Disengage AND Integrate’: Personalized Causal Network for Gaze Estimation

    by Yi Tian, Xiyun Wang, Sihui Zhang, Wanru Xu, Yi Jin, Yaping Huang

    Gaze estimation task aims to predict a 3D gaze direction or a 2D gaze point given a face or eye image. To improve generalization of gaze estimation models to unseen new users, existing methods either disentangle personalized information of all subjects from their gaze features, or integrate unrefined personalized information into blended embeddings. Their methodologies are not rigorous whose performance is still unsatisfactory. In this paper, we put forward a comprehensive perspective named ‘Disengage AND Integrate’ to deal with personalized information, which elaborates that for specified users, their irrelevant personalized information should be discarded while relevant one should be considered. Accordingly, a novel Personalized Causal Network (PCNet) for generalizable gaze estimation has been proposed. The PCNet adopts a two-branch framework, which consists of a subject-deconfounded appearance sub-network (SdeANet) and a prototypical personalization sub-network (ProPNet). The SdeANet aims to explore causalities among facial images, gazes, and personalized information and extract a subject-invariant appearance-aware feature of each image by means of causal intervention. The ProPNet aims to characterize customized personalization-aware features of arbitrary users with the help of a prototype-based subject identification task. Furthermore, our whole PCNet is optimized in a hybrid episodic training paradigm, which further improve its adaptability to new users. Experiments on three challenging datasets over within-domain and cross-domain gaze estimation tasks demonstrate the effectiveness of our method.


  • Contour-Aware Multi-Expert Model for Ambiguous Medical Image Segmentation

    by Jiangnan Wang, Caixia Zhou, Yaping Huang

    Medical image segmentation is highly challenging due to the uncertainties caused by the inherent ambiguous regions and expert knowledge variations. Some recent works explore the uncertainties and produce multiple outputs to obtain more robust results. However, the quality of the boundary areas remains unsatisfactory. Unfortunately, the key differences among experts usually lie in these boundary areas, which are more critical in practical diagnosis. To tackle the above issues, different from previous pixel-wise segmentation approaches, we present a new perspective and formulate the task as a contour-based regression problem, and further propose a novel Contour-aware Multi-expert Segmentor, named ContourMS, which can provide diverse segmentation results with rich boundary details in a coarse-to-fine manner. Specifically, in the coarse stage, we use a SegmentNet to predict a region mask by leveraging the knowledge of multiple experts, and then the mask is converted to an initial contour shared by all experts. In the fine stage, we design a LatentNet to learn the expert-level latent space and a ContourNet to refine each expert contour, where the deformation guided by the expert style can gradually adjust the contour to match different annotations. Extensive experiments demonstrate that the proposed method can generate diverse segment variants and achieve competitive performance on multiple public multi-expert medical segmentation datasets.


  • Cost-Optimized Crowdsourcing for NLP via Worker Selection and Data Augmentation

    by Liner Yang, Yujie Wang, Zhixuan Fang, Yaping Huang, Erhong Yang

    This paper presents worker selection and data augmentation algorithms aimed at improving annotation quality and reducing costs in crowdsourcing for Natural Language Processing (NLP). Unlike previous studies targeting simpler tasks like binary classification, which require less contextual understanding, this study aims to provide a unified paradigm for a wider spectrum of NLP tasks, with sequence labeling and text generation as application showcases. Utilizing a Combinatorial Multi-Armed Bandit (CMAB) approach and a cost-effective human feedback mechanism, the proposed worker selection algorithm effectively addresses the challenge of label inter-dependency in NLP tasks. Additionally, our algorithm tackles the issues presented by imbalanced and small-scale datasets through data augmentation methods. Experiments on the CoNLL 2003 NER, Chinese OEI, and YACLC datasets demonstrated the algorithm's efficiency, achieving up to 100.04% of the expert-only baseline ${\text{F}}$-score and 65.97% cost savings. A dataset-independent experiment yielded 97.56% of the expert baseline ${\text{F}}$-score and 59.88% cost savings. We also provide a theoretical analysis proving our worker selection framework achieves sub-linear regret.