Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Suggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works68 from public data
- PointConv: Deep Convolutional Networks on 3D Point Clouds1,931
The dynamic filter is extended to a new convolution operation, named PointConv, which can be applied on point clouds to build deep convolutional networks and is able to achieve state-of-the-art on challenging semantic segmentation benchmarks on 3D point clouds.
- 923
- MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing902
MasaCtrl converts existing self-attention in diffusion models into mutual self-attention, so that it can query correlated local contents and textures from source images for consistency, and proposes a mask-guided mutual self-attention strategy.
- PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding410
PhotoMaker is introduced, an efficient personalized text-to-image generation method, which mainly encodes an arbitrary number of input ID images into a stack ID embed-ding for preserving ID information, and an ID-oriented data construction pipeline to assemble the training data.
- LayoutDiffusion: Controllable Diffusion Model for Layout-to-Image Generation369
A diffusion model named LayoutDiffusion is proposed that can obtain higher generation quality and greater controllability than the previous works and is proposed to construct a structural image patch with region information and transform the patched image into a special layout to fuse with the normal layout in a unified form.
- Deep Air Learning: Interpolation, Prediction, and Feature Analysis of Fine-Grained Air Quality274
The proposed approach utilizes the information pertaining to the unlabeled spatio-temporal data to improve the performance of the interpolation and the prediction, and performs feature selection and association analysis to reveal the main relevant features to the variation of the air quality.
- Open-book Video Captioning with Retrieve-Copy-Generate Network118
A novel Retrieve-Copy-Generate network is proposed, where a pluggable video-to-text retriever is constructed to retrieve sentences as hints from the training corpus effectively, and a copy-mechanism generator is introduced to extract expressions from multi-retrieved sentences dynamically.
- RecDCL: Dual Contrastive Learning for Recommendation82
This work investigates how to employ both batch-wise CL (BCL) and feature-wise CL (FCL) for recommendation and proposes a dual contrastive learning recommendation framework---RecDCL, which can consistently outperform the state-of theart GNNs-based and SSL-based models.
- StyleAdapter: A Unified Stylized Image Generation Model52
The StyleAdapter is proposed, a unified stylized image generation model capable of producing a variety of stylized images that match both the content of a given prompt and the style of reference images, without the need for per-style fine-tuning.
- PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM46
This research introduces a unified framework for automated graphic layout generation, leveraging the multi-modal large language model (MLLM) to accommodate diverse design tasks and develops an automated text-to-poster system that generates editable SVG posters based on users' design intentions, bridging the gap between layout generation and real-world graphic design applications.
- Semantic-Guided Relation Propagation Network for Few-shot Action Recognition44
A novel semantic-guided relation propagation network (SRPN), which leverages semantic information together with visual information for few-shot action recognition and outperforms several state-of-the-art methods with a significant margin.
- 38
- 37
- 35
- CustomNet: Zero-shot Object Customization with Variable-Viewpoints in Text-to-Image Diffusion Models34
The CustomNet is introduced, a novel object customization approach that explicitly incorporates 3D novel view synthesis capabilities into the object customization process, and facilitates zero-shot object customization without test-time optimization, offering simultaneous control over the viewpoints, location, and background.
- Embedding deep networks into visual explanations31
The explanation module works by embedding a high-dimensional deep network layer nonlinearly into a low-dimensional explanation space while retaining faithfulness, so that the original deep learning predictions can be constructed from the few concepts extracted by the explanation module.
- Multi-Task Medical Concept Normalization Using Multi-View Convolutional Neural Network30
A general framework which introduces a tensor generator and a novel multi-view convolutional neural network with multi-task shared structure to tackle the two tasks simultaneously to address non-standard expressions and short-text problem.
- 29
- SphereDiffusion: Spherical Geometry-Aware Distortion Resilient Diffusion Model26
A novel framework of SphereDiffusion is introduced to address the unique challenges of spherical distortion and geometry characteristics, for better generating high-quality and precisely controllable spherical panoramic images.
- Do We Really Need Temporal Convolutions in Action Segmentation?24
This paper presents a pure Transformer-based model without temporal convolutions in action segmentation, called Temporal U-Transformer, and proposes a boundary-aware loss based on the distribution of similarity scores between frames from attention modules to improve the ability to recognize boundaries.
- 24
- Mining partially annotated images24
The Semi-Supervised Correspondence Hierarchical Dirichlet Process (SSCHDP) is proposed, which lies in exploiting the information pertaining to partially annotated images or even unannotated images to achieve semi-supervised learning under the HDP structure.
- 21
- 19
- VideoMaker: Zero-shot Customized Video Generation with the Inherent Force of Video Diffusion Models18
A novel framework that leverages VDM's inherent force to enable high-quality zero-shot customized video generation and devise an innovative bidirectional interaction between subject features and generated content through spatial self-attention within VDM, ensuring that VDM has better subject fidelity while maintaining the diversity of the generated video.
- 15
- Sticker820K: Empowering Interactive Retrieval with Stickers15
The StickerCLIP is proposed as a benchmark model on the Sticker820K dataset, demonstrating strong superiority over the CLIP for the text-to-image retrieval task, and the recently popularized LLM is extended by means of prompt tuning, integrating its ability for sticker retrieval and allowing users to retrieve stickers through instructions.
- 14
- DOGR: Towards Versatile Visual Document Grounding and Referring12
The DOGR-Engine is proposed, which generates two types of high-quality fine-grained document data: multi-granular parsing data to improve text localization and recognition, and instruction-tuning data to activate MLLMs' grounding and referring capabilities in dialogue and reasoning.
- Weakly-Supervised Temporal Action Localization by Progressive Complementary Learning12
This work addresses the Weakly-Supervised Temporal Action Localization from a novel category exclusion perspective, which gradually enhances the snippet-level supervision to bridge the gap between video-level supervision and unavailable snippet-level supervision.
- How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?11
A novel Contrastive Partial Ranking Distillation (CPRD) method is proposed, which implements the objective of mimicking relative order between hard negative samples with contrastive learning, and surpasses other distillation methods and significantly improves the accuracy of dual-encoder.
- CustomNet: Object Customization with Variable-Viewpoints in Text-to-Image Diffusion Models10
CustomNet is presented, a unified encoder-based object customization framework that explicitly incorporates 3D novel view synthesis capabilities into the customization process, and outperforms other customization methods regarding identity preservation, diversity, and harmony.
- Mono2Stereo: A Benchmark and Empirical Study for Stereo Conversion9
The Mono2Stereo dataset is introduced, providing high-quality training data and benchmark to support in-depth exploration of stereo conversion and a new evaluation metric, Stereo Intersection-over-Union, which prioritizes disparity and achieves a high correlation with human judgments on stereo effect.
- CREATE: A Benchmark for Chinese Short Video Retrieval and Title Generation9
CREATE is proposed, the first large-scale Chinese shoRt vidEo retrievAl and Title gEneration benchmark, and a novel model ALWIG which combines video retrieval and video titling tasks to achieve the purpose of multi-modal ALignment WIth Generation with the help of video tags and a GPT pre-trained model.
- From heatmaps to structured explanations of image classifiers9
The explainable neural network (XNN), which attempts to extract and visualize several high-level concepts purely from the deep network, without relying on human linguistic concepts, is described, which helps users understand network classifications that are less intuitive and substantially improves user performance on a difficult fine-grained classification task of discriminating among different species of seagulls.
- UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding8
UniUGG is introduced, the first unified understanding and generation framework for 3D modalities that employs an LLM to comprehend and decode sentences and 3D representations and proposes a spatial decoder leveraging a latent diffusion model to generate high-quality 3D representations.
- 8
- 8
- Learning with limited and noisy tagging8
A discriminative model is proposed, called SpSVM-MC, that exploits both labeled and unlabeled data through a semi-parametric regularization and takes advantage of the multi-label constraints into the optimization of a robust tagging method.
- Multi-view learning from imperfect tagging8
A novel discriminative classification method is proposed under the framework of MITL, which explicitly makes use of the given multiple labels simultaneously as an additional feature to deliver a more effective classification performance than the existing literature where one label is considered at a time as the classification target.
- Mining noisy tagging from multi-label space8
It is argued that all the given multiple tags can be utilized simultaneously as an additional feature and the information contained in the multi-label space can be taken advantage of to improve the performance of the classification.
- 7
- Toward Human Perception-Centric Video Thumbnail Generation7
Extensive experimental results show that the HPCVTG framework outperforms existing methods in objective and subjective evaluations, highlighting its potential to improve the user experience when browsing videos and inspire future research in human perception-centric content generation tasks.
- TransFusion: Multi-Modal Fusion for Video Tag Inference via Translation-based Knowledge Embedding7
This paper proposes TransFusion, an end-to-end supervised learning framework that fuses multi-modal embeddings with the knowledge embedding to derive the video representation and adopts a dual attentive approach to learn both the modality importance in fusion and relation importance in inference.
- 5
- 5
- Visualizing point cloud classifiers by curvature smoothing5
A novel approach to visualize features important to the point cloud classifiers using an approximated curvature smoothing algorithm that can smoothly transition from the original point cloud to one of constant curvature, such as a uniform sphere.
- SynopGround: A Large-Scale Dataset for Multi-Paragraph Video Grounding from TV Dramas and Synopses4
A large-scale video grounding dataset named SynopGround is presented, in which more than 2800 hours of videos are sourced from popular TV dramas and are paired with accurately localized human-written synopses, and a novel Local-Global Multimodal Reasoner (LGMR) is proposed to explicitly model the local-global structures of long-term multimodal inputs for MPVG.
- 4
- 3
- 3
- 2
- 2
- VTLayout: A Multi-Modal Approach for Video Text Layout2
A Video-level Text Layout model (VTLayout) is proposed to address the layout problem, which fuses textual, visual, and spatial-temporal embedding of video text trajectories and is the first method to tackle text layout on video level.
- 1
- 1
- 1
- Towards Unseen Triples: Effective Text-Image-joint Learning for Scene Graph Generation1
A Text-Image-joint Scene Graph Generation (TISGG) model to resolve the unseen triples and improve the generalisation capability of the SGG models, and a novel balanced learning strategy, including a Charater Guided Sampling and an Informative Re-weighting module, to provide tailor-made learning methods for each predicate according to their characters.
- 1
- 1
- 1
- ScaleNet - Improve CNNs through Recursively Rescaling Objects1
The proposed ScaleNet, which recursively predicts object scale in a deep learning framework with an explicit objective to predict the scale of objects in images, enables pretrained deep learning models to identify objects in the scales that are not present in their training sets.
- Dynamic-in-Few-Step: Unifying Dynamic Computation and Few-Step Distillation for Efficient Video Generation–
A novel post-training acceleration framework that exploits this redundancy by integrating dynamic structural sparsification directly into the distillation process, and introduces a Progressive Training Strategy coupled with an Output Rollout Mechanism that ensures the coherent learning of structural decisions across timesteps.
- –
- –
- –
- –
- Characterizing and Comparing User Location Preference in an Urban Mobile Network–
A one-week network trace of an urban mobile network with over 200,000 users is reported, which proposes several normalized metrics such as the ratio of active users (RAU) and its z-score (ZLP) either by time or by user group, which allow comparison of location preferences across different user groups.
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-15. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.