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
- Xian‐Sheng HuaSuggested from co-authorship
- Alexander G. HauptmannSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works89 from public data
- Multi-View Image Generation from a Single-View193
This paper proposes a novel image generation model termed VariGANs, which combines the merits of the variational inference and the Generative Adversarial Networks (GANs), and generates the target image in a coarse-to-fine manner instead of a single pass which suffers from severe artifacts.
- 183
- Learning Spatial Awareness to Improve Crowd Counting149
A novel architecture called SPatial Awareness Network (SPANet) to incorporate spatial context for crowd counting is presented, and the Maximum Excess over Pixels (MEP) loss is proposed to achieve this by finding the pixel-level subregion with high discrepancy to the ground truth.
- DB-LSTM: Densely-connected Bi-directional LSTM for human action recognition141
A Densely-connected Bi-directional LSTM (DB-LSTM) network is proposed to model the visual and temporal associations in both forward and backward directions to boost the effectiveness and robustness of modeling long-range action recognition.
- Rethinking Spatial Invariance of Convolutional Networks for Object Counting140
Inspired by previous work, this work proposes a low-rank approximation accompanied with translation invariance to favorably implement the approximation of massive Gaussian convolution to improve the spatial invariance of convolutional networks.
- StableAnimator: High-Quality Identity-Preserving Human Image Animation114
StableAnimator is presented, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-quality videos without any post-processing, conditioned on a reference image and a sequence of poses.
- Hypergraph Transformer for Skeleton-based Action Recognition111
An underlying issue of graph models in general, i.e., pairwise aggregation essentially ignores the high-order kinematic dependencies between body joints is revealed, and a new self-attention mechanism on hypergraph is proposed, termed Hypergraph Self-Attention (HyperSA), to incorporate intrinsic higher-order relations into the model.
- 105
- Improving the Learning of Multi-column Convolutional Neural Network for Crowd Counting102
Extensive experiments on four challenging benchmarks show that McML can significantly improve the original multi-column networks and outperform the other state-of-the-art approaches.
- Video2Shop: Exact Matching Clothes in Videos to Online Shopping Images90
A novel deep neural network is proposed to explore a new cross-domain task, Video2Shop, targeting for matching clothes appeared in videos to the exactly same items in online shops, which outperforms the state-of-the-art methods.
- MotionEditor: Editing Video Motion via Content-Aware Diffusion84
MotionEditor is the first to use diffusion models specifically for video motion editing, considering the origin dynamic background and camera movement, and incorporates a novel content-aware motion adapter into ControlNet to capture temporal motion correspondence.
- Implicit Temporal Modeling with Learnable Alignment for Video Recognition72
This paper proposes a novel Implicit Learnable Alignment (ILA) method, which minimizes the temporal modeling effort while achieving incredibly high performance and allows eliminating the costly or insufficient temporal self-attention in video.
- 71
- Procontext: Exploring Progressive Context Transformer for Tracking65
This work revamped the tracking framework with Progressive Context Encoding Transformer Tracker (ProContEXT), which coherently exploits spatial and temporal contexts to predict object motion trajectories and raises a new pathway to multi-context modeling for transformer-based trackers.
- GNAS61
This work proposes an efficient greedy neural architecture search approach (GNAS) to automatically discover the optimal tree-like deep architecture for multi-attribute learning and demonstrates the effectiveness and compactness of neural architectures derived by GNAS.
- 59
- Personalized clothing recommendation combining user social circle and fashion style consistency52
Three social factors (i.e., personal interest, interpersonal interest similarity and interpersonal influence) and fashion style consistency are fused into a unified personalized recommendation model based on probabilistic matrix factorization (PMF).
- GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement48
A novel two-stage framework that focuses on utilizing bidirectional relations within verbs and roles is proposed, and extensive experimental results show that the renovated framework outperforms other state-of-the-art methods under various metrics.
- Video eCommerce47
An advertising system named Video eCommerce to exhibit appropriate product ads to particular users at proper time stamps of videos, which takes into account video semantics, user shopping preference and viewing behavior feedback by a two-level strategy is proposed.
- VIREO @ TRECVID 2017: Video-to-Text, Ad-hoc Video Search, and Video hyperlinking.45
The systems developed for Video-to-Text (VTT), Ad-hoc Video Search (AVS) and Video Hyper-linking (LNK) tasks at TRECVID 2017 and the achieved results are described.
- DCPT: Darkness Clue-Prompted Tracking in Nighttime UAVs39
A novel architecture called Darkness Clue-Prompted Tracking (DCPT) is proposed that achieves robust UAV tracking at night by efficiently learning to generate darkness clue prompts and efficiently injects anti-dark knowledge without extra modules.
- ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules39
The proposed framework can significantly reduce the manual effort involved in chart analysis, providing a step towards a universal chart understanding model and offers opportunities for plug-and-play integration with mainstream LLMs such as T5 and TaPas, extending their capability to chart comprehension tasks.
- Tracking with Human-Intent Reasoning39
This work proposes a tracker called TrackGPT, which is capable of performing complex reasoning-based tracking, which uses LVLM to understand tracking instructions and condense the cues of what target to track into referring embeddings and generates the tracking results based on the embeddings.
- Generating Person Images with Appearance-aware Pose Stylizer36
A novel end-to-end framework to generate realistic person images based on given person poses and appearances called Appearance-aware Pose Stylizer (APS) which generates human images by coupling the target pose with the conditioned person appearance progressively.
- MotionFollower: Editing Video Motion via Lightweight Score-Guided Diffusion35
The proposed MotionFollower is a lightweight score-guided diffusion model for video motion editing that achieves an approximately 80% reduction in GPU memory while delivering superior motion editing performance and exclusively supporting large camera movements and actions.
- PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimation33
The Multi-Hypothesis Pose Synthesis Domain Adaptation (PoSynDA) framework is presented, which simulates the 3D pose distribution in the target domain, filling the data diversity gap and paves the way for the practical application of 3D human pose estimation.
- 32
- Learning to Transfer27
Generalizable Attribute Learning Model (GALM) is proposed to automatically design the neural networks for generalizable attribute learning and fully exploits the Multi-Task Learning and Reinforcement Learning to speed up the search procedure.
- 26
- On the Selection of Anchors and Targets for Video Hyperlinking26
Insight is provided from the perspective of hubness and local intrinsic dimensionality, which are two statistical properties in assessing the popularity and complexity of data space and two novel algorithms are proposed for low-risk automatic selection of anchors and targets.
- FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio25
This paper abstracts the process of people hearing speech, extracting meaningful cues, and creating vari-ous dynamically audio-consistent talking faces, termed Lis-tening and Imagining, into the task of high-fidelity diverse talking faces generation from a single audio, and intro-duce the Controllable Coherent Frame generation.
- 25
- 24
- Emphasizing Discriminative Features for Dataset Distillation in Complex Scenarios23
EDF (emphasizes the discriminative features), a dataset distillation method that enhances key discriminative regions in synthetic images using Grad-CAM activation maps using Grad-CAM activation maps.
- Longshortnet: Exploring Temporal and Semantic Features Fusion In Streaming Perception21
This work proposes LongShortNet, a novel dual-path network that captures long-term temporal motion and integrates it with short-term spatial semantics for real-time perception, enabling spatiotemporal feature fusion in streaming perception.
- CrossNet: Boosting Crowd Counting with Localization21
A novel location-guided framework named CrossNet is proposed for crowd counting, which integrates location supervision into density maps through dual-branch joint training and outperforms the state-of-the-art approaches both in crowd counting and crowd localization.
- Rational Modulation Strategies to Improve Bioimaging Applications for Organic NIR‐II Fluorophores21
The modulation strategies focused on improving the performance and functionality of organic NIR‐II fluorophores are summarized and discussed in detail and the conclusion and future directions of the modulation strategy are presented.
- Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness18
The investigation revealed strong variations in joint-to-joint relationships across different actions, exposing the limitations of a single adjacency matrix in capturing the variations of relational configurations emblematic of human movement, which is addressed by proposing an efficient refinement to Graph Convolutions - the BlockGC.
- 17
- Real-time Semantic Segmentation with Parallel Multiple Views Feature Augmentation15
A new real-time semantic segmentation network, called MvFSeg, which combines multi-view features and augmented features from the lightweight networks with progressive dense aggregation structures and outperforms existing state-of-the-art methods.
- HA-VLN 2.0: An Open Benchmark and Leaderboard for Human-Aware Navigation in Discrete and Continuous Environments with Dynamic Multi-Human Interactions13
A unified Human-Aware VLN (HA-VLN) benchmark is introduced that merges these paradigms under explicit social-awareness constraints and shows improved navigation success and fewer collisions when social context is integrated, underscoring the need for human-centric design.
- 13
- Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models12
This work presents EIBench, a large-scale benchmark encompassing 1615 basic EI samples and 50 complex EI samples featuring multifaceted emotions, and proposes a Coarse-to-Fine Self-Ask (CFSA) annotation pipeline, which guides Vision-Language Models (VLLMs) through iterative question-answer rounds to yield high-quality labels at scale.
- UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts10
The UMETTS framework is introduced, a novel framework that leverages emotional cues from multiple modalities to generate highly expressive and emotionally resonant speech and achieves significant improvements in emotion accuracy and speech naturalness, outperforming traditional E-TTS methods on both objective and subjective metrics.
- Improving Anomaly Segmentation with Multi-Granularity Cross-Domain Alignment10
Multi-Granularity Cross-Domain Alignment (MGCDA) framework is proposed for anomaly segmentation in complex driving environments, which uniquely combines a new Multi-source Domain Adversarial Training (MDAT) module and a novel Cross-domain Anomaly-aware Contrastive Learning (CACL) method to boost the generality of the model.
- 10
- Debunking Free Fusion Myth: Online Multi-view Anomaly Detection with Disentangled Product-of-Experts Modeling10
dPoE, a novel multi-view variational autoencoder model that involves a Product-of-Experts (PoE) layer in tacklingMulti-view data, a Total Correction (TC) discriminator in disentangling view-common and view-specific representations, and a joint loss function in wrapping up all components is proposed.
- SZTU-CMU at MER2024: Improving Emotion-LLaMA with Conv-Attention for Multimodal Emotion Recognition9
This system leverages the advanced emotional understanding capabilities of Emotion-LLaMA to generate high-quality annotations for unlabeled samples, addressing the challenge of limited labeled data, and introduces Conv-Attention, a lightweight and efficient hybrid framework to enhance multimodal fusion while mitigating modality-specific noise.
- MetaDesigner: Advancing Artistic Typography Through AI-Driven, User-Centric, and Multilingual WordArt Synthesis9
MetaDesigner introduces a transformative framework for artistic typography synthesis, powered by Large Language Models (LLMs) and grounded in a user-centric design paradigm, that dynamically adjusts hyperparameters to align with user-defined stylistic and thematic preferences.
- UCDR-Adapter: Exploring Adaptation of Pre-Trained Vision-Language Models for Universal Cross-Domain Retrieval7
The UCDR-Adapter is proposed, which enhances pre-trained models with adapters and dynamic prompt generation through a two-phase training strategy and dynamically adapts to evolving data distributions, enhancing both flexibility and generalization.
- 6
- 6
- 6
- FlexEdit: Marrying Free-Shape Masks to VLLM for Flexible Image Editing5
FlexEdit is proposed, an end-to-end image editing method that leverages both free-shape masks and language instructions for Flexible Editing and achieves state-of-the-art (SOTA) performance in LLM-based image editing.
- 5
- KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range Multilateration5
A groundbreaking facial landmark detection framework that stands out from existing methods, which utilizes a fully convolutional network to predict a distance map, which computes the distance between a Point of Interest (POI) and multiple anchor points.
- Robust Adaptation of Foundation Models With Black-Box Visual Prompting4
This work proposes black-box visual prompting (BlackVIP), which efficiently adapts the PTMs without knowledge of their architectures or parameters, and introduces a variant, BlackVIP-SE, which significantly reduces the runtime and computational cost of BlackVIP.
- Refined Temporal Pyramidal Compression-and-Amplification Transformer for 3D Human Pose Estimation4
The Refined Temporal Pyramidal Compression-and-Amplification (RTPCA) transformer is introduced, an approach that tackles a critical issue in current transformer-based methods: the underutilization of intra-and inter-block relations through attention mechanisms.
- 4
- 4
- 4
- 4
- IVAC-$\mathbf {P^{2}L}$: Leveraging Irregular Repetition Priors for Improving Video Action Counting3
This study introduces a novel perspective on VAC, focusing on Irregular Video Action Counting (IVAC), which emphasizes the importance of modeling the irregular repetition priors present in video content, and introduces a novel methodology consisting of consistency and inconsistency modules, underpinned by a tailored pull-push loss mechanism.
- WordArt Designer API: User-Driven Artistic Typography Synthesis with Large Language Models on ModelScope3
The challenge of simplifying artistic typography for non-professionals is addressed by offering a dynamic, adaptive, and computationally efficient alternative to traditional rigid templates by leveraging the power of LLMs to understand and interpret user input, facilitating a more intuitive design process.
- A Study on the Translation of Cultural Classics Based on Deep Learning Methods3
This paper introduces the basic concept of deep learning and proposes an algorithm that deeply studies the convolution layer and pool layer and establishes a deep learning model that calculates and counts the text information of ancient books through explicit intertextuality so as to study cultural classics translation.
- 3
- DPDEdit: Detail-Preserved Diffusion Models for Multimodal Fashion Image Editing2
This work presents Detail-Preserved Diffusion Models (DPDEdit), a new multimodal fashion image editing architecture based on latent diffusion models that outperforms state-of-the-art methods in terms of image fidelity and coherence with the given multimodal input.
- DyRoNet: Dynamic Routing and Low-Rank Adapters for Autonomous Driving Streaming Perception2
DyRoNet is introduced, a low-rank enhanced dynamic routing framework designed for streaming perception in autonomous driving systems that establishes a new benchmark for streaming perception but also provides valuable engineering insights for future work.
- HCMA: Hierarchical Cross-model Alignment for Grounded Text-to-Image Generation2
Extensive experiments on the MS-COCO 2014 validation set show that HCMA surpasses state-of-the-art baselines, demonstrating HCMA's effectiveness in faithfully capturing intricate textual semantics while adhering to user-defined spatial constraints, offering a robust solution for semantically grounded image generation.
- 2
- 1
- Sign-Language Datasets at Scale: A Comprehensive Survey on Resources, Benchmarks, and Annotation Standards1
This survey presents a comprehensive index of sign-language datasets, covering 120 resources across 35 sign languages, and analyzes key challenges such as modality imbalance, annotation granularity, and signer bias, and outline considerations for future dataset design.
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- An Index of Refraction Adaptive Neural Refractive Radiance Field for Transparent Scenes–
A refractive radiance field method for the novel view synthesis of transparent object scenes that can reconstruct the geometry and radiance field using only a sequence of scene images of transparent objects, and it can automatically search for the optimal IOR without prior information.
- –
- –
- –
- A Novel Multi-Pose Person Re-Identification Method Based on Semantic- and Pose-Guided Feature Fusion–
- Music2P: A Multi-Modal AI-Driven Tool for Simplifying Album Cover Design–
Music2P is an open-source, multi-modal AI-driven tool that streamlines album cover creation, making it efficient, accessible, and cost-effective through Ngrok.
- Preoperative Head CT Assisted Prediction of Acute Encephalocele During Isolated Acute Subdural Hematoma Surgery–
An increased risk of intra-operative acute encephalocele is found in patients with lower preoperative GCS, HU-WM, HU-HT and higher preoperative TH and CES, which should help clinicians to develop a more scientific treatment strategy and improve the survival of such kind of patients.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. 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.