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
- Ling ShaoSuggested from co-authorship
- Xiaokang YangSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works89 from public data
- 398
- Person Re-identification via Recurrent Feature Aggregation253
This work shows that a progressive/sequential fusion framework based on long short term memory (LSTM) network aggregates the frame-wise human region representation at each time stamp and yields a sequence level human feature representation.
- Learning Context Graph for Person Search209
This work proposes a contextual instance expansion module, which employs a relative attention module to search and filter useful context information in the scene, and builds a graph learning framework to effectively employ context pairs to update target similarity.
- Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification162
This work proposes a novel graph-based framework, namely Multi-Granular Hypergraph (MGH), to pursue better representational capabilities by modeling spatiotemporal dependencies in terms of multiple granularities to enhance the overall video representation.
- Video Summarization via Semantic Attended Networks154
A semantic attended video summarization network (SASUM) which consists of a frame selector and video descriptor to select an appropriate number of video shots by minimizing the distance between the generated description sentence of the summarized video and the human annotated text of the original video.
- Anchor-Free Person Search132
This work presents the Feature-Aligned Person Search Network (AlignPS), the first anchor-free framework to efficiently tackle this challenging task, and proposes an aligned feature aggregation module to generate more discriminative and robust feature embeddings by following a "re-id first" principle.
- Inter-X: Towards Versatile Human-Human Interaction Analysis126
This work proposes Inter-X, a currently largest human-human interaction dataset with accurate body movements and diverse interaction patterns, together with detailed hand gestures, and proposes a unified bench-mark composed of 4 categories of downstream tasks from both the perceptual and generative directions.
- ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation110
A GAN-based Transformer for general action-conditioned 3D human motion generation, including not only single-person actions but also multi-person interactive actions, and introduces a new synthetic dataset of complex multi-person combat behaviors.
- Skeleton-Aided Articulated Motion Generation96
This work makes the first attempt to generate articulated human motion sequence from a single image by utilizing paired inputs including human skeleton information as motion embedding and a single human image as appearance reference to generate novel motion frames based on the conditional GAN infrastructure.
- Learning Multi-Attention Context Graph for Group-Based Re-Identification71
A novel unified framework based on graph neural networks is proposed to simultaneously address the above two group-based re-id tasks, i.e., group re-ID and group-aware person re-ids, and a context graph with group members as its nodes to exploit dependencies among different people is constructed.
- ReGenNet: Towards Human Action-Reaction Synthesis67
Quantitative and qualitative results show that the proposed diffusion-based generative model with a Trans-former decoder architecture called ReGenNet together with an explicit distance-based interaction loss is proposed to predict human reactions in an online manner, where the future states of actors are unavailable to reactors.
- EAN: Event Adaptive Network for Enhanced Action Recognition64
A unified action recognition framework to investigate the dynamic nature of video content by introducing the following designs, called the proposed framework as Event Adaptive Network because both key designs are adaptive to the input video content.
- A Coding Framework and Benchmark Towards Low-Bitrate Video Understanding50
By introducing the attention mechanism and adaptive modeling scheme, the video semantic modeling ability of the approach is further enhanced, and a low-bitrate video understanding benchmark is built with three downstream tasks on eight datasets, demonstrating the notable superiority of the approach.
- 46
- Exploring Visual Context for Weakly Supervised Person Search45
This paper inventively considers weakly supervised person search with only bounding box annotations, and discovers three levels of context clues in unconstrained natural images that promote local and global discriminative capabilities and enhances clustering accuracy.
- DialogueNeRF: towards realistic avatar face-to-face conversation video generation43
A novel unified framework based on the neural radiance field (NeRF) is proposed to address the challenges of conversation generation and demonstrates that the avatars in the resulting videos are able to carry on a realistic conversation, and maintain individual styles.
- 41
- 36
- MMHead: Towards Fine-grained Multi-modal 3D Facial Animation34
A simple but efficient VQ-VAE-based method named MM2Face is proposed to unify the multi-modal information and generate diverse and plausible 3D facial motions, which achieves competitive results on both benchmarks.
- GANHead: Towards Generative Animatable Neural Head Avatars32
GANHead (Generative Animatable Neural Head Avatar), a novel generative head model that takes advantages of both the fine-grained control over the explicit expression parameters and the realistic rendering results of implicit representations, achieves superior performance on head avatar generation and raw scan fitting.
- Efficient Person Search: An Anchor-Free Approach32
This work presents an anchor-free approach to efficiently tackling person search, and names its framework as Feature-Aligned Person Search Network (AlignPS), which achieves state-of-the-art or competitive performance on two challenging person search benchmarks, but can be also extended to other challenging searching tasks such as animal and object search.
- 28
- Multi-level attention model for person re-identification28
A feature attention block is proposed for person re-identification that can be seamlessly integrated into existing CNN structures, and is trained only with identity loss.
- 26
- 24
- Multimodal Latent Diffusion Model for Complex Sewing Pattern Generation21
The proposed SewingLDM is a multi-modal generative model that generates sewing patterns controlled by text prompts, body shapes, and garment sketches into a diffusion model, ensuring the generated garments are body-suited and detail-controlled.
- 21
- 20
- Predicting Human Interaction via Relative Attention Model20
The results demonstrate that the proposed relative attention network successfully predicts informative regions between interacting subjects, which in turn yields superior human interaction prediction accuracy.
- HyperStyle3D: Text-Guided 3D Portrait Stylization via Hypernetworks19
This paper proposes a novel method, dubbed HyperStyle3D, based on 3D-aware GANs for 3D portrait stylization, which offers a strong capacity to handle multiple styles with a single model, but also enables flexible fine-grained stylization that affects only texture, shape, or local part of the portrait.
- 19
- Infusion: Preventing Customized Text-to-Image Diffusion from Overfitting18
Drawing from the analysis, Infusion is proposed, a T2I customization method that enables the learning of target concepts to avoid being constrained by limited training diversities, while preserving non-customized knowledge.
- 17
- MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations17
Extensive experiments show that the MotionBank, which comprises 13 video action datasets, 1.24M motion sequences, and 132.9M frames of natural and diverse human motions, is beneficial for general motion-related tasks of human motion generation, motion in-context generation, and motion understanding.
- Hierarchical painter: Chinese landscape painting restoration with fine-grained styles17
A novel inpainting model specifically designed for Chinese landscape paintings, featuring a hierarchical structure that can be applied to restore the famous Dwelling in the Fuchun Mountains with remarkable fidelity is proposed.
- SingingHead: A Large-Scale 4D Dataset for Singing Head Animation16
A simple but efficient non-autoregressive VAE-based framework with background music as an input signal to generate diverse and accurate 3D singing facial motions in real time and demonstrates the significance of the SingingHead dataset in promoting the development of singing head animation.
- Movienet-PS: A Large-Scale Person Search Dataset in the Wild16
This paper introduces a new PS dataset, namely MovieNet-PS, based on an existing large-scale movie dataset, and proposes a novel global-local context network, which exploits scene and group context to boost the search performance.
- 15
- Deep Local Binary Coding for Person Re-Identification by Delving into the Details14
Deep Local Binary Coding significantly minimizes the accuracy gap between binary ReID methods and the state-of-the-art real-valued ones, whilst remarkably reducing query time and memory cost.
- Fine-Grained Recognition via Attribute-Guided Attentive Feature Aggregation14
This work develops a novel attribute-guided attentive network to sequentially discover informative parts/regions, by seeking a good registration between attentive regions and predefined object attributes, which might be more robust than conventional attention model.
- Head3D: Complete 3D Head Generation via Tri-plane Feature Distillation12
This work proposes Head3D, a method to generate full 3D heads with limited multi-view images that achieves cost-efficient and diverse complete head generation with photo-realistic renderings and high-quality geometry representations and mitigate the domain gap between the face and head models.
- E 3 Gen: Efficient, Expressive and Editable Avatars Generation12
A novel generative UV features plane representation that encodes unstructured 3D Gaussians onto a structured 2D UV space defined by the SMPL-X parametric model and introduces a shared structure among subjects to enable generative learning of the diffusion model is proposed.
- Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions11
This paper embeds the manual-assisted task into a vision-language-action framework, where the assistant provides services to the instructor following egocentric vision and commands, and establishes novel benchmarks on egocentric human motion estimation, interaction synthesis, and interaction prediction with comprehensive analysis.
- PostEdit: Posterior Sampling for Efficient Zero-Shot Image Editing11
This work introduces PostEdit, a method that incorporates a posterior scheme to govern the diffusion sampling process that achieves state-of-the-art editing performance while accurately preserving unedited regions.
- 11
- Towards High-fidelity 3D Talking Avatar with Personalized Dynamic Texture10
It is revealed that dynamic texture plays a key role in rendering high-fidelity talking avatars, and a high-resolution 4D dataset TexTalk4D is introduced, consisting of 100 minutes of audio-synced scan-level meshes with detailed 8K dynamic textures from 100 subjects.
- IPAD: Industrial Process Anomaly Detection Dataset10
This work proposes a new dataset, IPAD, specifically designed for VAD in industrial scenarios, and introduces a period memory module and a sliding window inspection mechanism to effectively investigate the periodic information in a basic reconstruction model.
- Fine-grained image analysis via progressive feature learning10
In this work, a two-stage framework for fine-grained recognition is developed that aims to discover and align local discriminative features, and the second stage aims to aggregate these features to get classification results.
- TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification9
This work argues that both domain-specific and domain-invariant features are crucial for improving the generalization ability of reid models, and designs a novel framework, which is name two-stream adaptive learning (TAL), to simultaneously model these two kinds of information.
- 9
- 9
- Disentangled Clothed Avatar Generation with Layered Representation8
A layered UV feature plane representation, where components are distributed in different layers of the Gaussian-based UV feature plane with corresponding semantic labels is proposed, which can be effectively learned with current feed-forward generation pipelines, facilitating component disentanglement and enhancing details of generated avatars.
- AniSDF: Fused-Granularity Neural Surfaces with Anisotropic Encoding for High-Fidelity 3D Reconstruction8
This work presents AniSDF, a novel approach that learns fused-granularity neural surfaces with physics-based encoding for high-fidelity 3D reconstruction and boosts the quality of SDF-based methods by a great scale in both geometry reconstruction and novel-view synthesis.
- MARS: Mesh AutoRegressive Model for 3D Shape Detailization7
This paper capitalizes on a novel multi-LOD, multi-category mesh representation to learn shape-consistent mesh representations in latent space across different LODs, and proposes a mesh autoregressive model capable of generating such latent representations through next-LOD token prediction.
- 7
- Deep Cross-Modality Alignment for Multi-Shot Person Re-IDentification7
A deep cross-modality alignment network is proposed, which jointly explores both human sequence pairs and image pairs to facilitate training better multi-shot human Re-ID models, i.e., via transferring knowledge from image data to sequence data.
- LERE: Learning-Based Low-Rank Matrix Recovery with Rank Estimation6
A novel LEarning-based low-rank matrix recovery with Rank Estimation (LERE) is proposed, which is more efficient and robust than existing LRMR methods and surpasses state-of-the-art (SOTA) methods.
- 6
- Correlated Low-Rank Adaptation for ConvNets5
A novel framework called Correlated Low-Rank Adaptation (CoLoRA), which explicitly utilizes correlated low-rank matrices to model the inter-layer dependencies among convolutional layers, and achieves superior performance with only 5% of trainable parameters.
- Two TAL effectors of Xanthomonas citri promote pustule formation by directly repressing the expression of GRAS transcription factor in citrus5
Two PthA1 variants are characterized, designated PthA5 and PthA6, which facilitate Xcc infection in susceptible citrus species by promoting the formation of hypertrophy and hyperplasia symptoms, and is the first report that TALEs act as repressors of a resistance gene to confer host susceptibility.
- 5
- Rethinking Clothes Changing Person ReID: Conflicts, Synthesis, and Optimization5
This study dives into the relationship between standard and clothes-changing~(CC) learning objectives, and brings the inner conflicts between these two objectives to the fore, and decouple these objectives and re-formulate CC-ReID learning as a multi-objective optimization (MOO) problem.
- Cross-modality motion parameterization for fine-grained video prediction5
This work proposes a novel cross-modality video generation network that directly links sound with the movement parameters of the operated object and automatically outputs corresponding object motion according to the rhythm of the given audio signal.
- Depth Structure Preserving Scene Image Generation5
A novel depth structure preserving scene image generation network (DSP-GAN), which favors a hierarchical architecture, which is built upon a Hawkes point process that models high-order spatial dependency between different depth layers.
- Flow Matching in the Low-Noise Regime: Pathologies and a Contrastive Remedy4
This work provides the first theoretical analysis of the low-noise pathology, establishing its intrinsic link to the structure of the flow matching objective and proposes Local Contrastive Flow (LCF), a hybrid training protocol that replaces direct velocity regression with contrastive feature alignment at small noise levels, while retaining standard flow matching at moderate and high noise.
- 4
- S3-Face: SSS-Compliant Facial Reflectance Estimation via Diffusion Priors3
This paper introduces the use of Stable Diffusion as a prior for facial reflectance estimation, achieving robust results with minimal captured data for fine-tuning, and presents S3-Face, a comprehensive framework capable of producing SSS-compliant skin reflectance from in-the-wild images.
- EvaSurf: Efficient View-Aware Implicit Textured Surface Reconstruction3
The EvaSurf method can reconstruct high-quality appearance and accurate mesh on both synthetic and real-world datasets and can be trained in just 1-2 hours using a single GPU and run on mobile devices at over 40 FPS.
- 3
- Generalizable Person Search on Open-world User-Generated Video Content3
This work focuses on learning domain-invariant representations for both detection and ReID by introducing a multi-task prototype-based domain-specific batch normalization, and a channel-wise ID-relevant feature decorrelation strategy.
- 2
- 2
- DCN: Decoupled-Coupled Network for Text-based Person Search2
This paper first attempts to resolve the above conflicts by proposing a Decoupled Proposal Selection (DPS) strategy, inspired by the divide-and-conquer principle, and presents a Coupled Cascade Refinement (CCR) module to jointly optimize both sub-tasks in a multi-stage manner.
- Directional Texture Editing for 3D Models2
This work proposes ITEM3D, a Texture Editing Model designed for automatic 3D object editing according to the text Instructions, which takes the rendered images as the bridge between text and 3D representation and further optimizes the disentangled texture and environment map.
- 1
- 1
- 1
- 1
- Image Matching via Loopy RNN1
This work proposes a novel loopy recurrent neural network (Loopy RNN), which is capable of aggregating relationship information of two input images in a progressive/iterative manner and outputting the consolidated matching score in the final iteration.
- –
- –
- De-biasing Facial Albedo Estimation via Visual-Textual Cues–
The relationship between albedo and face attributes is reconsidered and an ID2Albedo++ method to directly estimate albedo without constraining illumination is proposed and outperforms state-of-the-art albedo estimation methods in terms of both accuracy and fidelity.
- –
- –
- –
- –
- –
- –
- The R&D Project Termination Decision Based on Discriminant Analysis–
The RD project termination decision will has great significance for optimizing science and technology resources and the discriminant analysis is much easier because of its using available existing project information as much as possible.
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.