Jiankang Deng

UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning AAAI 2026 ViCToR: Improving Visual Comprehension via Token Reconstruction for Pretraining LMMs AAAI 2026 Plug-and-Play Clarifier: A Zero-Shot Multimodal Framework for Egocentric Intent Disambiguation AAAI 2026 ImHead: A Large-scale Implicit Morphable Model for Localized Head Modeling ICCV 2025 Fractal Calibration for Long-tailed Object Detection CVPR 2025 HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos CVPR 2025 WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild CVPR 2025 CaricatureBooth: Data-Free Interactive Caricature Generation in a Photo Booth CVPR 2025 S^3-Face: SSS-Compliant Facial Reflectance Estimation via Diffusion Priors CVPR 2025 Single-view Image to Novel-view Generation for Hand-Object Interactions AAAI 2025 Unsupervised Audio-Visual Segmentation with Modality Alignment AAAI 2025 CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination AAAI 2025 From Attention to Activation: Unraveling the Enigmas of Large Language Models ICLR 2025 Frequency-Guided Diffusion for Training-Free Text-Driven Image Translation ICCV 2025 VTimeCoT: Thinking by Drawing for Video Temporal Grounding and Reasoning ICCV 2025 Region-based Cluster Discrimination for Visual Representation Learning ICCV 2025 Unlocking the Potential of Diffusion Priors in Blind Face Restoration ICCV 2025 ForCenNet: Foreground-Centric Network for Document Image Rectification ICCV 2025 HUST: High-Fidelity Unbiased Skin Tone Estimation via Texture Quantization ICCV 2025 "Principal Components" Enable A New Language of Images ICCV 2025 Signs as Tokens: A Retrieval-Enhanced Multilingual Sign Language Generator ICCV 2025 Multi-Label Cluster Discrimination for Visual Representation Learning ECCV 2024 AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesis NIPS 2024 TopoFR: A Closer Look at Topology Alignment on Face Recognition NIPS 2024 VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections NIPS 2024 Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization NIPS 2024 ID-to-3D: Expressive ID-guided 3D Heads via Score Distillation Sampling NIPS 2024 DiffSED: Sound Event Detection with Denoising Diffusion AAAI 2024 Any-Size-Diffusion: Toward Efficient Text-Driven Synthesis for Any-Size HD Images AAAI 2024 Three Heads Are Better than One: Complementary Experts for Long-Tailed Semi-supervised Learning AAAI 2024 G3DR: Generative 3D Reconstruction in ImageNet CVPR 2024 CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofing CVPR 2024 Monocular Identity-Conditioned Facial Reflectance Reconstruction CVPR 2024 VkD: Improving Knowledge Distillation using Orthogonal Projections CVPR 2024 Neural Sign Actors: A Diffusion Model for 3D Sign Language Production from Text CVPR 2024 WaveFace: Authentic Face Restoration with Efficient Frequency Recovery CVPR 2024 Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation CVPR 2024 Self-Adaptive Reality-Guided Diffusion for Artifact-Free Super-Resolution CVPR 2024 SAGS: Structure-Aware 3D Gaussian Splatting ECCV 2024 3DGazeNet: Generalizing Gaze Estimation with Weak Supervision from Synthetic Views ECCV 2024 Arc2Face: A Foundation Model for ID-Consistent Human Faces ECCV 2024 Adaptive Parametric Activation ECCV 2024 RWKV-CLIP: A Robust Vision-Language Representation Learner EMNLP 2024 Unified Physical-Digital Face Attack Detection IJCAI 2024 Regularization of Polynomial Networks for Image Recognition CVPR 2023 Unicom: Universal and Compact Representation Learning for Image Retrieval ICLR 2023 FitMe: Deep Photorealistic 3D Morphable Model Avatars CVPR 2023 Improving Fairness in Facial Albedo Estimation via Visual-Textual Cues CVPR 2023 Domain-General Crowd Counting in Unseen Scenarios AAAI 2023 HeadSculpt: Crafting 3D Head Avatars with Text NIPS 2023 Spatio-temporal Prompting Network for Robust Video Feature Extraction ICCV 2023 DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion ICCV 2023 ALIP: Adaptive Language-Image Pre-Training with Synthetic Caption ICCV 2023 Adaptive Spiral Layers for Efficient 3D Representation Learning on Meshes ICCV 2023 Controllable Person Image Synthesis with Pose-Constrained Latent Diffusion ICCV 2023 Holistic Label Correction for Noisy Multi-Label Classification ICCV 2023 TransFace: Calibrating Transformer Training for Face Recognition from a Data-Centric Perspective ICCV 2023 DamoFD: Digging into Backbone Design on Face Detection ICLR 2023 Sample and Computation Redistribution for Efficient Face Detection ICLR 2022 MimicME: A Large Scale Diverse 4D Database for Facial Expression Analysis ECCV 2022 Physically-Based Face Rendering for NIR-VIS Face Recognition NIPS 2022 Augmenting Deep Classifiers with Polynomial Neural Networks ECCV 2022 MogFace: Towards a Deeper Appreciation on Face Detection CVPR 2022 Killing Two Birds With One Stone: Efficient and Robust Training of Face Recognition CNNs by Partial FC CVPR 2022 Long-Tailed Instance Segmentation Using Gumbel Optimized Loss ECCV 2022 Decoupled Multi-Task Learning With Cyclical Self-Regulation for Face Parsing CVPR 2022 Variational Prototype Learning for Deep Face Recognition CVPR 2021 OSTeC: One-Shot Texture Completion CVPR 2021 Poly-NL: Linear Complexity Non-Local Layers With 3rd Order Polynomials ICCV 2021 Gait Recognition in the Wild: A Benchmark ICCV 2021 WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition CVPR 2021 Sub-center ArcFace: Boosting Face Recognition by Large-scale Noisy Web Faces ECCV 2020 Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning NIPS 2020 GP-NAS: Gaussian Process Based Neural Architecture Search CVPR 2020 RetinaFace: Single-Shot Multi-Level Face Localisation in the Wild CVPR 2020 P-nets: Deep Polynomial Neural Networks CVPR 2020 Synthesizing Coupled 3D Face Modalities by Trunk-Branch Generative Adversarial Networks ECCV 2020 ArcFace: Additive Angular Margin Loss for Deep Face Recognition CVPR 2019 Dense 3D Face Decoding Over 2500FPS: Joint Texture & Shape Convolutional Mesh Decoders CVPR 2019 UV-GAN: Adversarial Facial UV Map Completion for Pose-Invariant Face Recognition CVPR 2018