Chen Qian

76

Papers

277

Total Citations

Papers (76)

Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation

Local Correlation Consistency for Knowledge Distillation

REEF: Representation Encoding Fingerprints for Large Language Models

Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning

AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision Tasks

Parameterization-driven Neural Surface Reconstruction for Object-oriented Editing in Neural Rendering

UniFS: Universal Few-shot Instance Perception with Point Representations

SFDM: Robust Decomposition of Geometry and Reflectance for Realistic Face Rendering from Sparse-view Images

NADER: Neural Architecture Design via Multi-Agent Collaboration

ShotVL: Human-Centric Highlight Frame Retrieval via Language Queries

GreedyNAS: Towards Fast One-Shot NAS With Greedy Supernet

TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting

CentripetalNet: Pursuing High-Quality Keypoint Pairs for Object Detection

A Real-Time Cross-Modality Correlation Filtering Method for Referring Expression Comprehension

When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks

Reformulating HOI Detection As Adaptive Set Prediction

Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search

Prioritized Architecture Sampling With Monto-Carlo Tree Search

Pareidolia Face Reenactment

ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search

BCNet: Searching for Network Width With Bilaterally Coupled Network

SimMatch: Semi-Supervised Learning With Similarity Matching

Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection

Bailando: 3D Dance Generation by Actor-Critic GPT With Choreographic Memory

DyRep: Bootstrapping Training With Dynamic Re-Parameterization

GreedyNASv2: Greedier Search With a Greedy Path Filter

Not All Tokens Are Equal: Human-Centric Visual Analysis via Token Clustering Transformer

A Keypoint-Based Global Association Network for Lane Detection

Learning Where To Learn in Cross-View Self-Supervised Learning

OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation

Aggregation via Separation: Boosting Facial Landmark Detector With Semi-Supervised Style Translation

FAB: A Robust Facial Landmark Detection Framework for Motion-Blurred Videos

Deep Comprehensive Correlation Mining for Image Clustering

Semi-Supervised Monocular 3D Face Reconstruction With End-to-End Shape-Preserved Domain Transfer

TRB: A Novel Triplet Representation for Understanding 2D Human Body

Make a Face: Towards Arbitrary High Fidelity Face Manipulation

TAM: Temporal Adaptive Module for Video Recognition

Learning With Privileged Tasks

Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images

Weakly Supervised Contrastive Learning

SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling

DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-Centric Rendering

Deformable Model-Driven Neural Rendering for High-Fidelity 3D Reconstruction of Human Heads Under Low-View Settings

Simulating Fluids in Real-World Still Images

SimMatchV2: Semi-Supervised Learning with Graph Consistency

HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation

Whole-Body Human Pose Estimation in the Wild

Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation

PoseTrans: A Simple yet Effective Pose Transformation Augmentation for Human Pose Estimation

3D Interacting Hand Pose Estimation by Hand De-Occlusion and Removal

Pose for Everything: Towards Category-Agnostic Pose Estimation

HEAD: HEtero-Assists Distillation for Heterogeneous Object Detectors

StyleGAN-Human: A Data-Centric Odyssey of Human Generation

ScaleNet: Searching for the Model to Scale

ViTAS: Vision Transformer Architecture Search

Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation

Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing

Structure-Aware Editable Morphable Model for 3D Facial Detail Animation and Manipulation

Unsupervised Continual Domain Shift Learning with Multi-Prototype Modeling

Residual Attention Network for Image Classification

Look at Boundary: A Boundary-Aware Face Alignment Algorithm

Multi-Person Articulated Tracking With Spatial and Temporal Embeddings

TransGaGa: Geometry-Aware Unsupervised Image-To-Image Translation

Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation

PPDM: Parallel Point Detection and Matching for Real-Time Human-Object Interaction Detection

3D Sketch-Aware Semantic Scene Completion via Semi-Supervised Structure Prior

DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection

ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding

Agree to Disagree: Adaptive Ensemble Knowledge Distillation in Gradient Space

AOT: Appearance Optimal Transport Based Identity Swapping for Forgery Detection

ReSSL: Relational Self-Supervised Learning with Weak Augmentation

Green Hierarchical Vision Transformer for Masked Image Modeling

Weak-shot Semantic Segmentation via Dual Similarity Transfer

Knowledge Distillation from A Stronger Teacher

RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars

Knowledge Diffusion for Distillation