Chunhua Shen
Identifiers
- name variant Chunhua Shen 0.60 · backfill
Papers (193)
- Geo-Align: Video Generation Alignment via Metric Geometry Reward cs.CV · 2026 · author #4
- MARBLE: Multi-Aspect Reward Balance for Diffusion RL cs.CV · 2026 · author #6
- Unlocking the Power of Critical Factors for 3D Visual Geometry Estimation cs.CV · 2026 · author #7
- Exploring Spatial Intelligence from a Generative Perspective cs.CV · 2026 · author #12
- MMControl: Unified Multi-Modal Control for Joint Audio-Video Generation cs.CV · 2026 · author #7
- OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering cs.CV · 2026 · author #10
- TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders cs.CV · 2026 · author #7
- AGILE: Hand-Object Interaction Reconstruction from Video via Agentic Generation cs.CV · 2026 · author #9
- Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality cs.CV · 2025 · author #10
- Probabilistic Modeling of Multi-rater Medical Image Segmentation for Diversity and Personalization cs.CV · 2025 · author #6
- Evolutionary Profiles for Protein Fitness Prediction cs.LG · 2025 · author #8
- StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation cs.RO · 2025 · author #9
- NoTVLA: Semantics-Preserving Robot Adaptation via Narrative Action Interfaces cs.RO · 2025 · author #12
- $\pi^3$: Permutation-Equivariant Visual Geometry Learning cs.CV · 2025 · author #9
- MobileVLM V2: Faster and Stronger Baseline for Vision Language Model cs.CV · 2024 · author #11
- MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices cs.CV · 2023 · author #11
- Attention-guided Network for Ghost-free High Dynamic Range Imaging cs.CV · 2019 · author #5
- Architecture Search of Dynamic Cells for Semantic Video Segmentation cs.CV · 2019 · author #3
- Knowledge Adaptation for Efficient Semantic Segmentation cs.CV · 2019 · author #2
- CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning cs.CV · 2019 · author #5
- Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation cs.CV · 2019 · author #3
- Associatively Segmenting Instances and Semantics in Point Clouds cs.CV · 2019 · author #4
- Salient Object Detection with Lossless Feature Reflection and Weighted Structural Loss cs.CV · 2019 · author #4
- Embedding Bilateral Filter in Least Squares for Efficient Edge-preserving Image Smoothing cs.GR · 2018 · author #4
- Neighbourhood Watch: Referring Expression Comprehension via Language-guided Graph Attention Networks cs.CV · 2018 · author #4
- Coarse-to-fine: A RNN-based hierarchical attention model for vehicle re-identification cs.CV · 2018 · author #4
- Visual Question Answering as Reading Comprehension cs.CV · 2018 · author #3
- RGB-D Based Action Recognition with Light-weight 3D Convolutional Networks cs.CV · 2018 · author #5
- Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation cs.CV · 2018 · author #2
- Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition cs.CV · 2018 · author #3
- Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells cs.CV · 2018 · author #3
- Light-Weight RefineNet for Real-Time Semantic Segmentation cs.CV · 2018 · author #2
- Correlation Propagation Networks for Scene Text Detection cs.CV · 2018 · author #5
- Diagnostics in Semantic Segmentation cs.CV · 2018 · author #2
- Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations cs.CV · 2018 · author #5
- Towards Effective Deep Embedding for Zero-Shot Learning cs.CV · 2018 · author #4
- Training Compact Neural Networks with Binary Weights and Low Precision Activations cs.CV · 2018 · author #2
- Troy: Give Attention to Saliency and for Saliency cs.CV · 2018 · author #3
- Learning to predict crisp boundaries cs.CV · 2018 · author #2
- Deep attention-based classification network for robust depth prediction cs.CV · 2018 · author #3
- Adversarial Learning with Local Coordinate Coding cs.CV · 2018 · author #4
- Adaptive Importance Learning for Improving Lightweight Image Super-resolution Network cs.CV · 2018 · author #3
- Monocular Depth Estimation with Augmented Ordinal Depth Relationships cs.CV · 2018 · author #4
- Multi-label Learning Based Deep Transfer Neural Network for Facial Attribute Classification cs.CV · 2018 · author #5
- HyperFusion-Net: Densely Reflective Fusion for Salient Object Detection cs.CV · 2018 · author #3
- VITAL: VIsual Tracking via Adversarial Learning cs.CV · 2018 · author #7
- An end-to-end TextSpotter with Explicit Alignment and Attention cs.CV · 2018 · author #4
- Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation cs.CV · 2018 · author #5
- Non-rigid Object Tracking via Deep Multi-scale Spatial-temporal Discriminative Saliency Maps cs.CV · 2018 · author #6
- Agile Amulet: Real-Time Salient Object Detection with Contextual Attention cs.CV · 2018 · author #5
- Salient Object Detection by Lossless Feature Reflection cs.CV · 2018 · author #4
- Edge-Preserving Piecewise Linear Image Smoothing Using Piecewise Constant Filters cs.GR · 2018 · author #5
- Automatic Image Cropping for Visual Aesthetic Enhancement Using Deep Neural Networks and Cascaded Regression cs.CV · 2017 · author #3
- Real-time Semantic Image Segmentation via Spatial Sparsity cs.CV · 2017 · author #2
- FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors cs.CV · 2017 · author #4
- Repulsion Loss: Detecting Pedestrians in a Crowd cs.CV · 2017 · author #6
- Asking the Difficult Questions: Goal-Oriented Visual Question Generation via Intermediate Rewards cs.CV · 2017 · author #3
- Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning cs.CV · 2017 · author #3
- Kill Two Birds with One Stone: Weakly-Supervised Neural Network for Image Annotation and Tag Refinement cs.CV · 2017 · author #4
- Parallel Attention: A Unified Framework for Visual Object Discovery through Dialogs and Queries cs.CV · 2017 · author #3
- Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization cs.CV · 2017 · author #2
- Towards End-to-End Car License Plates Detection and Recognition with Deep Neural Networks cs.CV · 2017 · author #3
- Beyond Low Rank: A Data-Adaptive Tensor Completion Method cs.CV · 2017 · author #4
- Relative Depth Order Estimation Using Multi-scale Densely Connected Convolutional Networks cs.CV · 2017 · author #3
- Unsupervised Object Discovery and Co-Localization by Deep Descriptor Transforming cs.CV · 2017 · author #4
- When Unsupervised Domain Adaptation Meets Tensor Representations cs.CV · 2017 · author #6
- Visually Aligned Word Embeddings for Improving Zero-shot Learning cs.CV · 2017 · author #3
- Visual Question Answering with Memory-Augmented Networks cs.CV · 2017 · author #2
- Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks cs.CV · 2017 · author #3
- Adversarial Generation of Training Examples: Applications to Moving Vehicle License Plate Recognition cs.CV · 2017 · author #4
- TasselNet: Counting maize tassels in the wild via local counts regression network cs.CV · 2017 · author #5
- Care about you: towards large-scale human-centric visual relationship detection cs.CV · 2017 · author #3
- Weakly Supervised Semantic Segmentation Based on Web Image Co-segmentation cs.CV · 2017 · author #4
- Deep Descriptor Transforming for Image Co-Localization cs.CV · 2017 · author #6
- Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation cs.CV · 2017 · author #2
- Robust Guided Image Filtering cs.CV · 2017 · author #3
- Structured Learning of Tree Potentials in CRF for Image Segmentation cs.CV · 2017 · author #4
- Towards Context-aware Interaction Recognition cs.CV · 2017 · author #3
- Learning Multi-level Region Consistency with Dense Multi-label Networks for Semantic Segmentation cs.CV · 2017 · author #3
- Deep Learning Features at Scale for Visual Place Recognition cs.CV · 2017 · author #6
- The VQA-Machine: Learning How to Use Existing Vision Algorithms to Answer New Questions cs.CV · 2016 · author #3
- From Motion Blur to Motion Flow: a Deep Learning Solution for Removing Heterogeneous Motion Blur cs.CV · 2016 · author #6
- Multi-Label Image Classification with Regional Latent Semantic Dependencies cs.CV · 2016 · author #3
- Wider or Deeper: Revisiting the ResNet Model for Visual Recognition cs.CV · 2016 · author #2
- Sequential Person Recognition in Photo Albums with a Recurrent Network cs.CV · 2016 · author #5
- Attend in groups: a weakly-supervised deep learning framework for learning from web data cs.CV · 2016 · author #4
- Learning Deep Representations Using Convolutional Auto-encoders with Symmetric Skip Connections cs.CV · 2016 · author #3
- RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation cs.CV · 2016 · author #3
- Exploiting Depth from Single Monocular Images for Object Detection and Semantic Segmentation cs.CV · 2016 · author #2
- Visual Question Answering: A Survey of Methods and Datasets cs.CV · 2016 · author #4
- Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections cs.CV · 2016 · author #2
- Where to Focus: Query Adaptive Matching for Instance Retrieval Using Convolutional Feature Maps cs.CV · 2016 · author #5
- FVQA: Fact-based Visual Question Answering cs.CV · 2016 · author #3
- Deep Recurrent Convolutional Networks for Video-based Person Re-identification: An End-to-End Approach cs.CV · 2016 · author #2
- Deep Linear Discriminant Analysis on Fisher Networks: A Hybrid Architecture for Person Re-identification cs.CV · 2016 · author #2
- Bridging Category-level and Instance-level Semantic Image Segmentation cs.CV · 2016 · author #2
- Estimating Depth from Monocular Images as Classification Using Deep Fully Convolutional Residual Networks cs.CV · 2016 · author #3
- Crowd Counting via Weighted VLAD on Dense Attribute Feature Maps cs.CV · 2016 · author #2
- High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks cs.CV · 2016 · author #2
- Less is more: zero-shot learning from online textual documents with noise suppression cs.CV · 2016 · author #3
- Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections cs.CV · 2016 · author #2
- Image Co-localization by Mimicking a Good Detector's Confidence Score Distribution cs.CV · 2016 · author #3
- Pushing the Limits of Deep CNNs for Pedestrian Detection cs.CV · 2016 · author #3
- Exploring Context with Deep Structured models for Semantic Segmentation cs.CV · 2016 · author #2
- Fast Training of Triplet-based Deep Binary Embedding Networks cs.CV · 2016 · author #3
- Image Captioning and Visual Question Answering Based on Attributes and External Knowledge cs.CV · 2016 · author #2
- Structured Learning of Binary Codes with Column Generation cs.LG · 2016 · author #3
- Hi Detector, What's Wrong with that Object? Identifying Irregular Object From Images by Modelling the Detection Score Distribution cs.CV · 2016 · author #3
- Order-aware Convolutional Pooling for Video Based Action Recognition cs.CV · 2016 · author #3
- Discriminative Training of Deep Fully-connected Continuous CRF with Task-specific Loss cs.CV · 2016 · author #3
- PersonNet: Person Re-identification with Deep Convolutional Neural Networks cs.CV · 2016 · author #2
- Reading Car License Plates Using Deep Convolutional Neural Networks and LSTMs cs.CV · 2016 · author #2
- Compositional Model based Fisher Vector Coding for Image Classification cs.CV · 2016 · author #3
- Data Driven Robust Image Guided Depth Map Restoration cs.CV · 2015 · author #3
- Structured learning of metric ensembles with application to person re-identification cs.CV · 2015 · author #3
- Ask Me Anything: Free-form Visual Question Answering Based on Knowledge from External Sources cs.CV · 2015 · author #3
- Explicit Knowledge-based Reasoning for Visual Question Answering cs.CV · 2015 · author #3
- Fast detection of multiple objects in traffic scenes with a common detection framework cs.CV · 2015 · author #3
- Cross-convolutional-layer Pooling for Image Recognition cs.CV · 2015 · author #2
- Online Metric-Weighted Linear Representations for Robust Visual Tracking cs.CV · 2015 · author #2
- Mining Mid-level Visual Patterns with Deep CNN Activations cs.CV · 2015 · author #3
- Deeply Learning the Messages in Message Passing Inference cs.CV · 2015 · author #2
- What value do explicit high level concepts have in vision to language problems? cs.CV · 2015 · author #2
- Learning discriminative trajectorylet detector sets for accurate skeleton-based action recognition cs.CV · 2015 · author #3
- Efficient SDP Inference for Fully-connected CRFs Based on Low-rank Decomposition cs.CV · 2015 · author #2
- Efficient piecewise training of deep structured models for semantic segmentation cs.CV · 2015 · author #2
- CRF Learning with CNN Features for Image Segmentation cs.CV · 2015 · author #3
- Supervised Discrete Hashing cs.CV · 2015 · author #2
- Learning to rank in person re-identification with metric ensembles cs.CV · 2015 · author #2
- Temporal Pyramid Pooling Based Convolutional Neural Networks for Action Recognition cs.CV · 2015 · author #3
- Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields cs.CV · 2015 · author #2
- Unsupervised Feature Learning for Dense Correspondences across Scenes cs.CV · 2015 · author #2
- Hashing on Nonlinear Manifolds cs.CV · 2014 · author #2
- Large-scale Binary Quadratic Optimization Using Semidefinite Relaxation and Applications cs.CV · 2014 · author #2
- The Treasure beneath Convolutional Layers: Cross-convolutional-layer Pooling for Image Classification cs.CV · 2014 · author #2
- Encoding High Dimensional Local Features by Sparse Coding Based Fisher Vectors cs.CV · 2014 · author #2
- Deep Convolutional Neural Fields for Depth Estimation from a Single Image cs.CV · 2014 · author #2
- Mid-level Deep Pattern Mining cs.CV · 2014 · author #3
- Pedestrian Detection with Spatially Pooled Features and Structured Ensemble Learning cs.CV · 2014 · author #2
- A Computational Model of the Short-Cut Rule for 2D Shape Decomposition cs.CV · 2014 · author #2
- Supervised Hashing Using Graph Cuts and Boosted Decision Trees cs.LG · 2014 · author #2
- Optimizing Ranking Measures for Compact Binary Code Learning cs.LG · 2014 · author #2
- Strengthening the Effectiveness of Pedestrian Detection with Spatially Pooled Features cs.CV · 2014 · author #2
- Face Identification with Second-Order Pooling cs.CV · 2014 · author #2
- Face Image Classification by Pooling Raw Features cs.CV · 2014 · author #2
- Efficient Semidefinite Branch-and-Cut for MAP-MRF Inference cs.CV · 2014 · author #2
- Learning Deep Convolutional Features for MRI Based Alzheimer's Disease Classification cs.CV · 2014 · author #2
- Fast Supervised Hashing with Decision Trees for High-Dimensional Data cs.CV · 2014 · author #2
- Large-margin Learning of Compact Binary Image Encodings cs.CV · 2014 · author #2
- Efficient Semidefinite Spectral Clustering via Lagrange Duality cs.LG · 2014 · author #2
- Extrinsic Methods for Coding and Dictionary Learning on Grassmann Manifolds cs.LG · 2014 · author #3
- A Generalized Probabilistic Framework for Compact Codebook Creation cs.CV · 2014 · author #3
- From Kernel Machines to Ensemble Learning cs.LG · 2014 · author #1
- Context-Aware Hypergraph Construction for Robust Spectral Clustering cs.CV · 2014 · author #3
- Constraint Reduction using Marginal Polytope Diagrams for MAP LP Relaxations cs.CV · 2013 · author #4
- Fast Training of Effective Multi-class Boosting Using Coordinate Descent Optimization cs.CV · 2013 · author #2
- Contextual Hypergraph Modelling for Salient Object Detection cs.CV · 2013 · author #3
- Dictionary Learning and Sparse Coding on Grassmann Manifolds: An Extrinsic Solution cs.CV · 2013 · author #3
- Online Unsupervised Feature Learning for Visual Tracking cs.CV · 2013 · author #2
- Efficient pedestrian detection by directly optimize the partial area under the ROC curve cs.CV · 2013 · author #2
- Multiple Kernel Learning in the Primal for Multi-modal Alzheimer's Disease Classification cs.LG · 2013 · author #3
- Characterness: An Indicator of Text in the Wild cs.CV · 2013 · author #3
- Generic Image Classification Approaches Excel on Face Recognition cs.CV · 2013 · author #2
- A General Two-Step Approach to Learning-Based Hashing cs.LG · 2013 · author #2
- A scalable stage-wise approach to large-margin multi-class loss based boosting cs.LG · 2013 · author #2
- Fast Approximate L_infty Minimization: Speeding Up Robust Regression cs.CV · 2013 · author #2
- A Fast Semidefinite Approach to Solving Binary Quadratic Problems cs.CV · 2013 · author #2
- Inductive Hashing on Manifolds cs.LG · 2013 · author #2
- Asymmetric Pruning for Learning Cascade Detectors cs.CV · 2013 · author #2
- A Survey of Appearance Models in Visual Object Tracking cs.CV · 2013 · author #3
- Learning Hash Functions Using Column Generation cs.LG · 2013 · author #3
- An Efficient Dual Approach to Distance Metric Learning cs.LG · 2013 · author #1
- RandomBoost: Simplified Multi-class Boosting through Randomization cs.LG · 2013 · author #2
- Training Effective Node Classifiers for Cascade Classification cs.CV · 2013 · author #1
- A Direct Approach to Multi-class Boosting and Extensions cs.LG · 2012 · author #1
- Incremental Learning of 3D-DCT Compact Representations for Robust Visual Tracking cs.CV · 2012 · author #3
- Non-sparse Linear Representations for Visual Tracking with Online Reservoir Metric Learning cs.CV · 2012 · author #2
- Face Recognition using Optimal Representation Ensemble cs.CV · 2011 · author #2
- Positive Semidefinite Metric Learning Using Boosting-like Algorithms cs.CV · 2011 · author #1
- Real-time Visual Tracking Using Sparse Representation cs.CV · 2010 · author #2
- Face Detection with Effective Feature Extraction cs.CV · 2010 · author #2
- Totally Corrective Multiclass Boosting with Binary Weak Learners cs.LG · 2010 · author #2
- Asymmetric Totally-corrective Boosting for Real-time Object Detection cs.CV · 2010 · author #2
- Effective Pedestrian Detection Using Center-symmetric Local Binary/Trinary Patterns cs.CV · 2010 · author #2
- Totally Corrective Boosting for Regularized Risk Minimization cs.AI · 2010 · author #1
- Optimally Training a Cascade Classifier cs.CV · 2010 · author #1
- Incremental Training of a Detector Using Online Sparse Eigen-decomposition cs.CV · 2010 · author #2
- LACBoost and FisherBoost: Optimally Building Cascade Classifiers cs.CV · 2010 · author #1
- Scalable Large-Margin Mahalanobis Distance Metric Learning cs.CV · 2010 · author #1
- Positive Semidefinite Metric Learning with Boosting cs.CV · 2009 · author #1
- Generalized Kernel-based Visual Tracking cs.CV · 2009 · author #1
- Boosting through Optimization of Margin Distributions cs.LG · 2009 · author #1
- Efficiently Learning a Detection Cascade with Sparse Eigenvectors cs.MM · 2009 · author #1
Mentions
- 1302.0963 #2 · backfill · confidence 0.70 Chunhua Shen
- 1301.2032 #1 · backfill · confidence 0.70 Chunhua Shen
- 2605.23903 #4 · arxiv_oai · confidence 0.70 Chunhua Shen
- 1210.4601 #1 · backfill · confidence 0.70 Chunhua Shen
- 1207.3389 #3 · backfill · confidence 0.70 Chunhua Shen
- 1204.2912 #2 · backfill · confidence 0.70 Chunhua Shen
- 1110.0264 #2 · backfill · confidence 0.70 Chunhua Shen
- 1104.4704 #1 · backfill · confidence 0.70 Chunhua Shen
- 1012.2603 #2 · backfill · confidence 0.70 Chunhua Shen
- 1009.5758 #2 · backfill · confidence 0.70 Chunhua Shen
- 1009.3702 #2 · backfill · confidence 0.70 Chunhua Shen
- 1009.3078 #2 · backfill · confidence 0.70 Chunhua Shen
- 1009.0892 #2 · backfill · confidence 0.70 Chunhua Shen
- 1008.5188 #1 · backfill · confidence 0.70 Chunhua Shen
- 1008.3742 #1 · backfill · confidence 0.70 Chunhua Shen
- 2402.03766 #11 · arxiv_oai · confidence 0.70 Chunhua Shen
- 1005.4118 #2 · backfill · confidence 0.70 Chunhua Shen
- 1005.4103 #1 · backfill · confidence 0.70 Chunhua Shen
- 1003.0487 #1 · backfill · confidence 0.70 Chunhua Shen
- 0910.2279 #1 · backfill · confidence 0.70 Chunhua Shen
- 2312.16886 #11 · arxiv_oai · confidence 0.70 Chunhua Shen
- 0905.2463 #1 · backfill · confidence 0.70 Chunhua Shen
- 0904.2037 #1 · backfill · confidence 0.70 Chunhua Shen
- 0903.3103 #1 · backfill · confidence 0.70 Chunhua Shen
Frequent Coauthors
- Anton van den Hengel 76 shared papers
- Peng Wang 30 shared papers
- Lingqiao Liu 27 shared papers
- Ian Reid 25 shared papers
- Guosheng Lin 24 shared papers
- Qi Wu 15 shared papers
- Sakrapee Paisitkriangkrai 15 shared papers
- Anthony Dick 14 shared papers
- Fayao Liu 13 shared papers
- Hao Chen 13 shared papers
- Heng Tao Shen 11 shared papers
- Qinfeng Shi 10 shared papers
- Bohan Zhuang 9 shared papers
- Wei Liu 8 shared papers
- Yao Li 8 shared papers
- Fumin Shen 7 shared papers
- Lei Wang 7 shared papers
- Pingping Zhang 7 shared papers
- Xi Li 7 shared papers
- Huchuan Lu 6 shared papers