已发表成果:
WOK 论文 69 篇;
Dynamic capsule attention for visual question answering
Free vqa models from knowledge inertia by pairwise inconformity learning
Multi-task collaborative network for joint referring expression comprehension and segmentation
K-armed Bandit based Multi-Modal Network Architecture Search for Visual Question Answering
Cascade Grouped Attention Network for Referring Expression Segmentation
Attacking Image Captioning towards Accuracy-Preserving Target Words Removal
A Real-Time Global Inference Network for One-Stage Referring Expression Comprehension
Knowledge-Driven Generative Adversarial Network for Text-to-Image Synthesis
Plenty is Plague: Fine-Grained Learning for Visual Question Answering
Uncovering Media Bias via Social Network Learning
RSTNet: Captioning with Adaptive Attention on Visual and Non-Visual Words
TRAR: Routing the Attention Spans in Transformer for Visual Question Answering
Knowing What it is: Semantic-Enhanced Dual Attention Transformer
SeqTR: A Simple yet Universal Network for Visual Grounding
What Goes beyond Multi-modal Fusion in One-stage Referring Expression Comprehension: An Empirical Study
Towards Lightweight Transformer via Group-wise Transformation for Vision-and-Language Tasks
Multi-Branch Distance-Sensitive Self-Attention Network for Image Captioning
PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation
Towards Lightweight Transformer Via Group-Wise Transformation for Vision-and-Language Tasks
Knowing What to Learn: A Metric-Oriented Focal Mechanism for Image Captioning
CycleTrans: Learning Neutral yet Discriminative Features for Visible-Infrared Person Re-Identification
Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach
DIFNet: Boosting Visual Information Flow for Image Captioning
Active Teacher for Semi-Supervised Object Detection
SeqTR: A Simple Yet Universal Network for Visual Grounding
PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation
Towards Real-Time Panoptic Narrative Grounding by an End-to-End Grounding Network
Towards local visual modeling for image captioning
Towards Local Visual Modeling for Image Captioning
Semantic-Guided Selective Representation for Image Captioning
Towards Efficient Visual Adaption via Structural Re-parameterization
Towards End-to-end Semi-supervised Learning for One-stage Object Detection
Learning Dynamic Prior Knowledge for Text-to-Face Pixel Synthesis
Active Teacher for Semi-Supervised Object Detection
Towards Open-Ended Text-to-Face Generation, Combination and Manipulation
Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models
Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach
Adapting Pre-trained Language Models to Vision-Language Tasks via Dynamic Visual Prompting
Approximated Prompt Tuning for Vision-Language Pre-trained Models
HSM-QA: Question Answering System Based on Hierarchical Semantic Matching
Systematic Investigation of Sparse Perturbed Sharpness-Aware Minimization Optimizer
Towards Language-Guided Visual Recognition via Dynamic Convolutions
Towards Real-Time Panoptic Narrative Grounding by an End-to-End Grounding Network
M3PS: End-to-End Multi-Grained Multi-Modal Attribute-Aware Product Summarization in E-commerce
A Survivor in the Era of Large-Scale Pretraining: An Empirical Study of One-Stage Referring Expression Comprehension
Parameter and Computation Efficient Transfer Learning for Vision-Language Pre-trained Models
RefTeacher: A Strong Baseline for Semi-Supervised Referring Expression Comprehension
RefCLIP: A Universal Teacher for Weakly Supervised Referring Expression Comprehension
Towards Omni-supervised Referring Expression Segmentation
PixelFace plus : Towards Controllable Face Generation and Manipulation with Text Descriptions and Segmentation Masks
Towards Efficient Diffusion-Based Image Editing with Instant Attention Masks
Fast Text-to-3D-Aware Face Generation and Manipulation via Direct Cross-modal Mapping and Geometric Regularization
Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models
Towards Efficient Diffusion-Based Image Editing with Instant Attention Masks
Not All Attention is Needed: Parameter and Computation Efficient Transfer Learning for Multi-modal Large Language Models
CycleTrans: Learning Neutral Yet Discriminative Features via Cycle Construction for Visible-Infrared Person Re-Identification
Parameter and Computation Efficient Transfer Learning for Vision-Language Pre-trained Models
Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models
Deep Instruction Tuning for Segment Anything Model
MMAPS: End-to-End Multi-Grained Multi-Modal Attribute-Aware Product Summarization
Image Captioning via Dynamic Path Customization
Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models
Deep hybrid transformer network for robust modulation classification in wireless communications
Parameter and Computation Efficient Transfer Learning for Vision-Language Pre-trained Models
Towards Real-Time Panoptic Narrative Grounding by an End-to-End Grounding Network
Image Captioning via Dynamic Path Customization
Towards Efficient Diffusion-Based Image Editing with Instant Attention Masks
MoIL: Momentum Imitation Learning for Efficient Vision-Language Adaptation
M<SUP>3</SUP>ixup: 3 ixup: A multi-modal data augmentation approach for image captioning