Discriminator-Cooperated Feature Map Distillation for GAN Compression

SMMix: Self-Motivated Image Mixing for Vision Transformers

Exploring Content Relationships for Distilling Efficient GANs

Shadow Removal by High-Quality Shadow Synthesis

Self-supervised Graph Representation Learning for Black Market Account Detection

Meta Architecture for Point Cloud Analysis

Exploiting the Partly Scratch-off Lottery Ticket for Quantization-Aware Training

Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach

Learning Dynamic Prior Knowledge for Text-to-Face Pixel Synthesis

Cycle Encoding of a StyleGAN Encoder for Improved Reconstruction and Editability

X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval

Dynamic Prototype Mask for Occluded Person Re-Identification

Searching Lightweight Neural Network for Image Signal Processing

Towards Open-Ended Text-to-Face Generation, Combination and Manipulation

ECO-TR: Efficient Correspondences Finding Via Coarse-to-Fine Refinement

Exploring Target Representations for Masked Autoencoders

CycleTrans: Learning Neutral yet Discriminative Features for Visible-Infrared Person Re-Identification

A Closer Look at Branch Classiers of Multi-Exit Architectures

Cycle Encoding of a StyleGAN Encoder for Improved Reconstruction and Editability

Dynamic Prototype Mask for Occluded Person Re-Identification

Clover: Towards A Unified Video-Language Alignment and Fusion Model

Privacy-Preserving Face Recognition with Learnable Privacy Budgets in Frequency Domain

X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval

Learning to Learn Transferable Attack

Dual Contrastive Learning for General Face Forgery Detection

Learning Best Combination for Efficient N:M Sparsity

Super Vision Transformer

Shadow-Aware Dynamic Convolution for Shadow Removal

Deepwalk-aware graph convolutional networks

A Closer Look at Branch Classifiers of Multi-exit Architectures

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

PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation

End-to-End Zero-Shot HOI Detection via Vision and Language Knowledge Distillation

Towards Robust Adversarial Training via Dual-label Supervised and Geometry Constraint

SeqTR: A Simple yet Universal Network for Visual Grounding

Training-free Transformer Architecture Search

ARM: Any-Time Super-Resolution Method

Global2Local: A Joint-Hierarchical Attention for Video Captioning

Factored Attention and Embedding for Unstructured-view Topic-related Ultrasound Report Generation

Differentiated Relevances Embedding for Group-based Referring Expression Comprehension

Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks

Coarse-to-Fine Vision Transformer

Boosting Crowd Counting via Multifaceted Attention

Pruning Networks With Cross-Layer Ranking & k-Reciprocal Nearest Filters

Distilling a Powerful Student Model via Online Knowledge Distillation

Theophylline Extracted from Fu Brick Tea Affects the Metabolism of Preadipocytes and Body Fat in Mice as a Pancreatic Lipase Inhibitor

Plenty is Plague: Fine-Grained Learning for Visual Question Answering

Carrying Out CNN Channel Pruning in a White Box

Disentangling Task-Oriented Representations for Unsupervised Domain Adaptation

Fast Monocular Depth Estimation via Side Prediction Aggregation with Continuous Spatial Refinement

Learning Efficient GANs for Image Translation via Differentiable Masks and Co-Attention Distillation

Knowing What it is: Semantic-Enhanced Dual Attention Transformer

Knowing What to Learn: A Metric-Oriented Focal Mechanism for Image Captioning

Towards Lightweight Transformer Via Group-Wise Transformation for Vision-and-Language Tasks

Multi-Branch Distance-Sensitive Self-Attention Network for Image Captioning

SiamBAN: Target-Aware Tracking With Siamese Box Adaptive Network

1xN Pattern for Pruning Convolutional Neural Networks

Training-free Transformer Architecture Search

Boosting Crowd Counting via Multifaceted Attention

Learning Best Combination for Efficient N:M Sparsity

Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach

Generating Hypergraph-Based High-Order Representations of Whole-Slide Histopathological Images for Survival Prediction

SiMaN: Sign-to-Magnitude Network Binarization

Leveraging Local and Global Cues for Visual Tracking via Parallel Interaction Network

Robust Tracking via Uncertainty-Aware Semantic Consistency

DIFNet: Boosting Visual Information Flow for Image Captioning

IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization

Neural Architecture Search with Representation Mutual Information

Active Teacher for Semi-Supervised Object Detection

ECO-TR: Efficient Correspondences Finding via Coarse-to-Fine Refinement

An Information Theoretic Approach for Attention-Driven Face Forgery Detection

SeqTR: A Simple Yet Universal Network for Visual Grounding

Black-Box Dissector: Towards Erasing-Based Hard-Label Model Stealing Attack

Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks

Privacy-Preserving Face Recognition with Learnable Privacy Budgets in Frequency Domain

Fine-grained Data Distribution Alignment for Post-Training Quantization

PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation

ARM: Any-Time Super-Resolution Method