Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation

Adaptive Feature Selection for No-Reference Image Quality Assessment using Contrastive Mitigating Semantic Noise Sensitivity

PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization

Aligning and Prompting Everything All at Once for Universal Visual Perception

Lottery Jackpots Exist in Pre-Trained Models

X-Dreamer: Creating High-quality 3D Content by Bridging the Domain Gap Between Text-to-2D and Text-to-3D Generation

Code Search Debiasing: Improve Search Results beyond Overall Ranking Performance

I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization

Semi-Supervised Panoptic Narrative Grounding

Semi-Supervised Panoptic Narrative Grounding

PixelFace plus : Towards Controllable Face Generation and Manipulation with Text Descriptions and Segmentation Masks

Learning Occlusion Disentanglement with Fine-grained Localization for Occluded Person Re-identification

Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation

Improving Human-Object Interaction Detection via Virtual Image Learning

Beat: Bi-directional One-to-Many Embedding Alignment for Text-based Person Retrieval

Shadow Removal by High-Quality Shadow Synthesis

CAPro: Webly Supervised Learning with Cross-Modality Aligned Prototypes

JM3D & JM3D-LLM: Elevating 3D Representation with Joint Multi-modal Cues

Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs

AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration

Parameter and Computation Efficient Transfer Learning for Vision-Language Pre-trained Models

Towards Unified Token Learning for Vision-Language Tracking

DLIP: Distilling Language-Image Pre-training

M3PS: End-to-End Multi-Grained Multi-Modal Attribute-Aware Product Summarization in E-commerce

EALink: An Efficient and Accurate Pre-trained Framework for Issue-Commit Link Recovery

HODN: Disentangling Human-Object Feature for HOI Detection

Towards Language-Guided Visual Recognition via Dynamic Convolutions

Continual Face Forgery Detection via Historical Distribution Preserving

Pseudo-label Alignment for Semi-supervised Instance Segmentation

Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation

Improving Human-Object Interaction Detection via Virtual Image Learning

Towards General Visual-Linguistic Face Forgery Detection

REFBERT: A Two-Stage Pre-trained Framework for Automatic Rename Refactoring

Systematic Investigation of Sparse Perturbed Sharpness-Aware Minimization Optimizer

CF-ViT: A General Coarse-to-Fine Method for Vision Transformer

OMPQ: Orthogonal Mixed Precision Quantization

Approximated Prompt Tuning for Vision-Language Pre-trained Models

MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Shadow-Aware Dynamic Convolution for Shadow Removal

Spatial Re-parameterization for N:M Sparsity

STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection

Adapting Pre-trained Language Models to Vision-Language Tasks via Dynamic Visual Prompting

Towards local visual modeling for image captioning

CamoDiffusion: Camouflaged Object Detection via Conditional Diffusion Models

DiffRate: Differentiable Compression Rate for Efficient Vision Transformers

RefBERT: A Two-Stage Pre-trained Framework for Automatic Rename Refactoring

Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models

MultiQuant: A Novel Multi-Branch Topology Method for Arbitrary Bit-width Network Quantization

Distribution-Flexible Subset Quantization for Post-Quantizing Super-Resolution Networks

InterFormer: Real-time Interactive Image Segmentation

Latent Feature Relation Consistency for Adversarial Robustness

X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance

CAT: Collaborative Adversarial Training

You Only Segment Once: Towards Real-Time Panoptic Segmentation

Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective

Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-Identification

Active Teacher for Semi-Supervised Object Detection

DistilPose: Tokenized Pose Regression with Heatmap Distillation

Dynamic Support Network for Few-Shot Class Incremental Learning

HGNN<SUP>+</SUP>: General Hypergraph Neural Networks

Self-supervised Graph Representation Learning for Black Market Account Detection

Towards End-to-end Semi-supervised Learning for One-stage Object Detection

Towards Efficient Visual Adaption via Structural Re-parameterization

Towards Local Visual Modeling for Image Captioning

Bi-directional Masks for Efficient N:M Sparse Training

REAL-TIME IMAGE DEMOIRéING ON MOBILE DEVICES

Exploring Invariant Representation for Visible-Infrared Person Re-Identification

Spectral Aware Softmax for Visible-Infrared Person Re-Identification

Unsupervised Domain Adaptation on Person Re-Identification via Dual-level Asymmetric Mutual Learning

DDPNAS: Efficient Neural Architecture Search via Dynamic Distribution Pruning

Training Compact CNNs for Image Classification Using Dynamic-Coded Filter Fusion

Prioritized Subnet Sampling for Resource-Adaptive Supernet Training

Transformer Tracking via Frequency Fusion

Positive-Sample-Free Object Tracking via a Soft Constraint

Toward Unified Token Learning for Vision-Language Tracking

HODN: Disentangling Human-Object Feature for HOI Detection

Semantically Consistent Visual Representation for Adversarial Robustness

Bilateral Knowledge Interaction Network for Referring Image Segmentation

A Survivor in the Era of Large-Scale Pretraining: An Empirical Study of One-Stage Referring Expression Comprehension

Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective

RefCLIP: A Universal Teacher for Weakly Supervised Referring Expression Comprehension

You Only Segment Once: Towards Real-Time Panoptic Segmentation

Bi-directional Masks for Efficient N:M Sparse Training

Interactive Object Placement with Reinforcement Learning

DistilPose: Tokenized Pose Regression with Heatmap Distillation

RefTeacher: A Strong Baseline for Semi-Supervised Referring Expression Comprehension

Meta Architecture for Point Cloud Analysis

Discriminator-Cooperated Feature Map Distillation for GAN Compression

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

STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection

EALink: An Efficient and Accurate Pre-trained Framework for Issue-Commit Link Recovery

AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration

Category-aware Allocation Transformer for Weakly Supervised Object Localization

SMMix: Self-Motivated Image Mixing for Vision Transformers

X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance

InterFormer Real-time Interactive Image Segmentation

DiffRate : Differentiable Compression Rate for Efficient Vision Transformers

Automatic Network Pruning via Hilbert-Schmidt Independence Criterion Lasso under Information Bottleneck Principle

Pseudo-label Alignment for Semi-supervised Instance Segmentation

Parameter and Computation Efficient Transfer Learning for Vision-Language Pre-trained Models

Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models

Improving Adversarial Robustness via Information Bottleneck Distillation

Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning

REAL-TIME IMAGE DEMOIRéING ON MOBILE DEVICES