Publications

FlowFixer: Towards Detail-Preserving Subject-Driven Generation

Focus, Don’t Prune: Identifying Instruction-Relevant Regions for Information-Rich Image Understanding

MambaEye: A Size-Agnostic Visual Encoder with Causal Sequential Processing

Image-Guided Semantic Pseudo-LiDAR Point Generation for 3D Object Detection

Style-Friendly SNR Sampler for Style-Driven Generation

Towards Failure-Resilient Lifelong Learning Agents through Scene Graph-Guided Proactive Replanning

3D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformation

DiffExp: Efficient Exploration in Reward Fine-tuning for Text-to-Image Diffusion Models

Encoder-only Next Token Prediction

Fast and Precise Multimodal Spatiotemporal Calibration via Periodic-Activated 2D Gaussian Splatting

Fpanet: Frequency-based video demoireing using frame-level post alignment

GUIDE-CoT: Goal-driven and user-informed dynamic estimation for pedestrian trajectory using chain-of-thought

Hard-Negative Prototype-Based Regularization for Few-Shot Class-Incremental Learning

Know "No" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP

Parameter-Efficient 12-Lead ECG Reconstruction from a Single Lead

Querying Labeled Time Series Data with Scenario Programs

Scene Graph-Guided Proactive Replanning for Failure-Resilient Embodied Agents

SemanticControl: A Training-free Approach for Handling Loosely Aligned Visual Conditions in ControlNet

ViTA-PAR: Visual and Textual Attribute Alignment with Attribute Prompting for Pedestrian Attribute Recognition

Watermarking for Factuality: Guiding Vision-Language Models Toward Truth via Tri-layer Contrastive Decoding

Advancing Cross-Domain Generalizability in Face Anti-Spoofing: Insights, Design, and Metrics

Audio-guided implicit neural representation for local image stylization

BEVMap: Map-Aware BEV Modeling for 3D Perception

CMDA: Cross-Modal and Domain Adversarial Adaptation for LiDAR-Based 3D Object Detection

Clustering-based Image-Text Graph Matching for Domain Generalization

Enhanced Motion Forecasting with Visual Relation Reasoning

Finetuning Pre-trained Model with Limited Data for LiDAR-based 3D Object Detection by Bridging Domain Gaps

FoMu-SSL: Foundation Model-Guided Multi-Sensor Self-Supervised Learning for Remote Sensing

Higher-order Relational Reasoning for Pedestrian Trajectory Prediction

InstructBooth: Instruction-following Personalized Text-to-Image Generation

Just Add $100 More: Augmenting Pseudo-LiDAR Point Cloud for Resolving Class-imbalance Problem

LRSLAM: Low-Rank Representation of Signed Distance Fields in Dense Visual SLAM System

Learning Temporal Cues by Predicting Objects Move for Multi-camera 3D Object Detection

Localization and Manipulation of Immoral Visual Cues for Safe Text-to-Image Generation

Mitigating the Linguistic Gap with Phonemic Representations for Robust Cross-lingual Transfer

Robust sound-guided image manipulation

Text-Driven Prototype Learning for Few-Shot Class-Incremental Learning

Toward Interactive Regional Understanding in Vision-Large Language Models

Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection

VisionTrap: Vision-Augmented Trajectory Prediction Guided by Textual Descriptions

Who Should Have Been Focused: Transferring Attention-Based Knowledge from Future Observations for Trajectory Prediction

An Embedding-Dynamic Approach to Self-Supervised Learning

CloudNet: A LiDAR-based face anti-spoofing model that is robust against light variation

Ensuring visual commonsense morality for text-to-image generation

Improving Visual Prompt Tuning for Self-supervised Vision Transformers

Resolving class imbalance for lidar-based object detector by dynamic weight average and contextual ground truth sampling

The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion

Weakly Supervised Referring Image Segmentation with Intra-Chunk and Inter-Chunk Consistency

Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization

Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization

Bridging the domain gap towards generalization in automatic colorization

Grounding visual representations with texts for domain generalization

Inter-domain curriculum learning for domain generalization

Occupancy flow fields for motion forecasting in autonomous driving

Ora3d: Overlap region aware multi-view 3d object detection

Perception Prioritized Training of Diffusion Models

Sound-guided semantic image manipulation

Sound-guided semantic video generation

Stopnet: Scalable trajectory and occupancy prediction for urban autonomous driving

Weakly Supervised Semantic Segmentation using Out-of-Distribution Data

Zero-shot visual commonsense immorality prediction

A Scenario-Based Platform for Testing Autonomous Vehicle Behavior Prediction Models in Simulation

Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation

Audio-Guided Image Manipulation for Artistic Paintings

BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation

Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation

Selfreg: Self-supervised contrastive regularization for domain generalization

Toward Spatially Unbiased Generative Models

Toward explainable and advisable model for self‐driving cars

Towards an Interpretable Deep Driving Network by Attentional Bottleneck

Advisable learning for self-driving vehicles by internalizing observation-to-action rules

Attentional bottleneck: Towards an interpretable deep driving network

Periphery-fovea multi-resolution driving model guided by human attention

FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference

Frame-to-Frame Aggregation of Active Regions in Web Videos for Weakly Supervised Semantic Segmentation

Grounding human-to-vehicle advice for self-driving vehicles

Msnet: Mutual suppression network for disentangled video representations

Deep traffic light detection for self-driving cars from a large-scale dataset

Explainable deep driving by visualizing causal attention

Predicting driver attention in critical situations

Textual explanations for self-driving vehicles

Interpretable learning for self-driving cars by visualizing causal attention