Meet ApplyKite Twin, the application assistant that learns with you

Meet your Twin, it learns with you

Your Twin learns with you

Launch week codes:30% off annual Pro20% off monthly Pro

Ends in00h00m00s

Xu Jia

Associate Professor

Dalian University of Technology

China

Research Interests

Articles (20)

Year:

2026

Year:

2026

Year:

2026

Year:

2026

Year:

2026

Year:

2026

Year:

2026

Year:

2025

Year:

2025

Year:

2025

Year:

2025

Year:

2025

Year:

2025

Year:

2025

Year:

2025

Year:

2025

Year:

2024

Year:

2024

Year:

2024

Year:

2024

Collaborators (1)

Wei Zhou

Assistant Professor

Cardiff University

UNITED KINGDOM

View details

ApplyKite TwinLearns as you apply

Make your next move.

Prepare your application

Review drafts before you send them.

Xu Jia

Research Interests

Articles (20)

Self-distilled learning of adaptive interval 3D lookup tables on real-time image enhancement

Video Demoiréing With Spatial–Temporal Filtering in Frequency Domain

Event-based Lip Reading with Triplane Fusion Network

EvMic: Event-Based Non-Contact Sound Recovery From Effective Spatial–Temporal Modeling

Exploiting Cross-Task Synergy via Frequency-Driven Hierarchical Learning for Multi-Task Dense Prediction

Perceptual Quality Assessment of Real-World Noise in Ultra-High-Definition Images

TemLo: Temporal-Local Synergy Enhanced RWKV for Audio-Visual Segmentation

Regularizing Subspace Redundancy of Low-Rank Adaptation

CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation

Event-Assisted Recurrent Network for Arbitrary-Temporal-Scale Blurry Image Unfolding

Hierarchical Frequency-Based Upsampling and Refining for HEVC Compressed Video Enhancement

MoBox: Enhancing Video Object Segmentation With Motion-Augmented Box Supervision

CharacterFactory: Sampling Consistent Characters With GANs for Diffusion Models

Perception-Oriented Bidirectional Attention Network for Image Super-Resolution Quality Assessment

Pyramid Learnable Bandpass Filters for Ultra-High-Definition Image Demoiréing

StableIdentity: Inserting Anybody Into Anywhere at First Sight

Deformable Dynamic Sampling and Dynamic Predictable Mask Mining for Image Inpainting

Neural image re-exposure

Customizing Text-to-Image Generation with Inverted Interaction

Event-Guided Rolling Shutter Correction with Time-Aware Cross-Attentions

Collaborators (1)

Wei Zhou

Make your next move.