Changsheng Xu

18

Papers

56

Total Citations

Papers (18)

Music Style Transfer with Time-Varying Inversion of Diffusion Models

Three Heads Are Better than One: Complementary Experts for Long-Tailed Semi-supervised Learning

R-EDL: Relaxing Nonessential Settings of Evidential Deep Learning

Language Guided Concept Bottleneck Models for Interpretable Continual Learning

FedVAD: Enhancing Federated Video Anomaly Detection with GPT-Driven Semantic Distillation

Customized Condition Controllable Generation for Video Soundtrack

Pseudo Informative Episode Construction for Few-Shot Class-Incremental Learning

Pilot: Building the Federated Multimodal Instruction Tuning Framework

Overcoming Dual Drift for Continual Long-Tailed Visual Question Answering

NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments

TCP:Textual-based Class-aware Prompt tuning for Visual-Language Model

Modality-Collaborative Test-Time Adaptation for Action Recognition

Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigation

Cluster-Aware Similarity Diffusion for Instance Retrieval

Libra: Building Decoupled Vision System on Large Language Models

Evidential Knowledge Distillation

Enhancing Storage and Computational Efficiency in Federated Multimodal Learning for Large-Scale Models

When Open-Vocabulary Visual Question Answering Meets Causal Adapter: Benchmark and Approach