Kun Wei

Backtrace Mamba: Reviving Critical Temporal Contexts via Hierarchical Memory Compression for Online Action Detection AAAI 2026 Diffusion-calibrated Continual Test-time Adaptation AAAI 2026 Hearing More with Less: Multi-Modal Retrieval-and-Selection Augmented Conversational LLM-Based ASR AAAI 2026 Towards Robust Edge Model Adaptation via Elastic Architecture Search AAAI 2026 Compress to One Point: Neural Collapse for Pre-Trained Model-Based Class-Incremental Learning AAAI 2025 Dynamic Adapter Tuning for Long-Tailed Class-Incremental Learning WACV 2025 Energy vs. Noise: Towards Robust Temporal Action Localization in Open-World AAAI 2025 Outstanding Orthodontist: No More Artifactual Teeth in Talking Face IJCAI 2025 Q-MiniSAM2: A Quantization-based Benchmark for Resource-Efficient Video Segmentation IJCAI 2025 ACFun: Abstract-Concrete Fusion Facial Stylization NeurIPS 2024 A Versatile Framework for Continual Test-Time Domain Adaptation: Balancing Discriminability and Generalizability CVPR 2024 Exploiting Intrinsic Multilateral Logical Rules for Weakly Supervised Natural Language Video Localization ACL 2024 Long-Tail Class Incremental Learning via Independent Sub-prototype Construction CVPR 2024 Navigating Continual Test-time Adaptation with Symbiosis Knowledge IJCAI 2024 SEQ-former: A context-enhanced and efficient automatic speech recognition framework Interspeech 2024 Exploring Safety Supervision for Continual Test-time Domain Adaptation IJCAI 2023 Hierarchical Prompt Learning for Compositional Zero-Shot Recognition IJCAI 2023 StyleS2ST: Zero-shot Style Transfer for Direct Speech-to-speech Translation Interspeech 2023 The NPU-MSXF Speech-to-Speech Translation System for IWSLT 2023 Speech-to-Speech Translation Task ACL 2023 Improving Transformer-based Conversational ASR by Inter-Sentential Attention Mechanism Interspeech 2022 Learning Universal Adversarial Perturbation by Adversarial Example AAAI 2022 Leveraging Acoustic Contextual Representation by Audio-textual Cross-modal Learning for Conversational ASR Interspeech 2022 ME-GAN: Learning Panoptic Electrocardio Representations for Multi-view ECG Synthesis Conditioned on Heart Diseases ICML 2022 Not Just Selection, but Exploration: Online Class-Incremental Continual Learning via Dual View Consistency CVPR 2022 Siamese Contrastive Embedding Network for Compositional Zero-Shot Learning CVPR 2022 Class-Incremental Instance Segmentation via Multi-Teacher Networks AAAI 2021 Generalized Zero-Shot Learning via Disentangled Representation AAAI 2021 Incremental Embedding Learning via Zero-Shot Translation AAAI 2021 Nearest Neighbor Matching for Deep Clustering CVPR 2021 SelfSAGCN: Self-Supervised Semantic Alignment for Graph Convolution Network CVPR 2021 Adversarial Learning for Robust Deep Clustering NeurIPS 2020 Lifelong Zero-Shot Learning IJCAI 2020 Adversarial Fine-Grained Composition Learning for Unseen Attribute-Object Recognition ICCV 2019