cross-attention mechanism

UDAPose: Unsupervised Domain Adaptation for Low-Light Human Pose Estimation CVPR 2026 Unlocking 3D Affordance Segmentation with 2D Semantic Knowledge CVPR 2026 VIMCAN: Visual-Inertial 3D Human Pose Estimation with Hybrid Mamba-Cross-Attention Network CVPR 2026 X-AVDT: Audio-Visual Cross-Attention for Robust Deepfake Detection CVPR 2026 I^2AM: Interpreting Image-to-Image Latent Diffusion Models via Bi-Attribution Maps ICLR 2025 Aerodynamic Coefficients Prediction via Cross-Attention Fusion and Physical-Informed Training AAAI 2025 AIComposer: Any Style and Content Image Composition via Feature Integration ICCV 2025 ASAP: Advancing Semantic Alignment Promotes Multi-Modal Manipulation Detecting and Grounding CVPR 2025 Auto-Regressive Transformation for Image Alignment ICCV 2025 Beyond Image Classification: A Video Benchmark and Dual-Branch Hybrid Discrimination Framework for Compositional Zero-Shot Learning CVPR 2025 Beyond Manual Transcripts: The Potential of Automated Speech Recognition Errors in Improving Alzheimer’s Disease Detection Interspeech 2025 BiCrossMamba-ST: Speech Deepfake Detection with Bidirectional Mamba Spectro-Temporal Cross-Attention Interspeech 2025 Bridge the GAP: Multi-lingual Models For Ambiguous Pronominal Coreference Resolution in South Asian Languages COLING 2025 CACA: Context-Aware Cross-Attention Network for Extractive Aspect Sentiment Quad Prediction COLING 2025 CAGCRN: Real-Time Speech Enhancement with a Lightweight Model for Joint Acoustic Echo Cancellation and Noise Suppression Interspeech 2025 CAMER: Contribution-Aware Multimodal Emotion Recognition Interspeech 2025 CA-MLIF: Cross-Attention and Multimodal Low-Rank Interaction Fusion Framework for Tumor Prognostic Prediction AAAI 2025 CasP: Improving Semi-Dense Feature Matching Pipeline Leveraging Cascaded Correspondence Priors for Guidance ICCV 2025 Categorical Attention: Fine-grained Language-guided Noise Filtering Network for Occluded Person Re-Identification IJCAI 2025 CheapNet: Cross-attention on Hierarchical representations for Efficient protein-ligand binding Affinity Prediction ICLR 2025 ConceptSplit: Decoupled Multi-Concept Personalization of Diffusion Models via Token-wise Adaptation and Attention Disentanglement ICCV 2025 CU at BEA 2025 Shared Task: A BERT-Based Cross-Attention Approach for Evaluating Pedagogical Responses in Dialogue ACL 2025 Describe, Don't Dictate: Semantic Image Editing with Natural Language Intent ICCV 2025 DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis AAAI 2025 DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Model ICCV 2025