Computer Vision – ECCV 2024

Few-shot Class Incremental Learning with Attention-Aware Self-Adaptive Prompt.- An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models.- Generalizable Symbolic Optimizer Learning.- Online Continuous Generalized Category Discovery.- Bridging Different Language Models and Generative Vision Models for Text-to-Image Generation.- Tackling Structural Hallucination in Image Translation with Local Diffusion.- Hierarchical Separable Video Transformer for Snapshot Compressive Imaging.- Unified Medical Image Pre-training in Language-Guided Common Semantic Space.- On the Vulnerability of Skip Connections to Model Inversion Attacks.- Adversarial Robustification via Text-to-Image Diffusion Models.- Overcome Modal Bias in Multi-modal Federated Learning via Balanced Modality Selection.- Comprehensive Attribution: Inherently Explainable Vision Model with Feature Detector.- Reinforcement Learning via Auxillary Task Distillation.- DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentation.- Pre-trained Visual Dynamics Representations for Efficient Policy Learning.- View-Consistent Hierarchical 3D Segmentation Using Ultrametric Feature Fields.- Plug and Play: A Representation Enhanced Domain Adapter for Collaborative Perception.- Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models.- SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation.- TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias.- Learning Quantized Adaptive Conditions for Diffusion Models.- STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay.- Remove Projective LiDAR Depthmap Artifacts via Exploiting Epipolar Geometry.- Accelerating Online Mapping and Behavior Prediction via Direct BEV Feature Attention.- High-Fidelity Modeling of Generalizable Wrinkle Deformation.- Instruction Tuning-free Visual Token Complement for Multimodal LLMs.