Description
Book SynopsisMRSP: Learn Multi-Representations of Single Primitive for Compositional Zero-Shot Learning.- Cross-Domain Semantic Segmentation on Inconsistent Taxonomy using VLMs.- TrafficNight : An Aerial Multimodal Benchmark For Nighttime Vehicle Surveillance.- Loc3Diff: Local Diffusion for 3D Human Head Synthesis and Editing.- Towards Open Domain Text-Driven Synthesis of Multi-Person Motions.- Generative End-to-End Autonomous Driving.- Learning to Distinguish Samples for Generalized Category Discovery.- COM Kitchens: An Unedited Overhead-view Procedural Videos Dataset a Vision-Language Benchmark.- PILoRA: Prototype Guided Incremental LoRA for Federated Class-Incremental Learning.- Diff-Reg: Diffusion Model in Doubly Stochastic Matrix Space for Registration Problem.- WBP: Training-time Backdoor Attacks through Hardware-based Weight Bit Poisoning.- Towards Dual Transparent Liquid Level Estimation in Biomedical Lab: Dataset, Methods and Practice.- Encapsulating Knowledge in One Prompt.- Cross-Input Certified Training for Universal Perturbations.- Visual Relationship Transformation.- Not Just Change the Labels, Learn the Features: Watermarking Deep Neural Networks with Multi-View Data.- Delving into Adversarial Robustness on Document Tampering Localization.- Adaptive Selection of Sampling-Reconstruction in Fourier Compressed Sensing.- Confidence-Based Iterative Generation for Real-World Image Super-Resolution.- Learning Scalable Model Soup on a Single GPU: An Efficient Subspace Training Strategy.- Correspondences of the Third Kind: Camera Pose Estimation from Object Reflection.- Seeing Faces in Things: A Model and Dataset for Pareidolia.- Cocktail Universal Adversarial Attack on Deep Neural Networks.- Gaussian Frosting: Editable Complex Radiance Fields with Real-Time Rendering.- AMD: Automatic Multi-step Distillation of Large-scale Vision Models.- FairViT: Fair Vision Transformer via Adaptive Masking.- TrojVLM: Backdoor Attack Against Vision Language Models.
