SOAR: Self-supervision Optimized UAV Action Recognition with Efficient Object-Aware Pretrainingby Ruiqi Xian, Xiyang Wu, Tianrui…
Wavelet-Driven Generalizable Framework for Deepfake Face Forgery Detectionby Lalith Bharadwaj Baru, Rohit Boddeda, Shilhora Akshay…
HydroVision: LiDAR-Guided Hydrometric Prediction with Vision Transformers and Hybrid Graph Learningby Naghmeh Shafiee Roudbari, Ursula…
Patch Ranking: Efficient CLIP by Learning to Rank Local Patchesby Cheng-En Wu, Jinhong Lin, Yu…
OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decompositionby Stephen Zhang, Vardan PapyanFirst submitted to…
On Vision Transformers for Classification Tasks in Side-Scan Sonar Imageryby BW Sheffield, Jeffrey Ellen, Ben…
Are Deep Learning Models Robust to Partial Object Occlusion in Visual Recognition Tasks?by Kaleb Kassaw,…
Token Turing Machines are Efficient Vision Modelsby Purvish Jajal, Nick John Eliopoulos, Benjamin Shiue-Hal Chou,…
AttentionX: Exploiting Consensus Discrepancy In Attention from A Distributed Optimization Perspectiveby Guoqiang Zhang, Richard HeusdensFirst…
Evidential Transformers for Improved Image Retrievalby Danilo Dordevic, Suryansh KumarFirst submitted to arxiv on: 2…