CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Databy Sachin Mehta,…
Efficient Transformer Encoders for Mask2Former-style modelsby Manyi Yao, Abhishek Aich, Yumin Suh, Amit Roy-Chowdhury, Christian…
Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Modelby Xu Han,…
Language-Driven Active Learning for Diverse Open-Set 3D Object Detectionby Ross Greer, Bjørk Antoniussen, Andreas Møgelmose,…
TempBEV: Improving Learned BEV Encoders with Combined Image and BEV Space Temporal Aggregationby Thomas Monninger,…
Leveraging 3D LiDAR Sensors to Enable Enhanced Urban Safety and Public Health: Pedestrian Monitoring and…
A Realistic Protocol for Evaluation of Weakly Supervised Object Localizationby Shakeeb Murtaza, Soufiane Belharbi, Marco…
Coreset Selection for Object Detectionby Hojun Lee, Suyoung Kim, Junhoo Lee, Jaeyoung Yoo, Nojun KwakFirst…
BG-YOLO: A Bidirectional-Guided Method for Underwater Object Detectionby Jian Zhang, Ruiteng Zhang, Xinyue Yan, Xiting…
Enhanced Cooperative Perception for Autonomous Vehicles Using Imperfect Communicationby Ahmad Sarlak, Hazim Alzorgan, Sayed Pedram…