Learn advanced techniques for human activity recognition with limited labeled data and privacy preservation, including pseudolevel...
Explore emerging properties in self-supervised vision transformers, covering related topics, model overview, and implementation de...
Explore vision transformer improvements through relative position encoding, examining bias modes, piecewise indexing, and 2D calcu...
Explore the evolution of vision architectures, comparing SWIN and CNNs, and learn about modernizing ConvNets with macro and micro...
Explore tokens, cross-view fusion, and attention in computer vision, examining experimental results and innovations in multi-view...
Students present their projects, showcasing innovative approaches in computer vision and AI. Topics include object detection, vide...
Final project presentations showcasing innovative approaches in video action recognition, offline reinforcement learning, and deci...
Learn about Grounded Visual Question Answering systems, their limitations, and innovative approaches using Transformers with Capsu...
Explore advanced geo-localization techniques using vision transformers and novel loss functions for improved accuracy in real-worl...
Explore spatio-temporal learning techniques for video action detection with limited labels, focusing on semi-supervised methods an...
Learn domain-adaptive meta-learning for one-shot imitation, enabling robots to quickly learn new tasks by observing human demonstr...
Explore the development of trustworthy multimodal AI systems that can adapt continuously, presented by Jaehong Yoon from UNC Chape...