Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
Dynamic Inter-Class Confusion-Aware Encoder for Audio-Visual Fusion in Human Activity Recognition
Kaixuan Cong, Yifan Wang, Rongkun Xue +3
Humans do not understand individual events in isolation; rather, they generalize concepts within classes and compare them to others. Existing audio-video pre-training paradigms onl…
cs.CV2024
Pretrained Reversible Generation as Unsupervised Visual Representation Learning
Rongkun Xue, Jinouwen Zhang, Yazhe Niu +4
Recent generative models based on score matching and flow matching have significantly advanced generation tasks, but their potential in discriminative tasks remains underexplored.…