4 accepted papers
Bridging contrastive language-image pre-training (CLIP) to video action recognition has attracted growing interest. Human actions are inherently rich in spatial and temporal contexts, involving dynamic interactions among people, objects, and the environment. Accurately recognizing actions requires e…
Adapting CLIP models for few-shot recognition has recently attracted significant attention. Despite considerable progress, these adaptations remain hindered by the pervasive challenge of data scarcity. Text-to-image models, capable of generating abundant photorealistic labeled images, offer a promis…
In self-supervised speaker verification, the quality of generated pseudo labels becomes a bottleneck for the performance. This work introduces a dynamic threshold within the iterative DIstillation with NO labels (DINO) framework. We employ a Gaussian Mixture Model (GMM) to model the loss distributio…
Since pioneering work of Hinton et al., knowledge distillation based on Kullback-Leibler Divergence (KL-Div) has been predominant, and recently its variants have achieved compelling performance. However, KL-Div only compares probabilities of the corresponding category between the teacher and stud…