Deep learning approaches have recently raised the bar in many fields, from Natural
Language Processing to Computer Vision, by leveraging large amounts of data. However …

The aim of multi-output learning is to simultaneously predict multiple outputs given an input.
It is an important learning problem for decision-making since making decisions in the real …

Contrastive language-image pretraining has shown great success in learning visual-textual
joint representation from web-scale data, demonstrating remarkable “zero-shot” …

Humans are able to recognize structured relations in observation, allowing us to decompose
complex scenes into simpler parts and abstract the visual world in multiple levels. However …

Zero-shot semantic segmentation (ZS3) aims to segment the novel categories that have not
been seen in the training. Existing works formulate ZS3 as a pixel-level zero-shot …

Generalized zero-shot learning (GZSL) aims to recognize objects from both seen and
unseen classes, when only the labeled examples from seen classes are provided. Recent …

Recent developments in multimodal training methodologies, including CLIP and ALIGN,
obviate the necessity for individual data labeling. These approaches utilize pairs of data and …

Generalized zero-shot learning (GZSL) has achieved significant progress, with many efforts
dedicated to overcoming the problems of visual-semantic domain gaps and seen-unseen …

Abstract Contrastive Language-Image Pre-training (CLIP) achieves promising results in 2D
zero-shot and few-shot learning. Despite the impressive performance in 2D, applying CLIP …

Large-scale multi-modal training with image-text pairs imparts strong generalization to CLIP
model. Since training on a similar scale for videos is infeasible, recent approaches focus on …