Connecting Vision and Language plays an essential role in Generative Intelligence. For this
reason, large research efforts have been devoted to image captioning, ie describing images …

Generating a description of an image is called image captioning. Image captioning requires
recognizing the important objects, their attributes, and their relationships in an image. It also …

Recent text-to-image matching models apply contrastive learning to large corpora of
uncurated pairs of images and sentences. While such models can provide a powerful score …

Most machine-learning methods focus on classifying instances whose classes have already
been seen in training. In practice, many applications require classifying instances whose …

The limited availability of annotated data often hinders real-world applications of machine
learning. To efficiently learn from small quantities of multimodal data, we leverage the …

Augmented reality (AR) has proven to be an invaluable interactive medium to reduce
cognitive load by bridging the gap between the task-at-hand and relevant information by …

Existing studies on question answering on knowledge bases (KBQA) mainly operate with
the standard iid assumption, ie, training distribution over questions is the same as the test …

We introduce a novel framework for image captioning that can produce natural language
explicitly grounded in entities that object detectors find in the image. Our approach …

Current image captioning methods are usually trained via maximum likelihood estimation.
However, the log-likelihood score of a caption does not correlate well with human …

Image captioning models have achieved impressive results on datasets containing limited
visual concepts and large amounts of paired image-caption training data. However, if these …