Thousands of images are generated every day, which implies the necessity to classify,
organise and access them using an easy, faster and efficient way. Scene classification, the …

Localizing objects in image collections without supervision can help to avoid expensive
annotation campaigns. We propose a simple approach to this problem, that leverages the …

Instance segmentation is a fundamental vision task that aims to recognize and segment
each object in an image. However, it requires costly annotations such as bounding boxes …

How do humans recognize the action" opening a book"? We argue that there are two
important cues: modeling temporal shape dynamics and modeling functional relationships …

Self-supervised learning aims to learn representations from the data itself without explicit
manual supervision. Existing efforts ignore a crucial aspect of self-supervised learning-the …

Visual relationships capture a wide variety of interactions between pairs of objects in images
(eg “man riding bicycle” and “man pushing bicycle”). Consequently, the set of possible …

We present an unsupervised representation learning approach using videos without
semantic labels. We leverage the temporal coherence as a supervisory signal by formulating …

Object detection, scene graph generation and region captioning, which are three scene
understanding tasks at different semantic levels, are tied together: scene graphs are …

Probabilistic topic models are unsupervised generative models which model document
content as a two-step generation process, that is, documents are observed as mixtures of …

In this paper, we present an approach for learning a visual representation from the raw
spatiotemporal signals in videos. Our representation is learned without supervision from …