Easy access to audio-visual content on social media, combined with the availability of
modern tools such as Tensorflow or Keras, and open-source trained models, along with …

Emotion recognition is an aspect of human-computer interaction, affective computing, and
social robotics. Conventional unimodal approaches for emotion recognition, depending on …

We present a new framework for semantic segmentation without annotations via clustering.
Off-the-shelf clustering methods are limited to curated, single-label, and object-centric …

Unsupervised visual representation learning remains a largely unsolved problem in
computer vision research. Among a big body of recently proposed approaches for …

The objective of this paper is self-supervised learning from video, in particular for
representations for action recognition. We make the following contributions:(i) We propose a …

Synthetically-generated audios and videos-so-called deep fakes-continue to capture the
imagination of the computer-graphics and computer-vision communities. At the same time …

A major challenge in DeepFake forgery detection is that state-of-the-art algorithms are
mostly trained to detect a specific fake method. As a result, these approaches show poor …

Obtaining large, human labelled speech datasets to train models for emotion recognition is a
notoriously challenging task, hindered by annotation cost and label ambiguity. In this work …

Recent interest in self-supervised dense tracking has yielded rapid progress, but
performance still remains far from supervised methods. We propose a dense tracking model …

We propose a method for learning landmark detectors for visual objects (such as the eyes
and the nose in a face) without any manual supervision. We cast this as the problem of …