Multimodal learning, which aims to understand and analyze information from multiple
modalities, has achieved substantial progress in the supervised regime in recent years …

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 …

We describe an approach to predict open-vocabulary 3D semantic voxel occupancy map
from input 2D images with the objective of enabling 3D grounding, segmentation and …

Learning to classify video data from classes not included in the training data, ie video-based
zero-shot learning, is challenging. We conjecture that the natural alignment between the …

Multi-modal clustering represents a formidable challenge in the domain of unsupervised
learning. The objective of multi-modal clustering is to categorize data collected from diverse …

Contrastive self-supervised learning has shown impressive results in learning visual
representations from unlabeled images by enforcing invariance against different data …

We introduce an audiovisual method for long-range text-to-video retrieval. Unlike previous
approaches designed for short video retrieval (eg, 5–15 s in duration), our approach aims to …

Audio-visual generalised zero-shot learning for video classification requires understanding
the relations between the audio and visual information in order to be able to recognise …

The images and sounds that we perceive undergo subtle but geometrically consistent
changes as we rotate our heads. In this paper, we use these cues to solve a problem we call …

This work investigates learning pixel-wise semantic image segmentation in urban scenes
without any manual annotation, just from the raw non-curated data collected by cars which …