← Search

Lucas Smaira

6 accepted papers

2023

Perception Test: A Diagnostic Benchmark for Multimodal Video Models

NeurIPS 2023poster

We propose a novel multimodal video benchmark - the Perception Test - to evaluate the perception and reasoning skills of pre-trained multimodal models (e.g. Flamingo, BEiT-3, or GPT-4). Compared to existing benchmarks that focus on computational tasks (e.g. classification, detection or tracking), th…

2022

TAP-Vid: A Benchmark for Tracking Any Point in a Video

NeurIPS 2022accept

Generic motion understanding from video involves not only tracking objects, but also perceiving how their surfaces deform and move. This information is useful to make inferences about 3D shape, physical properties and object interactions. While the problem of tracking arbitrary physical points on su…

2022

Towards Learning Universal Audio Representations

ICASSP 2022accepted

The ability to learn universal audio representations that can solve diverse speech, music, and environment tasks can spur many applications that require general sound content understanding. In this work, we introduce a holistic audio representation evaluation suite (HARES) spanning 12 downstream tas…

Cited by 0SourceScholar
2020

End-to-End Learning of Visual Representations From Uncurated Instructional Videos

CVPR 2020oral

Annotating videos is cumbersome, expensive and not scalable. Yet, many strong video models still rely on manually annotated data. With the recent introduction of the HowTo100M dataset, narrated videos now offer the possibility of learning video representations without manual supervision. In this wor…

Cited by 867PDFcodeScholar
2020

Self-Supervised MultiModal Versatile Networks

NeurIPS 2020poster

Videos are a rich source of multi-modal supervision. In this work, we learn representations using self-supervision by leveraging three modalities naturally present in videos: visual, audio and language streams. To this end, we introduce the notion of a multimodal versatile network -- a network that…

2020

Visual Grounding in Video for Unsupervised Word Translation

CVPR 2020poster

There are thousands of actively spoken languages on Earth, but a single visual world. Grounding in this visual world has the potential to bridge the gap between all these languages. Our goal is to use visual grounding to improve unsupervised word mapping between languages. The key idea is to establi…

Cited by 58PDFcodeScholar