Quick search
Advanced search in
Field to searchTerm
Add rule
Filters (5)
Download Results
34 research outcomes, page 1 of 4
  • publication . Conference object . Preprint . 2020
    Open Access
    Authors:
    Antoine Miech; Jean-Baptiste Alayrac; Lucas Smaira; Ivan Laptev; Josef Sivic; Andrew Zisserman;
    Persistent Identifiers
    Publisher: IEEE
    Project: EC | LEAP (336845)

    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 m...

    Add to ORCIDorcid
  • publication . Conference object . Preprint . 2019
    Open Access English
    Authors:
    Julia Peyre; Josef Sivic; Ivan Laptev; Cordelia Schmid;
    Persistent Identifiers
    Publisher: HAL CCSD
    Project: EC | LEAP (336845), EC | ACTIVIA (307574), EC | ALLEGRO (320559)

    International audience; We seek to detect visual relations in images of the form of triplets t = (subject, predicate, object), such as “person riding dog”, where training examples of the individual entities are available but their combinations are unseen at training. Th...

    Add to ORCIDorcid
  • publication . Preprint . Conference object . 2019
    Open Access English
    Authors:
    Dimitri Zhukov; Jean-Baptiste Alayrac; Ramazan Gokberk Cinbis; David F. Fouhey; Ivan Laptev; Josef Sivic;
    Persistent Identifiers
    Project: EC | LEAP (336845), EC | ACTIVIA (307574)

    In this paper we investigate learning visual models for the steps of ordinary tasks using weak supervision via instructional narrations and an ordered list of steps instead of strong supervision via temporal annotations. At the heart of our approach is the observation t...

    Add to ORCIDorcid
  • publication . Article . 2019
    Open Access English
    Authors:
    Alejandrina Cristia; Emmanuel Dupoux; Nan Bernstein Ratner; Melanie Soderstrom;
    Persistent Identifiers
    Publisher: HAL CCSD
    Project: EC | BOOTPHON (295810), ANR | IEC (ANR-10-LABX-0087), ANR | PSL (ANR-10-IDEX-0001), ANR | FrontCog (ANR-17-EURE-0017), SSHRC , ANR | MechELex (ANR-14-CE30-0003)

    International audience; Previous computational modeling suggests it is much easier to segment words from child-directed speech (CDS) than adult-directed speech (ADS). However, this conclusion is based on data collected in the laboratory, with CDS from play sessions and ...

    Add to ORCIDorcid
  • publication . Conference object . Preprint . 2018
    Open Access
    Authors:
    Rachid Riad; Corentin Dancette; Julien Karadayi; Neil Zeghidour; Thomas Schatz; Emmanuel Dupoux;
    Persistent Identifiers
    Publisher: ISCA
    Project: ANR | IEC (ANR-10-LABX-0087), EC | BOOTPHON (295810)

    Recent studies have investigated siamese network architectures for learning invariant speech representations using same-different side information at the word level. Here we investigate systematically an often ignored component of siamese networks: the sampling procedur...

    Add to ORCIDorcid
  • publication . Article . 2018
    Open Access
    Authors:
    Guillaume Cordonnier; Marie-Paule Cani; Bedrich Benes; Jean Braun; Eric Galin;
    Persistent Identifiers
    Project: EC | EXPRESSIVE (291184)

    International audience; Most mountain ranges are formed by the compression and folding of colliding tectonic plates. Subduction of one plate causes large-scale asymmetry while their layered composition (or stratigraphy) explains the multi-scale folded strata observed on...

    Add to ORCIDorcid
  • publication . Article . 2018
    English
    Authors:
    Boukhelifa, Nadia; Bryant, Mike; Bulatović, Nataša; Fekete, Jean-Daniel; Knežević, Milica; Lehmann, Jörg; Stuart, David; Thiel, Carsten;
    Publisher: HAL CCSD
    Project: EC | CENDARI (284432)

    International audience; The CENDARI infrastructure is a research-supporting platform designed to provide tools for transnational historical research, focusing on two topics: medieval culture and World War I. It exposes to the end users modern Web-based tools relying on ...

  • publication . Article . 2017
    Open Access English
    Authors:
    Adela Barbulescu; Rémi Ronfard; Gérard Bailly;
    Persistent Identifiers
    Publisher: HAL CCSD
    Project: ANR | PERSYVAL-lab (ANR-11-LABX-0025), EC | EXPRESSIVE (291184)

    An important problem in computer animation of virtual characters is the expression of complex mental states during conversation using the coordinated prosody of voice, rhythm, facial expressions, and head and gaze motion. In this work, the authors propose an expressive ...

    Add to ORCIDorcid
  • publication . Contribution for newspaper or weekly magazine . Conference object . Preprint . 2017
    Open Access English
    Authors:
    Héctor Martínez Alonso; Željko Agić; Barbara Plank; Anders Søgaard;
    Publisher: Association for Computational Linguistics
    Project: EC | LOWLANDS (313695)

    We propose UDP, the first training-free parser for Universal Dependencies (UD). Our algorithm is based on PageRank and a small set of head attachment rules. It features two-step decoding to guarantee that function words are attached as leaf nodes. The parser requires no...

    Add to ORCIDorcid
  • publication . Preprint . Conference object . 2017
    Open Access English
    Authors:
    Rahma Chaabouni; Ewan Dunbar; Neil Zeghidour; Emmanuel Dupoux;
    Persistent Identifiers
    Project: ANR | IEC (ANR-10-LABX-0087), EC | BOOTPHON (295810)

    Recent works have explored deep architectures for learning multimodal speech representation (e.g. audio and images, articulation and audio) in a supervised way. Here we investigate the role of combining different speech modalities, i.e. audio and visual information repr...

    Add to ORCIDorcid
34 research outcomes, page 1 of 4