Filtrer vos résultats
- 9
- 5
- 3
- 1
- 9
- 2
- 1
- 3
- 1
- 2
- 3
- 9
- 5
- 5
- 4
- 4
- 9
- 4
- 4
- 4
- 4
- 3
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
9 résultats
|
|
triés par
|
|
Estimating semantic structure for the VQA answer space2020
Pré-publication, Document de travail
hal-02862763v1
|
||
|
An Occam’s Razor View on Learning Audiovisual Emotion Recognition with Small Training SetsICMI (EmotiW) 2018, Oct 2018, Boulder, Colorado, United States
Communication dans un congrès
hal-01854019v1
|
||
|
Weak Supervision helps Emergence of Word-Object Alignment and improves Vision-Language Tasks2019
Pré-publication, Document de travail
hal-02393019v1
|
||
|
VisQA: X-raying Vision and Language Reasoning in TransformersIEEE Transactions on Visualization and Computer Graphics, 2021, ⟨10.1109/TVCG.2021.3114683⟩
Article dans une revue
hal-03293079v1
|
||
|
Roses Are Red, Violets Are Blue... but Should Vqa Expect Them To?Computer Vision and Pattern Recognition (CVPR), IEEE, Jun 2021, Virtual, France
Communication dans un congrès
hal-02860823v3
|
||
|
The Many Variations of EmotionThe 14th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019), May 2019, Lille, France
Communication dans un congrès
hal-02051792v1
|
||
|
CAKE: Compact and Accurate K-dimensional representation of EmotionImage Analysis for Human Facial and Activity Recognition (BMVC Workshop), Dr. Zhaojie Ju, Sep 2018, Newcastle, United Kingdom
Communication dans un congrès
hal-01849908v2
|
||
|
How Transferable are Reasoning Patterns in VQA?IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2021, Nashville, Tennessee, United States. ⟨10.1109/CVPR46437.2021.00419⟩
Communication dans un congrès
hal-03192949v1
|
||
|
The Many Moods of Emotion2018
Pré-publication, Document de travail
hal-01908390v1
|