α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
AJ Piergiovanni
AJ Piergiovanni
14
papers
772
total citations
papers (14)
On Scaling Up a Multilingual Vision and Language Model
CVPR 2024
arXiv
256
citations
Evolving Losses for Unsupervised Video Representation Learning
CVPR 2020
arXiv
145
citations
Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning
CVPR 2023
arXiv
70
citations
4D-Net for Learned Multi-Modal Alignment
ICCV 2021
arXiv
68
citations
AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification
ECCV 2020
arXiv
53
citations
AViD Dataset: Anonymized Videos from Diverse Countries
NEURIPS 2020
arXiv
42
citations
Adversarial Generative Grammars for Human Activity Prediction
ECCV 2020
arXiv
35
citations
Recognizing Actions in Videos From Unseen Viewpoints
CVPR 2021
arXiv
33
citations
Mirasol3B: A Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities
CVPR 2024
arXiv
26
citations
Video Question Answering with Iterative Video-Text Co-Tokenization
ECCV 2022
arXiv
21
citations
FindIt: Generalized Localization with Natural Language Queries
ECCV 2022
arXiv
18
citations
VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models
CVPR 2025
arXiv
5
citations
AssembleNet++: Assembling Modality Representations via Attention Connections - Supplementary Material -
ECCV 2020
0
citations
TokenLearner: Adaptive Space-Time Tokenization for Videos
NEURIPS 2021
0
citations
