research
∙
06/08/2023
Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment
The egocentric and exocentric viewpoints of a human activity look dramat...
share
research
∙
02/03/2023
Egocentric Video Task Translation @ Ego4D Challenge 2022
This technical report describes the EgoTask Translation approach that ex...
research
∙
12/13/2022
Egocentric Video Task Translation
Different video understanding tasks are typically treated in isolation, ...
research
∙
06/13/2022
The Modality Focusing Hypothesis: On the Blink of Multimodal Knowledge Distillation
Multimodal knowledge distillation (KD) extends traditional knowledge dis...
research
∙
03/31/2022
Dynamic Multimodal Fusion
Deep multimodal learning has achieved great progress in recent years. Ho...
research
∙
01/31/2022
SUGAR: Efficient Subgraph-level Training via Resource-aware Graph Partitioning
Graph Neural Networks (GNNs) have demonstrated a great potential in a va...
research
∙
06/23/2021
Co-advise: Cross Inductive Bias Distillation
Transformers recently are adapted from the community of natural language...
research
∙
06/08/2021
What Makes Multimodal Learning Better than Single (Provably)
The world provides us with data of multiple modalities. Intuitively, mod...
research
∙
03/26/2021