Search Results for author:
Found 3 papers, 2 papers with code
MMTF: Multi-Modal Temporal Fusion for Commonsense Video Question Answering
To address this, we propose a novel vision-text fusion module that learns the temporal context of the video and question.
Ranked #8 on
Video Question Answering
on AGQA 2.0 balanced
(Average Accuracy metric)
Query-Dependent Video Representation for Moment Retrieval and Highlight Detection
As we observe the insignificant role of a given query in transformer architectures, our encoding module starts with cross-attention layers to explicitly inject the context of text query into video representation.
Ranked #2 on
Highlight Detection
on TvSum
Technical Report for CVPR 2022 LOVEU AQTC Challenge
This technical report presents the 2nd winning model for AQTC, a task newly introduced in CVPR 2022 LOng-form VidEo Understanding (LOVEU) challenges.
