9 citations · 22 across the 10 of their papers we have counts for
Showing 2020 · cs.CLShow all
2 papers · 2 filters
cs.CL2020★ 3 cited
MTAG: Modal-Temporal Attention Graph for Unaligned Human Multimodal Language Sequences
Jianing Yang, Yongxin Wang, Ruitao Yi +5
Human communication is multimodal in nature; it is through multiple modalities such as language, voice, and facial expressions, that opinions and emotions are expressed. Data in th…
cs.CL2020★ 7 cited
What Gives the Answer Away? Question Answering Bias Analysis on Video QA Datasets
Jianing Yang, Yuying Zhu, Yongxin Wang +3
Question answering biases in video QA datasets can mislead multimodal model to overfit to QA artifacts and jeopardize the model's ability to generalize. Understanding how strong th…