conftrace_

question-guided fusion

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

cross-modal grounding (1) motion appearance (1) neural network (1) video question answering (1) visual reasoning (1) video understanding (1) cross-modal learning (1) multimodal learning (1) visual question answering (1) action recognition (1)

Papers

Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answering ACL 2021