This academic journey may be dull and challenging, but luckily you are with me.
NavMorph. Official implementation of NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments (ICCV'25).
87ICML2024-FSTTA. Fast-Slow Test-time Adaptation for Online Vision-and-Language Navigation
35MM2023-SACCN. [MM'23] Video Entailment via Reaching a Structure-Aware Cross-modal Consensus
7GMC. Video Question Answering Method Based on Self-supervised Graph Neural Network with Contrastive Learning
2ACM-DA. Active Cross-Modal Domain Adaptation
1