Search Results for author:
Found 4 papers, 1 papers with code
Multiscale Superpixel Structured Difference Graph Convolutional Network for VL Representation
It parses the entire image as a fine-to-coarse hierarchical structure of constituent visual patterns, and captures multiscale features by progressively merging adjacent superpixels as graph nodes.
Guided Cooperation in Hierarchical Reinforcement Learning via Model-based Rollout
Here, we propose a goal-conditioned HRL framework named Guided Cooperation via Model-based Rollout (GCMR), aiming to bridge inter-layer information synchronization and cooperation by exploiting forward dynamics.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
Artificial-Spiking Hierarchical Networks for Vision-Language Representation Learning
In this work, we propose an efficient computation framework for multimodal alignment by introducing a novel visual semantic module to further improve the performance of the VL tasks.
LOIS: Looking Out of Instance Semantics for Visual Question Answering
Visual question answering (VQA) has been intensively studied as a multimodal task that requires effort in bridging vision and language to infer answers correctly.
