Search Results for author:
Found 5 papers, 2 papers with code
Weight Excitation: Built-in Attention Mechanisms in Convolutional Neural Networks
We propose novel approaches for simultaneously identifying important weights of a convolutional neural network (ConvNet) and providing more attention to the important weights during training.
Towards Efficient Coarse-to-Fine Networks for Action and Gesture Recognition
State-of-the-art approaches to video-based action and gesture recognition often employ two key concepts: First, they employ multistream processing; second, they use an ensemble of convolutional networks.
Ranked #1 on
Action Classification
on Jester test
Self-supervised Spatiotemporal Representation Learning by Exploiting Video Continuity
Recent self-supervised video representation learning methods have found significant success by exploring essential properties of videos, e. g. speed, temporal order, etc.
ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenation
We present ConDA, a concatenation-based domain adaptation framework for LiDAR segmentation that: 1) constructs an intermediate domain consisting of fine-grained interchange signals from both source and target domains without destabilizing the semantic coherency of objects and background around the ego-vehicle; and 2) utilizes the intermediate domain for self-training.
Class Semantics-based Attention for Action Detection
Our attention mechanism outperforms prior self-attention modules such as the squeeze-and-excitation in action detection task.
