Search Results for author:
Found 9 papers, 2 papers with code
Not Just Object, But State: Compositional Incremental Learning without Forgetting
Most incremental learners excessively prioritize coarse classes of objects while neglecting various kinds of states (e. g. color and material) attached to the objects.
CSCNET: Class-Specified Cascaded Network for Compositional Zero-Shot Learning
Inspired by this, we propose a novel A-O disentangled framework for CZSL, namely Class-specified Cascaded Network (CSCNet).
VidTr: Video Transformer Without Convolutions
We first introduce the vanilla video transformer and show that transformer module is able to perform spatio-temporal modeling from raw pixels, but with heavy memory usage.
Ranked #15 on
Action Classification
on Charades
TubeR: Tubelet Transformer for Video Action Detection
We propose TubeR: a simple solution for spatio-temporal video action detection.
Multi-Label Activity Recognition using Activity-specific Features and Activity Correlations
Multi-label activity recognition is designed for recognizing multiple activities that are performed simultaneously or sequentially in each video.
Tri-axial Self-Attention for Concurrent Activity Recognition
We present a system for concurrent activity recognition.
Progress Estimation and Phase Detection for Sequential Processes
For the Olympic swimming dataset, our system achieved an accuracy of 88%, an F1-score of 0. 58, a completeness estimation error of 6. 3% and a remaining-time estimation error of 2. 9 minutes.
Online People Tracking and Identification with RFID and Kinect
We introduce a novel, accurate and practical system for real-time people tracking and identification.
Concurrent Activity Recognition with Multimodal CNN-LSTM Structure
Our system is the first to address the concurrent activity recognition with multisensory data using a single model, which is scalable, simple to train and easy to deploy.
