Search Results for author:
Found 9 papers, 1 papers with code
Regularization-Based Efficient Continual Learning in Deep State-Space Models
Deep state-space models (DSSMs) have gained popularity in recent years due to their potent modeling capacity for dynamic systems.
Vertex-based Networks to Accelerate Path Planning Algorithms
Path planning plays a crucial role in various autonomy applications, and RRT* is one of the leading solutions in this field.
BEV-IO: Enhancing Bird's-Eye-View 3D Detection with Instance Occupancy
At the core of our method is the newly-designed instance occupancy prediction (IOP) module, which aims to infer point-level occupancy status for each instance in the frustum space.
UniCon+: ICTCAS-UCAS Submission to the AVA-ActiveSpeaker Task at ActivityNet Challenge 2022
This report presents a brief description of our winning solution to the AVA Active Speaker Detection (ASD) task at ActivityNet Challenge 2022.
RealNet: Combining Optimized Object Detection with Information Fusion Depth Estimation Co-Design Method on IoT
Innovation of our method is using information fusion to compensate the problem of insufficient frame rate of output image, and improve the robustness of target detection and depth estimation under monocular vision. Object Detection is based on YOLO-v5.
UniCon: Unified Context Network for Robust Active Speaker Detection
Our solution is a novel, unified framework that focuses on jointly modeling multiple types of contextual information: spatial context to indicate the position and scale of each candidate's face, relational context to capture the visual relationships among the candidates and contrast audio-visual affinities with each other, and temporal context to aggregate long-term information and smooth out local uncertainties.
ICTCAS-UCAS-TAL Submission to the AVA-ActiveSpeaker Task at ActivityNet Challenge 2021
This report presents a brief description of our method for the AVA Active Speaker Detection (ASD) task at ActivityNet Challenge 2021.
Ultrabroadband Polarization Insensitive Hybrid using Multiplane Light Conversion
We designed, fabricated and tested an optical hybrid that supports an octave of bandwidth (900-1800 nm) and below 4-dB insertion loss using multiplane light conversion.
Optics
Multi-Task Learning for Audio Visual Active Speaker Detection
This report describes the approach underlying our submission to the active speaker detection task (task B-2) of ActivityNet Challenge 2019.
Ranked #17 on
Audio-Visual Active Speaker Detection
on AVA-ActiveSpeaker
(using extra training data)
