Search Results for author:
Found 10 papers, 4 papers with code
ANMS: Asynchronous Non-Maximum Suppression in Event Stream
As a result, the performance of event-based corner detectors is limited.
Event Voxel Set Transformer for Spatiotemporal Representation Learning on Event Streams
To fit the sparse nature of events and sufficiently explore the relationship between them, we develop a novel attention-aware model named Event Voxel Set Transformer (EVSTr) for spatiotemporal representation learning on event streams.
A Dynamic Graph CNN with Cross-Representation Distillation for Event-Based Recognition
Recent advances in event-based research prioritize sparsity and temporal precision.
TokenHPE: Learning Orientation Tokens for Efficient Head Pose Estimation via Transformers
To leverage the observed findings, we propose a novel critical minority relationship-aware method based on the Transformer architecture in which the facial part relationships can be learned.
A Temporal Densely Connected Recurrent Network for Event-based Human Pose Estimation
By this recurrent architecture, we can explicitly model not only the sequential but also non-sequential geometric consistency across time steps to accumulate information from previous frames to recover the entire human bodies, achieving a stable and accurate human pose estimation from event data.
A Voxel Graph CNN for Object Classification with Event Cameras
This study aims to address the core problem of balancing accuracy and model complexity for event-based classification models.
CNN-based RGB-D Salient Object Detection: Learn, Select and Fuse
The goal of this work is to present a systematic solution for RGB-D salient object detection, which addresses the following three aspects with a unified framework: modal-specific representation learning, complementary cue selection and cross-modal complement fusion.
BigData Applications from Graph Analytics to Machine Learning by Aggregates in Recursion
In the past, the semantic issues raised by the non-monotonic nature of aggregates often prevented their use in the recursive statements of logic programs and deductive databases.
Progressively Complementarity-Aware Fusion Network for RGB-D Salient Object Detection
In this paper, we answer this question from two perspectives: (1) We argue that if the complementary part can be modelled more explicitly, the cross-modal complement is likely to be better captured.
Ranked #23 on
RGB-D Salient Object Detection
on NJU2K
RRV: A Spatiotemporal Descriptor for Rigid Body Motion Recognition
Motion behaviors of a rigid body can be characterized by a 6-dimensional motion trajectory, which contains position vectors of a reference point on the rigid body and rotations of this rigid body over time.
