62 citations · 250 across the 38 of their papers we have counts for
11 papers · 1 filter
One for More: Selecting Generalizable Samples for Generalizable ReID Model
Enwei Zhang, Xinyang Jiang, Hao Cheng +7
Current training objectives of existing person Re-IDentification (ReID) models only ensure that the loss of the model decreases on selected training batch, with no regards to the p…
Exploring Dynamic Context for Multi-path Trajectory Prediction
Hao Cheng, Wentong Liao, Xuejiao Tang +3
To accurately predict future positions of different agents in traffic scenarios is crucial for safely deploying intelligent autonomous systems in the real-world environment. Howeve…
Learning with Instance-Dependent Label Noise: A Sample Sieve Approach
Hao Cheng, Zhaowei Zhu, Xingyu Li +3
Human-annotated labels are often prone to noise, and the presence of such noise will degrade the performance of the resulting deep neural network (DNN) models. Much of the literatu…
Approximate Piecewise Constant Curvature Equivalent Model and Their Application to Continuum Robot Configuration Estimation
Hao Cheng, Houde Liu, Xueqian Wang +1
The continuum robot has attracted more attention for its flexibility. Continuum robot kinematics models are the basis for further perception, planning, and control. The design and…
Pruning Filter in Filter
Fanxu Meng, Hao Cheng, Ke Li +4
Pruning has become a very powerful and effective technique to compress and accelerate modern neural networks. Existing pruning methods can be grouped into two categories: filter pr…
Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians
Shizhen Zhao, Changxin Gao, Jun Zhang +7
In the conventional person Re-ID setting, it is widely assumed that cropped person images are for each individual. However, in a crowded scene, off-shelf-detectors may generate bou…
Attentive Graph Neural Networks for Few-Shot Learning
Hao Cheng, Joey Tianyi Zhou, Wee Peng Tay +1
Graph Neural Networks (GNN) has demonstrated the superior performance in many challenging applications, including the few-shot learning tasks. Despite its powerful capacity to lear…
AMENet: Attentive Maps Encoder Network for Trajectory Prediction
Hao Cheng, Wentong Liao, Michael Ying Yang +2
Trajectory prediction is critical for applications of planning safe future movements and remains challenging even for the next few seconds in urban mixed traffic. How an agent move…
Filter Grafting for Deep Neural Networks: Reason, Method, and Cultivation
Hao Cheng, Fanxu Meng, Ke Li +4
Filter is the key component in modern convolutional neural networks (CNNs). However, since CNNs are usually over-parameterized, a pre-trained network always contain some invalid (u…
Defending against Backdoor Attack on Deep Neural Networks
Hao Cheng, Kaidi Xu, Sijia Liu +3
Although deep neural networks (DNNs) have achieved a great success in various computer vision tasks, it is recently found that they are vulnerable to adversarial attacks. In this p…
MCENET: Multi-Context Encoder Network for Homogeneous Agent Trajectory Prediction in Mixed Traffic
Hao Cheng, Wentong Liao, Michael Ying Yang +2
Trajectory prediction in urban mixed-traffic zones (a.k.a. shared spaces) is critical for many intelligent transportation systems, such as intent detection for autonomous driving.…