111 citations · 734 across the 50 of their papers we have counts for
50 papers
Scalable Video Object Segmentation with Simplified Framework
Qiangqiang Wu, Tianyu Yang, Wei WU +1
The current popular methods for video object segmentation (VOS) implement feature matching through several hand-crafted modules that separately perform feature extraction and match…
Edit Temporal-Consistent Videos with Image Diffusion Model
Yuanzhi Wang, Yong Li, Xiaoya Zhang +4
Large-scale text-to-image (T2I) diffusion models have been extended for text-guided video editing, yielding impressive zero-shot video editing performance. Nonetheless, the generat…
Human Attention-Guided Explainable Artificial Intelligence for Computer Vision Models
Guoyang Liu, Jindi Zhang, Antoni B. Chan +1
We examined whether embedding human attention knowledge into saliency-based explainable AI (XAI) methods for computer vision models could enhance their plausibility and faithfulnes…
ODAM: Gradient-based instance-specific visual explanations for object detection
Chenyang Zhao, Antoni B. Chan
We propose the gradient-weighted Object Detector Activation Maps (ODAM), a visualized explanation technique for interpreting the predictions of object detectors. Utilizing the grad…
DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks
Qiangqiang Wu, Tianyu Yang, Ziquan Liu +3
This paper studies masked autoencoder (MAE) video pre-training for various temporal matching-based downstream tasks, i.e., object-level tracking tasks including video object tracki…
TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization
Ziquan Liu, Yi Xu, Xiangyang Ji +1
Recent years have seen the ever-increasing importance of pre-trained models and their downstream training in deep learning research and applications. At the same time, the defense…
Boosting Adversarial Robustness From The Perspective of Effective Margin Regularization
Ziquan Liu, Antoni B. Chan
The adversarial vulnerability of deep neural networks (DNNs) has been actively investigated in the past several years. This paper investigates the scale-variant property of cross-e…
Pareto Optimization for Active Learning under Out-of-Distribution Data Scenarios
Xueying Zhan, Zeyu Dai, Qingzhong Wang +4
Pool-based Active Learning (AL) has achieved great success in minimizing labeling cost by sequentially selecting informative unlabeled samples from a large unlabeled data pool and…
An Empirical Study on Distribution Shift Robustness From the Perspective of Pre-Training and Data Augmentation
Ziquan Liu, Yi Xu, Yuanhong Xu +5
The performance of machine learning models under distribution shift has been the focus of the community in recent years. Most of current methods have been proposed to improve the r…
Cross-View Cross-Scene Multi-View Crowd Counting
Qi Zhang, Wei Lin, Antoni B. Chan
Multi-view crowd counting has been previously proposed to utilize multi-cameras to extend the field-of-view of a single camera, capturing more people in the scene, and improve coun…
On Distinctive Image Captioning via Comparing and Reweighting
Jiuniu Wang, Wenjia Xu, Qingzhong Wang +1
Recent image captioning models are achieving impressive results based on popular metrics, i.e., BLEU, CIDEr, and SPICE. However, focusing on the most popular metrics that only cons…
A Comparative Survey of Deep Active Learning
Xueying Zhan, Qingzhong Wang, Kuan-hao Huang +3
While deep learning (DL) is data-hungry and usually relies on extensive labeled data to deliver good performance, Active Learning (AL) reduces labeling costs by selecting a small p…
A Lightweight and Detector-free 3D Single Object Tracker on Point Clouds
Yan Xia, Qiangqiang Wu, Wei Li +2
Recent works on 3D single object tracking treat the task as a target-specific 3D detection task, where an off-the-shelf 3D detector is commonly employed for the tracking. However,…
Improved Fine-Tuning by Better Leveraging Pre-Training Data
Ziquan Liu, Yi Xu, Yuanhong Xu +5
As a dominant paradigm, fine-tuning a pre-trained model on the target data is widely used in many deep learning applications, especially for small data sets. However, recent studie…
BEV-Net: Assessing Social Distancing Compliance by Joint People Localization and Geometric Reasoning
Zhirui Dai, Yuepeng Jiang, Yi Li +3
Social distancing, an essential public health measure to limit the spread of contagious diseases, has gained significant attention since the outbreak of the COVID-19 pandemic. In t…
Group-based Distinctive Image Captioning with Memory Attention
Jiuniu Wang, Wenjia Xu, Qingzhong Wang +1
Describing images using natural language is widely known as image captioning, which has made consistent progress due to the development of computer vision and natural language gene…
Multiple-criteria Based Active Learning with Fixed-size Determinantal Point Processes
Xueying Zhan, Qing Li, Antoni B. Chan
Active learning aims to achieve greater accuracy with less training data by selecting the most useful data samples from which it learns. Single-criterion based methods (i.e., infor…
Weight Rescaling: Effective and Robust Regularization for Deep Neural Networks with Batch Normalization
Ziquan Liu, Yufei Cui, Jia Wan +2
Weight decay is often used to ensure good generalization in the training practice of deep neural networks with batch normalization (BN-DNNs), where some convolution layers are inva…
Variational Nested Dropout
Yufei Cui, Yu Mao, Ziquan Liu +5
Nested dropout is a variant of dropout operation that is able to order network parameters or features based on the pre-defined importance during training. It has been explored for:…
Direct Quantization for Training Highly Accurate Low Bit-width Deep Neural Networks
Tuan Hoang, Thanh-Toan Do, Tam V. Nguyen +1
This paper proposes two novel techniques to train deep convolutional neural networks with low bit-width weights and activations. First, to obtain low bit-width weights, most existi…
Wide-Area Crowd Counting: Multi-View Fusion Networks for Counting in Large Scenes
Qi Zhang, Antoni B. Chan
Crowd counting in single-view images has achieved outstanding performance on existing counting datasets. However, single-view counting is not applicable to large and wide scenes (e…
ALdataset: a benchmark for pool-based active learning
Xueying Zhan, Antoni Bert Chan
Active learning (AL) is a subfield of machine learning (ML) in which a learning algorithm could achieve good accuracy with less training samples by interactively querying a user/or…
Improve Generalization and Robustness of Neural Networks via Weight Scale Shifting Invariant Regularizations
Ziquan Liu, Yufei Cui, Antoni B. Chan
Using weight decay to penalize the L2 norms of weights in neural networks has been a standard training practice to regularize the complexity of networks. In this paper, we show tha…
Tracking-by-Counting: Using Network Flows on Crowd Density Maps for Tracking Multiple Targets
Weihong Ren, Xinchao Wang, Jiandong Tian +2
State-of-the-art multi-object tracking~(MOT) methods follow the tracking-by-detection paradigm, where object trajectories are obtained by associating per-frame outputs of object de…