2 code implementations • 16 Dec 2024 • Yuanzhi Wang, Yong Li, Mengyi Liu, Xiaoya Zhang, Xin Liu, Zhen Cui, Antoni B. Chan
Therefore, the controllability of video editing remains a formidable challenge.
1 code implementation • 27 Nov 2024 • Ying Xiong, Linjing Liu, Yufei Cui, Shangyu Wu, Xue Liu, Antoni B. Chan, Chun Jason Xue
Gene expression profiling provides profound insights into molecular mechanisms, but its time-consuming and costly nature often presents significant challenges.
no code implementations • 27 Nov 2024 • Bo Fang, Wenhao Wu, Qiangqiang Wu, Yuxin Song, Antoni B. Chan
Audio Descriptions (ADs) aim to provide a narration of a movie in text form, describing non-dialogue-related narratives, such as characters, actions, or scene establishment.
1 code implementation • 3 Sep 2024 • Qi Zhang, Kaiyi Zhang, Antoni B. Chan, Hui Huang
Second, the object-to-camera distance in each view is used to adjust the optimal transport cost of each location further, where the wrong predictions far away from the camera are more heavily penalized.
Ranked #1 on
Multiview Detection
on CVCS
1 code implementation • 30 May 2024 • Qi Zhang, Yunfei Gong, Daijie Chen, Antoni B. Chan, Hui Huang
Recent deep learning-based multi-view people detection (MVD) methods have shown promising results on existing datasets.
Ranked #2 on
Multiview Detection
on CVCS
1 code implementation • 14 May 2024 • Ziquan Liu, Yufei Cui, Yan Yan, Yi Xu, Xiangyang Ji, Xue Liu, Antoni B. Chan
In safety-critical applications such as medical imaging and autonomous driving, where decisions have profound implications for patient health and road safety, it is imperative to maintain both high adversarial robustness to protect against potential adversarial attacks and reliable uncertainty quantification in decision-making.
1 code implementation • 18 Apr 2024 • Wei Wu, Qingnan Fan, Shuai Qin, Hong Gu, Ruoyu Zhao, Antoni B. Chan
Precise image editing with text-to-image models has attracted increasing interest due to their remarkable generative capabilities and user-friendly nature.
no code implementations • 15 Apr 2024 • Qiangqiang Wu, Antoni B. Chan
In this paper, we propose to learn tracking representations from single point annotations (i. e., 4. 5x faster to annotate than the traditional bounding box) in a weakly supervised manner.
no code implementations • 15 Mar 2024 • Wei Lin, Antoni B. Chan
Additionally, a contrastive training scheme is implemented to mitigate dataset bias inherent in current class-agnostic counting datasets, a strategy whose effectiveness is confirmed by our ablation study.
no code implementations • 27 Feb 2024 • Jia Wan, Qiangqiang Wu, Wei Lin, Antoni B. Chan
The existing crowd counting models require extensive training data, which is time-consuming to annotate.
1 code implementation • 17 Aug 2023 • Yuanzhi Wang, Yong Li, Xiaoya Zhang, Xin Liu, Anbo Dai, Antoni B. Chan, Zhen Cui
In addition to the utilization of a pretrained T2I 2D Unet for spatial content manipulation, we establish a dedicated temporal Unet architecture to faithfully capture the temporal coherence of the input video sequences.
no code implementations • 5 May 2023 • Guoyang Liu, Jindi Zhang, Antoni B. Chan, Janet H. Hsiao
We examined whether embedding human attention knowledge into saliency-based explainable AI (XAI) methods for computer vision models could enhance their plausibility and faithfulness.
no code implementations • 13 Apr 2023 • 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.
1 code implementation • CVPR 2023 • Qiangqiang Wu, Tianyu Yang, Ziquan Liu, Baoyuan Wu, Ying Shan, Antoni B. Chan
However, we find that this simple baseline heavily relies on spatial cues while ignoring temporal relations for frame reconstruction, thus leading to sub-optimal temporal matching representations for VOT and VOS.
Ranked #1 on
Visual Object Tracking
on TrackingNet
(AUC metric)
1 code implementation • CVPR 2023 • Ziquan Liu, Yi Xu, Xiangyang Ji, Antoni B. Chan
To better exploit the potential of pre-trained models in adversarial robustness, this paper focuses on the fine-tuning of an adversarially pre-trained model in various classification tasks.
1 code implementation • CVPR 2023 • Wei Lin, Antoni B. Chan
In this paper, we propose the optimal transport minimization (OT-M) algorithm for crowd localization with density maps.
1 code implementation • Conference 2022 • Wei Lin, Kunlin Yang, Xinzhu Ma, Junyu Gao, Lingbo Liu, Shinan Liu, Jun Hou, Shuai Yi, Antoni B. Chan
Here we propose a scale-sensitive generalized loss to tackle this problem.
Ranked #10 on
Object Counting
on FSC147
no code implementations • 11 Oct 2022 • Ziquan Liu, Antoni B. Chan
Our empirical study on feedforward DNNs demonstrates that the proposed effective margin regularization (EMR) learns large effective margins and boosts the adversarial robustness in both standard and adversarial training.
no code implementations • 4 Jul 2022 • Xueying Zhan, Zeyu Dai, Qingzhong Wang, Qing Li, Haoyi Xiong, Dejing Dou, Antoni B. Chan
In this paper, we propose a sampling scheme, Monte-Carlo Pareto Optimization for Active Learning (POAL), which selects optimal subsets of unlabeled samples with fixed batch size from the unlabeled data pool.
no code implementations • 25 May 2022 • Ziquan Liu, Yi Xu, Yuanhong Xu, Qi Qian, Hao Li, Rong Jin, Xiangyang Ji, Antoni B. Chan
With our empirical result obtained from 1, 330 models, we provide the following main observations: 1) ERM combined with data augmentation can achieve state-of-the-art performance if we choose a proper pre-trained model respecting the data property; 2) specialized algorithms further improve the robustness on top of ERM when handling a specific type of distribution shift, e. g., GroupDRO for spurious correlation and CORAL for large-scale out-of-distribution data; 3) Comparing different pre-training modes, architectures and data sizes, we provide novel observations about pre-training on distribution shift, which sheds light on designing or selecting pre-training strategy for different kinds of distribution shifts.
no code implementations • CVPR 2021 • 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 counting performance for occluded people or those in low resolution.
no code implementations • 8 Apr 2022 • Jiuniu Wang, Wenjia Xu, Qingzhong Wang, Antoni B. Chan
First, we propose a distinctiveness metric -- between-set CIDEr (CIDErBtw) to evaluate the distinctiveness of a caption with respect to those of similar images.
1 code implementation • 25 Mar 2022 • Xueying Zhan, Qingzhong Wang, Kuan-Hao Huang, Haoyi Xiong, Dejing Dou, Antoni B. Chan
In this work, We construct a DAL toolkit, DeepAL+, by re-implementing 19 highly-cited DAL methods.
1 code implementation • 8 Mar 2022 • Yan Xia, Qiangqiang Wu, Wei Li, Antoni B. Chan, Uwe Stilla
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.
1 code implementation • CVPR 2022 • Weibo Shu, Jia Wan, Kay Chen Tan, Sam Kwong, Antoni B. Chan
By transforming the density map into the frequency domain and using the nice properties of the characteristic function, we propose a novel method that is simple, effective, and efficient.
1 code implementation • ICCV 2021 • Zhirui Dai, Yuepeng Jiang, Yi Li, Bo Liu, Antoni B. Chan, Nuno Vasconcelos
A dataset of crowd scenes with people annotations under a bird's eye view (BEV) and ground truth for metric distances is introduced, and several measures for the evaluation of social distance detection systems are proposed.
no code implementations • 20 Aug 2021 • Jiuniu Wang, Wenjia Xu, Qingzhong Wang, Antoni B. Chan
In particular, we propose a group-based memory attention (GMA) module, which stores object features that are unique among the image group (i. e., with low similarity to objects in other images).
no code implementations • 4 Jul 2021 • Xueying Zhan, Qing Li, Antoni B. Chan
In this paper, we introduce a multiple-criteria based active learning algorithm, which incorporates three complementary criteria, i. e., informativeness, representativeness and diversity, to make appropriate selections in the active learning rounds under different data types.
no code implementations • CVPR 2021 • Jia Wan, Ziquan Liu, Antoni B. Chan
In this paper, we investigate learning the density map representation through an unbalanced optimal transport problem, and propose a generalized loss function to learn density maps for crowd counting and localization.
no code implementations • CVPR 2021 • Qiangqiang Wu, Jia Wan, Antoni B. Chan
In this paper, we propose a progressive unsupervised learning (PUL) framework, which entirely removes the need for annotated training videos in visual tracking.
no code implementations • 6 Feb 2021 • Ziquan Liu, Yufei Cui, Jia Wan, Yu Mao, Antoni B. Chan
On the one hand, when the non-adaptive learning rate e. g. SGD with momentum is used, the effective learning rate continues to increase even after the initial training stage, which leads to an overfitting effect in many neural architectures.
1 code implementation • CVPR 2021 • Yufei Cui, Yu Mao, Ziquan Liu, Qiao Li, Antoni B. Chan, Xue Liu, Tei-Wei Kuo, Chun Jason Xue
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.
1 code implementation • 2 Dec 2020 • Qi Zhang, Antoni B. Chan
We consider three versions of the fusion framework: the late fusion model fuses camera-view density map; the naive early fusion model fuses camera-view feature maps; and the multi-view multi-scale early fusion model ensures that features aligned to the same ground-plane point have consistent scales.
no code implementations • ICML Workshop AML 2021 • Ziquan Liu, Yufei Cui, Antoni B. Chan
The derived regularizer is an upper bound for the input gradient of the network so minimizing the improved regularizer also benefits the adversarial robustness.
no code implementations • 18 Jul 2020 • Weihong Ren, Xinchao Wang, Jiandong Tian, Yandong Tang, Antoni B. Chan
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 detectors.
no code implementations • ECCV 2020 • Jiuniu Wang, Wenjia Xu, Qingzhong Wang, Antoni B. Chan
A wide range of image captioning models has been developed, achieving significant improvement based on popular metrics, such as BLEU, CIDEr, and SPICE.
no code implementations • 13 Jul 2020 • Jia Wan, Nikil Senthil Kumar, Antoni B. Chan
Second, we propose a complementary attention model to share information between the two branches.
1 code implementation • 8 Jul 2020 • Qi Zhang, Antoni B. Chan
To handle the issue of unsynchronized multi-cameras, in this paper, we propose a synchronization model that works in conjunction with existing DNN-based multi-view models, thus avoiding the redesign of the whole model.
no code implementations • 9 Jun 2020 • Yuzhen Niu, Weifeng Shi, Wenxi Liu, Shengfeng He, Jia Pan, Antoni B. Chan
In this paper, we formulate a novel crowd analysis problem, in which we aim to predict the crowd distribution in the near future given sequential frames of a crowd video without any identity annotations.
no code implementations • 18 Mar 2020 • Qi Zhang, Antoni B. Chan
Unlike the previous research, we consider the variable height of the people in the 3D world and propose to solve the multi-view crowd counting task through 3D feature fusion with 3D scene-level density maps, instead of the 2D density map on the ground plane.
1 code implementation • 14 Aug 2019 • Qingzhong Wang, Antoni B. Chan
Although significant progress has been made in the field of automatic image captioning, it is still a challenging task.
no code implementations • CVPR 2020 • Tianyu Yang, Pengfei Xu, Runbo Hu, Hua Chai, Antoni B. Chan
In this paper, we design a tracking model consisting of response generation and bounding box regression, where the first component produces a heat map to indicate the presence of the object at different positions and the second part regresses the relative bounding box shifts to anchors mounted on sliding-window locations.
no code implementations • 12 Jul 2019 • Tianyu Yang, Antoni B. Chan
The reading and writing process of the external memory is controlled by an LSTM network with the search feature map as input.
1 code implementation • 29 May 2019 • Yufei Cui, Wuguannan Yao, Qiao Li, Antoni B. Chan, Chun Jason Xue
In this work, assuming that the exact posterior or a decent approximation is obtained, we propose a generic framework to approximate the output probability distribution induced by model posterior with a parameterized model and in an amortized fashion.
1 code implementation • CVPR 2019 • Qingzhong Wang, Antoni B. Chan
We find that there is still a large gap between the model and human performance in terms of both accuracy and diversity and the models that have optimized accuracy (CIDEr) have low diversity.
no code implementations • 13 Jan 2019 • Sahar Yousefi, M. T. Manzuri Shalmani, Antoni B. Chan
A major limitation of these models concerns the automatic selection of a proper number of DTs.
1 code implementation • 30 Oct 2018 • Qingzhong Wang, Antoni B. Chan
Attention modules connecting encoder and decoders have been widely applied in the field of object recognition, image captioning, visual question answering and neural machine translation, and significantly improves the performance.
no code implementations • 17 Oct 2018 • Antoni B. Chan, Janet H. Hsiao
Eye Movement analysis with Hidden Markov Models (EMHMM) is a method for modeling eye fixation sequences using hidden Markov models (HMMs).
no code implementations • CVPR 2018 • Weihong Ren, Di Kang, Yandong Tang, Antoni B. Chan
While people tracking has been greatly improved over the recent years, crowd scenes remain particularly challenging for people tracking due to heavy occlusions, high crowd density, and significant appearance variation.
1 code implementation • 23 May 2018 • Qingzhong Wang, Antoni B. Chan
We also test our model on the paragraph annotation dataset, and get higher CIDEr score compared with hierarchical LSTMs
1 code implementation • ECCV 2018 • Tianyu Yang, Antoni B. Chan
In this paper, we propose a dynamic memory network to adapt the template to the target's appearance variations during tracking.
1 code implementation • 13 Aug 2017 • Tianyu Yang, Antoni B. Chan
Recently using convolutional neural networks (CNNs) has gained popularity in visual tracking, due to its robust feature representation of images.
1 code implementation • 29 May 2017 • Di Kang, Zheng Ma, Antoni B. Chan
The goal of this paper is to evaluate density maps generated by density estimation methods on a variety of crowd analysis tasks, including counting, detection, and tracking.
no code implementations • 17 Mar 2017 • Huy Q. Phan, Hongbo Fu, Antoni B. Chan
As artists often use their personal color themes in their paintings, making these palettes appear frequently in the dataset, we employed density estimation to capture the characteristics of palette data.
no code implementations • 21 Nov 2016 • Di Kang, Debarun Dhar, Antoni B. Chan
In order to incorporate the available side information, we propose an adaptive convolutional neural network (ACNN), where the convolutional filter weights adapt to the current scene context via the side information.
no code implementations • ICCV 2015 • Sijin Li, Weichen Zhang, Antoni B. Chan
The score function is then the dot-product between the image and pose embeddings.
Ranked #331 on
3D Human Pose Estimation
on Human3.6M
no code implementations • CVPR 2015 • Zheng Ma, Lei Yu, Antoni B. Chan
For each region, a sliding window (ROI) is passed over the density map to calculate the instance count within each ROI.
no code implementations • 13 Jun 2014 • Sijin Li, Zhi-Qiang Liu, Antoni B. Chan
We propose an heterogeneous multi-task learning framework for human pose estimation from monocular image with deep convolutional neural network.
no code implementations • CVPR 2014 • Adeel Mumtaz, Weichen Zhang, Antoni B. Chan
We derive an EM algorithm for estimating the parameters of the FBM.
no code implementations • 10 Feb 2014 • Wenxi Liu, Antoni B. Chan, Rynson W. H. Lau, Dinesh Manocha
We present a multiple-person tracking algorithm, based on combining particle filters and RVO, an agent-based crowd model that infers collision-free velocities so as to predict pedestrian's motion.
no code implementations • 25 Nov 2013 • Lifeng Shang, Antoni B. Chan
In this paper, we consider efficient algorithms for approximate inference on GGPMs using the general form of the EFD.
no code implementations • 2 Nov 2013 • Antoni B. Chan
We propose a family of multivariate Gaussian process models for correlated outputs, based on assuming that the likelihood function takes the generic form of the multivariate exponential family distribution (EFD).
no code implementations • CVPR 2013 • Zheng Ma, Antoni B. Chan
Next, the number of people is estimated in a set of overlapping sliding windows on the temporal slice image, using a regression function that maps from local features to a count.
no code implementations • NeurIPS 2012 • Emanuele Coviello, Gert R. Lanckriet, Antoni B. Chan
In this paper, we derive a novel algorithm to cluster hidden Markov models (HMMs) according to their probability distributions.