no code implementations • ECCV 2020 • Zilong Ji, Xiaolong Zou, Xiaohan Lin, Xiao Liu, Tiejun Huang, Si Wu
By iteratively learning with the two strategies, the attentive regions are gradually shifted from the background to the foreground and the features become more discriminative.
no code implementations • 3 Apr 2024 • Yao Lu, Si Wu
We show that to store arbitrary pattern sequences, it is necessary for the network to include hidden neurons even though their role in displaying sequence memories is indirect.
no code implementations • 3 Dec 2023 • Fan Yang, Tianyi Chen, Xiaosheng He, Zhongang Cai, Lei Yang, Si Wu, Guosheng Lin
We propose AttriHuman-3D, an editable 3D human generation model, which address the aforementioned problems with attribute decomposition and indexing.
2 code implementations • 9 Nov 2023 • ChaoMing Wang, Tianqiu Zhang, Sichao He, Hongyaoxing Gu, Shangyang Li, Si Wu
Brain simulation builds dynamical models to mimic the structure and functions of the brain, while brain-inspired computing (BIC) develops intelligent systems by learning from the structure and functions of the brain.
1 code implementation • 5 Jun 2023 • Si Wu, David A. Smith
Although psycholinguists and psychologists have long studied the tendency of linguistic strings to evoke mental images in hearers or readers, most computational studies have applied this concept of imageability only to isolated words.
no code implementations • 20 Jan 2023 • Luyao Chen, Zhiqiang Chen, Longsheng Jiang, Xiang Liu, Linlu Xu, Bo Zhang, Xiaolong Zou, Jinying Gao, Yu Zhu, Xizi Gong, Shan Yu, Sen Song, Liangyi Chen, Fang Fang, Si Wu, Jia Liu
Nowadays, we have witnessed the great success of AI in various applications, including image classification, game playing, protein structure analysis, language translation, and content generation.
no code implementations • CVPR 2023 • Xiwen Wei, Zhen Xu, Cheng Liu, Si Wu, Zhiwen Yu, Hau San Wong
To address this limitation, we propose a Text-guided Unsupervised StyleGAN Latent Transformation (TUSLT) model, which adaptively infers a single transformation step in the latent space of StyleGAN to simultaneously manipulate multiple attributes on a given input image.
no code implementations • CVPR 2023 • Yunfei Zhang, Xiaoyang Huo, Tianyi Chen, Si Wu, Hau San Wong
Semi-supervised class-conditional image synthesis is typically performed by inferring and injecting class labels into a conditional Generative Adversarial Network (GAN).
no code implementations • CVPR 2023 • Wenhao Wu, Hau San Wong, Si Wu
Stereo-based 3D object detection, which aims at detecting 3D objects with stereo cameras, shows great potential in low-cost deployment compared to LiDAR-based methods and excellent performance compared to monocular-based algorithms.
no code implementations • CVPR 2023 • Lianxin Xie, Wen Xue, Zhen Xu, Si Wu, Zhiwen Yu, Hau San Wong
It is worth noting that we reduce the dependence of BPFRe on paired training samples by imposing effective regularization on unpaired ones.
no code implementations • 30 Nov 2022 • Si Wu, Tengfei Liu, Magnus Egerstedt, Zhong-Ping Jiang
Also, the interaction between the controlled integrator and the uncertain actuation dynamics may lead to significant robustness issues.
no code implementations • 23 Jan 2022 • Tiejun Huang, Yajing Zheng, Zhaofei Yu, Rui Chen, Yuan Li, Ruiqin Xiong, Lei Ma, Junwei Zhao, Siwei Dong, Lin Zhu, Jianing Li, Shanshan Jia, Yihua Fu, Boxin Shi, Si Wu, Yonghong Tian
By treating vidar as spike trains in biological vision, we have further developed a spiking neural network-based machine vision system that combines the speed of the machine and the mechanism of biological vision, achieving high-speed object detection and tracking 1, 000x faster than human vision.
no code implementations • CVPR 2022 • Tianyi Chen, Yunfei Zhang, Xiaoyang Huo, Si Wu, Yong Xu, Hau San Wong
To reduce the dependence of generative models on labeled data, we propose a semi-supervised hyper-spherical GAN for class-conditional fine-grained image generation, and our model is referred to as SphericGAN.
1 code implementation • 23 Dec 2021 • Alejandro H. Toselli, Si Wu, David A. Smith
Using markup schemes such as those of the Text Encoding Initiative and EpiDoc, these digital editions often record documents' semantic regions (such as notes and figures) and physical features (such as page and line breaks) as well as transcribing their textual content.
no code implementations • NeurIPS 2021 • Xingsi Dong, Tianhao Chu, Tiejun Huang, Zilong Ji, Si Wu
To elucidate the underlying mechanism clearly, we first study continuous attractor neural networks (CANNs), and find that noisy neural adaptation, exemplified by spike frequency adaptation (SFA) in this work, can generate Lévy flights representing transitions of the network state in the attractor space.
no code implementations • EMNLP 2021 • Nikita Srivatsan, Si Wu, Jonathan T. Barron, Taylor Berg-Kirkpatrick
We propose a deep generative model that performs typography analysis and font reconstruction by learning disentangled manifolds of both font style and character shape.
no code implementations • CVPR 2021 • Yi Liu, Xiaoyang Huo, Tianyi Chen, Xiangping Zeng, Si Wu, Zhiwen Yu, Hau-San Wong
Semi-supervised generative learning (SSGL) makes use of unlabeled data to achieve a trade-off between the data collection/annotation effort and generation performance, when adequate labeled data are not available.
no code implementations • ICCV 2021 • Tianyi Chen, Yi Liu, Yunfei Zhang, Si Wu, Yong Xu, Feng Liangbing, Hau San Wong
To ensure disentanglement among the variables, we maximize mutual information between the class-independent variable and synthesized images, map real images to the latent space of a generator to perform consistency regularization of cross-class attributes, and incorporate class semantic-based regularization into a discriminator's feature space.
no code implementations • 23 Aug 2020 • Zilong Ji, Xiaolong Zou, Tiejun Huang, Si Wu
In this study, we build a computational model to elucidate the computational advantages associated with the interactions between two pathways.
no code implementations • 20 Dec 2019 • Zilong Ji, Xiaolong Zou, Tiejun Huang, Si Wu
The proposed model consists of two alternate processes, progressive clustering and episodic training.
1 code implementation • NeurIPS 2019 • Xiao Liu, Xiaolong Zou, Zilong Ji, Gengshuo Tian, Yuanyuan Mi, Tiejun Huang, K. Y. Michael Wong, Si Wu
Experimental data has revealed that in addition to feedforward connections, there exist abundant feedback connections in a neural pathway.
1 code implementation • NeurIPS 2019 • Wenhao Zhang, Si Wu, Brent Doiron, Tai Sing Lee
This study provides a normative theory for how Bayesian causal inference can be implemented in neural circuits.
no code implementations • ICCV 2019 • Si Wu, Sihao Lin, Wenhao Wu, Mohamed Azzam, Hau-San Wong
We propose a GAN-based scene-specific instance synthesis and classification model for semi-supervised pedestrian detection.
no code implementations • 25 Sep 2019 • Zilong Ji, Xiaolong Zou, Tiejun Huang, Si Wu
Using the benchmark dataset Omniglot, we show that our model outperforms other unsupervised few-shot learning methods to a large extend and approaches to the performances of supervised methods.
no code implementations • 28 Jul 2019 • Yuanyuan Mi, Xiaohan Lin, Xiaolong Zou, Zilong Ji, Tiejun Huang, Si Wu
Spatiotemporal information processing is fundamental to brain functions.
no code implementations • CVPR 2019 • Si Wu, Guangchang Deng, Jichang Li, Rui Li, Zhiwen Yu, Hau-San Wong
We follow the adversarial training scheme of the original TripleGAN, but completely re-design the training targets of the generator and classifier.
no code implementations • CVPR 2019 • Si Wu, Jichang Li, Cheng Liu, Zhiwen Yu, Hau-San Wong
Our experimental results demonstrate that the proposed approach clearly improves mutual learning between essential networks, and achieves state-of-the-art results on multiple semi-supervised classification benchmarks.
no code implementations • NeurIPS 2016 • Wen-Hao Zhang, He Wang, K. Y. Michael Wong, Si Wu
Mimicking the experimental protocol, our model reproduces the characteristics of congruent and opposite neurons, and demonstrates that in each module, the sisters of congruent and opposite neurons can jointly achieve optimal multisensory information integration and segregation.
no code implementations • NeurIPS 2014 • Yuanyuan Mi, Luozheng Li, Dahui Wang, Si Wu
Here, in contrast to the view of attractor, we consider that the stimulus information is encoded in a marginally unstable state of the network which decays very slowly and exhibits persistent firing for a prolonged duration.
no code implementations • NeurIPS 2014 • Yuanyuan Mi, C. C. Alan Fung, K. Y. Michael Wong, Si Wu
To extract motion information, the brain needs to compensate for time delays that are ubiquitous in neural signal transmission and processing.
no code implementations • NeurIPS 2013 • Wen-Hao Zhang, Si Wu
Psychophysical experiments have demonstrated that the brain integrates information from multiple sensory cues in a near Bayesian optimal manner.
no code implementations • NeurIPS 2012 • Chi Fung, K. Wong, Si Wu
To achieve real-time tracking, it is critical to compensate the transmission and processing delays in a neural system.
no code implementations • NeurIPS 2010 • K. Wong, He Wang, Si Wu, Chi Fung
Neuronal connection weights exhibit short-term depression (STD).
no code implementations • NeurIPS 2008 • K. Wong, Si Wu, Chi Fung
Continuous attractor neural networks (CANNs) are emerging as promising models for describing the encoding of continuous stimuli in neural systems.