no code implementations • NeurIPS 2018 • Tong Yang, Xiangyu Zhang, Zeming Li, Wenqiang Zhang, Jian Sun
We propose a novel and flexible anchor mechanism named MetaAnchor for object detection frameworks.
1 code implementation • 7 Jul 2019 • Yan Wang, Wei Song, Giancarlo Fortino, Lizhe Qi, Wenqiang Zhang, Antonio Liotta
Underwater images play a key role in ocean exploration, but often suffer from severe quality degradation due to light absorption and scattering in water medium.
no code implementations • 25 Sep 2019 • Shizheng Qin, Yichen Zhu, Pengfei Hou, Xiangyu Zhang, Wenqiang Zhang, Jian Sun
In this paper, we propose a learnable sampling module based on variational auto-encoder (VAE) for neural architecture search (NAS), named as VAENAS, which can be easily embedded into existing weight sharing NAS framework, e. g., one-shot approach and gradient-based approach, and significantly improve the performance of searching results.
1 code implementation • 13 Dec 2020 • Wenqiang Zhang, Jiemin Fang, Xinggang Wang, Wenyu Liu
Human pose estimation from image and video is a vital task in many multimedia applications.
no code implementations • 3 Mar 2021 • Ting Wu, Junjie Peng, Wenqiang Zhang, Huiran Zhang, Chuanshuai Ma, Yansong Huang
Humans express feelings or emotions via different channels.
1 code implementation • 23 Mar 2021 • Hao Huang, Yongtao Wang, Zhaoyu Chen, Zhi Tang, Wenqiang Zhang, Kai-Kuang Ma
Firstly, we propose a patch selection and refining scheme to find the pixels which have the greatest importance for attack and remove the inconsequential perturbations gradually.
no code implementations • NAACL 2021 • Yucheng Zhou, Xiubo Geng, Tao Shen, Wenqiang Zhang, Daxin Jiang
That is, we can only access training data in a high-resource language, while need to answer multilingual questions without any labeled data in target languages.
1 code implementation • 12 Jul 2021 • Wei Tao, Yanlin Wang, Ensheng Shi, Lun Du, Shi Han, Hongyu Zhang, Dongmei Zhang, Wenqiang Zhang
We find that: (1) Different variants of the BLEU metric are used in previous works, which affects the evaluation and understanding of existing methods.
1 code implementation • ICCV 2021 • Yiting Cheng, Fangyun Wei, Jianmin Bao, Dong Chen, Fang Wen, Wenqiang Zhang
In this paper, based on the observation that domain adaptation frameworks performed in the source and target domain are almost complementary in terms of image translation and SSL, we propose a novel dual path learning (DPL) framework to alleviate visual inconsistency.
no code implementations • 17 Aug 2021 • Weier Wan, Rajkumar Kubendran, Clemens Schaefer, S. Burc Eryilmaz, Wenqiang Zhang, Dabin Wu, Stephen Deiss, Priyanka Raina, He Qian, Bin Gao, Siddharth Joshi, Huaqiang Wu, H. -S. Philip Wong, Gert Cauwenberghs
Realizing today's cloud-level artificial intelligence functionalities directly on devices distributed at the edge of the internet calls for edge hardware capable of processing multiple modalities of sensory data (e. g. video, audio) at unprecedented energy-efficiency.
no code implementations • 14 Mar 2022 • Siao Liu, Zhaoyu Chen, Wei Li, Jiwei Zhu, Jiafeng Wang, Wenqiang Zhang, Zhongxue Gan
Recently, adversarial attacks have been applied in visual object tracking to deceive deep trackers by injecting imperceptible perturbations into video frames.
no code implementations • CVPR 2022 • Zhaoyu Chen, Bo Li, Jianghe Xu, Shuang Wu, Shouhong Ding, Wenqiang Zhang
To move towards a practical certifiable patch defense, we introduce Vision Transformer (ViT) into the framework of Derandomized Smoothing (DS).
1 code implementation • CVPR 2022 • Yangji He, Weihan Liang, Dongyang Zhao, Hong-Yu Zhou, Weifeng Ge, Yizhou Yu, Wenqiang Zhang
To improve data efficiency, we propose hierarchically cascaded transformers that exploit intrinsic image structures through spectral tokens pooling and optimize the learnable parameters through latent attribute surrogates.
Ranked #1 on Few-Shot Learning on Mini-ImageNet - 1-Shot Learning
no code implementations • CVPR 2022 • Yan Wang, Yixuan Sun, Yiwen Huang, Zhongying Liu, Shuyong Gao, Wei zhang, Weifeng Ge, Wenqiang Zhang
Current benchmarks for facial expression recognition (FER) mainly focus on static images, while there are limited datasets for FER in videos.
Facial Expression Recognition Facial Expression Recognition (FER)
1 code implementation • 22 Mar 2022 • Shuyong Gao, Wei zhang, Yan Wang, Qianyu Guo, Chenglong Zhang, Yangji He, Wenqiang Zhang
Then we develop a transformer-based point-supervised saliency detection model to produce the first round of saliency maps.
1 code implementation • CVPR 2022 • Shaoyu Chen, Xinggang Wang, Tianheng Cheng, Wenqiang Zhang, Qian Zhang, Chang Huang, Wenyu Liu
For segmentation, we integrate AziNorm into KPConv.
2 code implementations • CVPR 2022 • Tianheng Cheng, Xinggang Wang, Shaoyu Chen, Wenqiang Zhang, Qian Zhang, Chang Huang, Zhaoxiang Zhang, Wenyu Liu
In this paper, we propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation.
Ranked #8 on Real-time Instance Segmentation on MSCOCO
3 code implementations • CVPR 2022 • Wenqiang Zhang, Zilong Huang, Guozhong Luo, Tao Chen, Xinggang Wang, Wenyu Liu, Gang Yu, Chunhua Shen
Although vision transformers (ViTs) have achieved great success in computer vision, the heavy computational cost hampers their applications to dense prediction tasks such as semantic segmentation on mobile devices.
1 code implementation • 13 Jun 2022 • Wenqiang Zhang, Tianheng Cheng, Xinggang Wang, Shaoyu Chen, Qian Zhang, Wenyu Liu
The query mechanism introduced in the DETR method is changing the paradigm of object detection and recently there are many query-based methods have obtained strong object detection performance.
no code implementations • 15 Jul 2022 • Shuyong Gao, Haozhe Xing, Wei zhang, Yan Wang, Qianyu Guo, Wenqiang Zhang
Several works attempt to use scribble annotations to mitigate this problem, but point supervision as a more labor-saving annotation method (even the most labor-saving method among manual annotation methods for dense prediction), has not been explored.
1 code implementation • European Conference on Computer Vision 2022 • Zhaoyu Chen, Bo Li, Shuang Wu, Jianghe Xu, Shouhong Ding, Wenqiang Zhang
Though deep neural networks (DNNs) have demonstrated excellent performance in computer vision, they are susceptible and vulnerable to carefully crafted adversarial examples which can mislead DNNs to incorrect outputs.
1 code implementation • ICCV 2023 • Lingyi Hong, Wenchao Chen, Zhongying Liu, Wei zhang, Pinxue Guo, Zhaoyu Chen, Wenqiang Zhang
The videos in our LVOS last 1. 59 minutes on average, which is 20 times longer than videos in existing VOS datasets.
2 code implementations • 21 Nov 2022 • Jiafeng Wang, Zhaoyu Chen, Kaixun Jiang, Dingkang Yang, Lingyi Hong, Pinxue Guo, Haijing Guo, Wenqiang Zhang
To tackle these issues, we propose Global Momentum Initialization (GI) to suppress gradient elimination and help search for the global optimum.
1 code implementation • 28 Nov 2022 • Qianyu Guo, Hongtong Gong, Xujun Wei, Yanwei Fu, Weifeng Ge, Yizhou Yu, Wenqiang Zhang
This paper introduces a new few-shot learning pipeline that casts relevance ranking for image retrieval as binary ranking relation classification.
no code implementations • 19 Dec 2022 • Xiaowen Qiu, Ruize Xu, Boan He, Yingtao Zhang, Wenqiang Zhang, Weifeng Ge
The style removal network removes the original image styles, and the style restoration network recovers image styles in a supervised manner.
1 code implementation • CVPR 2023 • Yixuan Sun, Dongyang Zhao, Zhangyue Yin, Yiwen Huang, Tao Gui, Wenqiang Zhang, Weifeng Ge
The asymmetric feature learning module exploits a biased cross-attention mechanism to encode token features of source images with their target counterparts.
1 code implementation • CVPR 2023 • Yixuan Sun, Yiwen Huang, Haijing Guo, Yuzhou Zhao, Runmin Wu, Yizhou Yu, Weifeng Ge, Wenqiang Zhang
Semantic correspondence have built up a new way for object recognition.
no code implementations • ICCV 2023 • Jinglun Li, Xinyu Zhou, Pinxue Guo, Yixuan Sun, Yiwen Huang, Weifeng Ge, Wenqiang Zhang
We use one fold as the in-distribution dataset and the others as out-of-distribution datasets to evaluate the proposed method.
no code implementations • 17 Feb 2023 • Yuzheng Wang, Zhaoyu Chen, Dingkang Yang, Yang Liu, Siao Liu, Wenqiang Zhang, Lizhe Qi
To this end, we propose a novel structured ARD method called Contrastive Relationship DeNoise Distillation (CRDND).
no code implementations • ICCV 2023 • Kaixun Jiang, Zhaoyu Chen, Hao Huang, Jiafeng Wang, Dingkang Yang, Bo Li, Yan Wang, Wenqiang Zhang
First, STDE introduces target videos as patch textures and only adds patches on keyframes that are adaptively selected by temporal difference.
no code implementations • 21 Mar 2023 • Yuzheng Wang, Zhaoyu Chen, Dingkang Yang, Pinxue Guo, Kaixun Jiang, Wenqiang Zhang, Lizhe Qi
Adversarial Robustness Distillation (ARD) is a promising task to solve the issue of limited adversarial robustness of small capacity models while optimizing the expensive computational costs of Adversarial Training (AT).
1 code implementation • CVPR 2023 • Yiting Cheng, Fangyun Wei, Jianmin Bao, Dong Chen, Wenqiang Zhang
Our framework, termed as domain-aware sign language retrieval via Cross-lingual Contrastive learning or CiCo for short, outperforms the pioneering method by large margins on various datasets, e. g., +22. 4 T2V and +28. 0 V2T R@1 improvements on How2Sign dataset, and +13. 7 T2V and +17. 1 V2T R@1 improvements on PHOENIX-2014T dataset.
Ranked #1 on Sign Language Retrieval on CSL-Daily
1 code implementation • 26 May 2023 • Pinxue Guo, Tony Huang, Peiyang He, Xuefeng Liu, Tianjun Xiao, Zhaoyu Chen, Wenqiang Zhang
Open-vocabulary Video Instance Segmentation (OpenVIS) can simultaneously detect, segment, and track arbitrary object categories in a video, without being constrained to categories seen during training.
no code implementations • 2 Jul 2023 • Zhaoyu Chen, Bo Li, Shuang Wu, Shouhong Ding, Wenqiang Zhang
In this work, we first explore the decision-based patch attack.
no code implementations • 31 Jul 2023 • Yuzheng Wang, Zhaoyu Chen, Jie Zhang, Dingkang Yang, Zuhao Ge, Yang Liu, Siao Liu, Yunquan Sun, Wenqiang Zhang, Lizhe Qi
Then, we introduce a low-noise representation to alleviate the domain shifts and build a structured relationship of multiple data examples to exploit data knowledge.
no code implementations • ICCV 2023 • Siao Liu, Zhaoyu Chen, Yang Liu, Yuzheng Wang, Dingkang Yang, Zhile Zhao, Ziqing Zhou, Xie Yi, Wei Li, Wenqiang Zhang, Zhongxue Gan
In particular, CG2A develops a Gradient Agreement Solver to adaptively balance the varying gradient magnitudes, and introduces a Soft Gradient Surgery strategy to alleviate the gradient conflicts.
1 code implementation • 21 Sep 2023 • Shilin Yan, Xiaohao Xu, Renrui Zhang, Lingyi Hong, Wenchao Chen, Wenqiang Zhang, Wei zhang
Our dataset poses new challenges in panoramic VOS and we hope that our PanoVOS can advance the development of panoramic segmentation/tracking.
no code implementations • 14 Oct 2023 • Qianyu Guo, Huifang Du, Xing Jia, Shuyong Gao, Yan Teng, Haofen Wang, Wenqiang Zhang
Finally, the generated features and prototypes are together to train a more generalized classifier.
no code implementations • 14 Oct 2023 • Yicheng Song, Shuyong Gao, Haozhe Xing, Yiting Cheng, Yan Wang, Wenqiang Zhang
Unsupervised salient object detection aims to detect salient objects without using supervision signals eliminating the tedious task of manually labeling salient objects.
no code implementations • 18 Oct 2023 • Zhaoyu Chen, Bo Li, Kaixun Jiang, Shuang Wu, Shouhong Ding, Wenqiang Zhang
Further, the fake faces by our method can pass face forgery detection and face recognition, which exposes the security problems of face forgery detectors.
no code implementations • 30 Nov 2023 • Lingyi Hong, Wei zhang, Shuyong Gao, Hong Lu, Wenqiang Zhang
We evaluate our method on several benchmark datasets and achieve state-of-the-art results.
1 code implementation • 16 Jan 2024 • Wei Tao, Yucheng Zhou, Yanlin Wang, Hongyu Zhang, Haofen Wang, Wenqiang Zhang
However, previous methods are trained on the entire dataset without considering the fact that a portion of commit messages adhere to good practice (i. e., good-practice commits), while the rest do not.
no code implementations • 2 Feb 2024 • Zhaoyu Chen, Zhengyang Shan, Jingwen Chang, Kaixun Jiang, Dingkang Yang, Yiting Cheng, Wenqiang Zhang
We conduct adversarial robustness evaluation on 5 models from Cityscapes and ADE20K under 8 attacks.
1 code implementation • 20 Feb 2024 • Nailei Hei, Qianyu Guo, ZiHao Wang, Yan Wang, Haofen Wang, Wenqiang Zhang
To bridge the distribution gap between user input behavior and model training datasets, we first construct a novel Coarse-Fine Granularity Prompts dataset (CFP) and propose a novel User-Friendly Fine-Grained Text Generation framework (UF-FGTG) for automated prompt optimization.
no code implementations • NeurIPS 2023 • Xinyu Zhou, Pinxue Guo, Lingyi Hong, Jinglun Li, Wei zhang, Weifeng Ge, Wenqiang Zhang
Therefore, using all features in the template and memory can lead to redundancy and impair tracking performance.
no code implementations • 7 Mar 2024 • Zeng Tao, Yan Wang, Junxiong Lin, Haoran Wang, Xinji Mai, Jiawen Yu, Xuan Tong, Ziheng Zhou, Shaoqi Yan, Qing Zhao, Liyuan Han, Wenqiang Zhang
Specifically, our A$^{3}$lign-DFER method is designed with multiple modules that work together to obtain the most suitable expanded-dimensional embeddings for classification and to achieve alignment in three key aspects: affective, dynamic, and bidirectional.
Dynamic Facial Expression Recognition Facial Expression Recognition
no code implementations • 9 Mar 2024 • Junxiong Lin, Yan Wang, Zeng Tao, Boyang Wang, Qing Zhao, Haorang Wang, Xuan Tong, Xinji Mai, Yuxuan Lin, Wei Song, Jiawen Yu, Shaoqi Yan, Wenqiang Zhang
Harnessing the potential of leveraging this a priori knowledge in the context of image super-resolution presents a compelling avenue.
1 code implementation • 10 Mar 2024 • Pinxue Guo, Lingyi Hong, Xinyu Zhou, Shuyong Gao, Wanyun Li, Jinglun Li, Zhaoyu Chen, Xiaoqiang Li, Wei zhang, Wenqiang Zhang
To address these limitations, we propose the setting named Click Video Object Segmentation (ClickVOS) which segments objects of interest across the whole video according to a single click per object in the first frame.
no code implementations • 13 Mar 2024 • Wanyun Li, Pinxue Guo, Xinyu Zhou, Lingyi Hong, Yangji He, Xiangyu Zheng, Wei zhang, Wenqiang Zhang
Contemporary Video Object Segmentation (VOS) approaches typically consist stages of feature extraction, matching, memory management, and multiple objects aggregation.
no code implementations • 14 Mar 2024 • Lingyi Hong, Shilin Yan, Renrui Zhang, Wanyun Li, Xinyu Zhou, Pinxue Guo, Kaixun Jiang, Yiting Chen, Jinglun Li, Zhaoyu Chen, Wenqiang Zhang
To evaluate the effectiveness of our general framework OneTracker, which is consisted of Foundation Tracker and Prompt Tracker, we conduct extensive experiments on 6 popular tracking tasks across 11 benchmarks and our OneTracker outperforms other models and achieves state-of-the-art performance.
no code implementations • 16 Mar 2024 • Jiyuan Fu, Zhaoyu Chen, Kaixun Jiang, Haijing Guo, Jiafeng Wang, Shuyong Gao, Wenqiang Zhang
Existing work rarely studies the transferability of attacks on VLP models, resulting in a substantial performance gap from white-box attacks.
no code implementations • 26 Mar 2024 • Wei Tao, Yucheng Zhou, Wenqiang Zhang, Yu Cheng
Motivated by the empirical findings, we propose a novel LLM-based Multi-Agent framework for GitHub Issue reSolution, MAGIS, consisting of four kinds of agents customized for the software evolution: Manager, Repository Custodian, Developer, and Quality Assurance Engineer agents.