1 code implementation • 18 Jun 2025 • Han Wu, Junyao Li, Kangbo Zhao, Sen Zhang, Yukai Shi, Liang Lin
In this paper, we propose a one-shot face sketch synthesis method based on diffusion models.
no code implementations • 17 Jun 2025 • Zijian Song, Xiaoxin Lin, Qiuming Huang, Guangrun Wang, Liang Lin
Large Language Models (LLMs) are experiencing rapid advancements in complex reasoning, exhibiting remarkable generalization in mathematics and programming.
1 code implementation • 12 Jun 2025 • Shicheng Yin, Kaixuan Yin, Yang Liu, Weixing Chen, Liang Lin
Recently, non-convolutional models such as the Vision Transformer (ViT) and Vision Mamba (Vim) have achieved remarkable performance in computer vision tasks.
1 code implementation • 26 May 2025 • Zhongzhan Huang, Guoming Ling, Shanshan Zhong, Hefeng Wu, Liang Lin
Long Context Understanding (LCU) is a critical area for exploration in current large language models (LLMs).
1 code implementation • 21 May 2025 • Miao Yu, Liang Lin, Guibin Zhang, Xinfeng Li, Junfeng Fang, Ningyu Zhang, Kun Wang, Yang Wang
Large language models require iterative updates to address challenges such as knowledge conflicts and outdated information (e. g., incorrect, private, or illegal contents).
1 code implementation • 7 May 2025 • Qi Zhou, Yukai Shi, Xiaojun Yang, Xiaoyu Xian, Lunjia Liao, Ruimao Zhang, Liang Lin
Visible and infrared image fusion is one of the most crucial tasks in the field of image fusion, aiming to generate fused images with clear structural information and high-quality texture features for high-level vision tasks.
no code implementations • 3 May 2025 • Kaidong Zhang, Rongtao Xu, Pengzhen Ren, Junfan Lin, Hefeng Wu, Liang Lin, Xiaodan Liang
Operating robots in open-ended scenarios with diverse tasks is a crucial research and application direction in robotics.
no code implementations • 22 Apr 2025 • Kun Wang, Guibin Zhang, Zhenhong Zhou, Jiahao Wu, Miao Yu, Shiqian Zhao, Chenlong Yin, Jinhu Fu, Yibo Yan, Hanjun Luo, Liang Lin, Zhihao Xu, Haolang Lu, Xinye Cao, Xinyun Zhou, Weifei Jin, Fanci Meng, Shicheng Xu, Junyuan Mao, Yu Wang, Hao Wu, Minghe Wang, Fan Zhang, Junfeng Fang, Wenjie Qu, Yue Liu, Chengwei Liu, Yifan Zhang, Qiankun Li, Chongye Guo, Yalan Qin, Zhaoxin Fan, Kai Wang, Yi Ding, Donghai Hong, Jiaming Ji, Yingxin Lai, Zitong Yu, Xinfeng Li, Yifan Jiang, Yanhui Li, Xinyu Deng, Junlin Wu, Dongxia Wang, Yihao Huang, Yufei Guo, Jen-tse Huang, Qiufeng Wang, Xiaolong Jin, Wenxuan Wang, Dongrui Liu, Yanwei Yue, Wenke Huang, Guancheng Wan, Heng Chang, Tianlin Li, Yi Yu, Chenghao Li, Jiawei Li, Lei Bai, Jie Zhang, Qing Guo, Jingyi Wang, Tianlong Chen, Joey Tianyi Zhou, Xiaojun Jia, Weisong Sun, Cong Wu, Jing Chen, Xuming Hu, Yiming Li, Xiao Wang, Ningyu Zhang, Luu Anh Tuan, Guowen Xu, Jiaheng Zhang, Tianwei Zhang, Xingjun Ma, Jindong Gu, Liang Pang, Xiang Wang, Bo An, Jun Sun, Mohit Bansal, Shirui Pan, Lingjuan Lyu, Yuval Elovici, Bhavya Kailkhura, Yaodong Yang, Hongwei Li, Wenyuan Xu, Yizhou Sun, Wei Wang, Qing Li, Ke Tang, Yu-Gang Jiang, Felix Juefei-Xu, Hui Xiong, XiaoFeng Wang, DaCheng Tao, Philip S. Yu, Qingsong Wen, Yang Liu
Currently, existing surveys on LLM safety primarily focus on specific stages of the LLM lifecycle, e. g., deployment phase or fine-tuning phase, lacking a comprehensive understanding of the entire "lifechain" of LLMs.
1 code implementation • 15 Apr 2025 • Zeming Wei, Junyi Lin, Yang Liu, Weixing Chen, Jingzhou Luo, Guanbin Li, Liang Lin
Building upon this dataset, we introduce AffordSplatNet, a novel model specifically designed for affordance reasoning using 3DGS representations.
no code implementations • 11 Apr 2025 • Junjia Huang, Pengxiang Yan, Jiyang Liu, Jie Wu, Zhao Wang, Yitong Wang, Liang Lin, Guanbin Li
Image fusion seeks to seamlessly integrate foreground objects with background scenes, producing realistic and harmonious fused images.
no code implementations • 8 Apr 2025 • Tianshui Chen, Jianman Lin, Zhijing Yang, Chumei Qing, Yukai Shi, Liang Lin
In this work, we propose to learn content and emotion priors as guidance augmented with contrastive learning to learn decoupled content and emotion representation via an innovative Contrastive Decoupled Representation Learning (CDRL) algorithm.
no code implementations • 18 Mar 2025 • Ziyu Lin, Yunfan Wu, Yuhang Ma, Junzhou Chen, Ronghui Zhang, Jiaming Wu, Guodong Yin, Liang Lin
To address this issue, we propose YOLO-LLTS, an end-to-end real-time traffic sign detection algorithm specifically designed for low-light environments.
no code implementations • CVPR 2025 • Zijian He, Yuwei Ning, Yipeng Qin, Guangrun Wang, Sibei Yang, Liang Lin, Guanbin Li
Virtual Try-On (VTON) is a transformative technology in e-commerce and fashion design, enabling realistic digital visualization of clothing on individuals.
no code implementations • 14 Mar 2025 • Kaixuan Jiang, Yang Liu, Weixing Chen, Jingzhou Luo, Ziliang Chen, Ling Pan, Guanbin Li, Liang Lin
Embodied Question Answering (EQA) is a challenging task in embodied intelligence that requires agents to dynamically explore 3D environments, actively gather visual information, and perform multi-step reasoning to answer questions.
1 code implementation • 8 Mar 2025 • Zhongzhan Huang, Guoming Ling, Yupei Lin, Yandong Chen, Shanshan Zhong, Hefeng Wu, Liang Lin
This improvement can even surpass the performance of the best single model in the pool and many existing strong LLMs, confirming it a highly promising paradigm.
1 code implementation • CVPR 2025 • Jingzhou Luo, Yang Liu, Weixing Chen, Zhen Li, YaoWei Wang, Guanbin Li, Liang Lin
In this paper, we propose a Dual-vision Scene Perception Network (DSPNet), to comprehensively integrate multi-view and point cloud features to improve robustness in 3D QA.
1 code implementation • CVPR 2025 • Weixing Chen, Yang Liu, Binglin Chen, Jiandong Su, Yongsen Zheng, Liang Lin
Video question grounding (VideoQG) requires models to answer the questions and simultaneously infer the relevant video segments to support the answers.
1 code implementation • 24 Feb 2025 • Ziyi Tang, Zechuan Chen, Jiarui Yang, Jiayao Mai, Yongsen Zheng, Keze Wang, Jinrui Chen, Liang Lin
Alpha mining, a critical component in quantitative investment, focuses on discovering predictive signals for future asset returns in increasingly complex financial markets.
no code implementations • 20 Feb 2025 • Yukai Shi, Cidan Shi, Zhipeng Weng, Yin Tian, Xiaoyu Xian, Liang Lin
Unlike existing research, our focus is on the challenges posed by OOD data in real-world applications and on enhancing the robustness and generalization of models.
no code implementations • 12 Feb 2025 • Junpeng Zhang, Lei Cheng, Qing Li, Liang Lin, Quanshi Zhang
In this paper, we find that the complexity of interactions encoded by a deep neural network (DNN) can explain its generalization power.
no code implementations • 10 Feb 2025 • Haoran He, Yang Zhang, Liang Lin, Zhongwen Xu, Ling Pan
Video generative models pre-trained on large-scale internet datasets have achieved remarkable success, excelling at producing realistic synthetic videos.
no code implementations • 6 Feb 2025 • Ziyi Dong, Yao Xiao, Pengxu Wei, Liang Lin
Groundbreaking advancements in text-to-image generation have recently been achieved with the emergence of diffusion models.
no code implementations • 25 Jan 2025 • Zhongzhan Huang, Shanshan Zhong, Pan Zhou, ShangHua Gao, Marinka Zitnik, Liang Lin
This game aligns well with the input-output structure of modern multimodal LLMs and benefits from a rich repository of high-quality, human-annotated creative responses, making it an ideal platform for studying LLM creativity.
1 code implementation • 20 Jan 2025 • Wentao Wan, Zhuojie Yang, Yongcan Chen, Chenglin Luo, Ruilin Wang, Kehao Cai, Nan Kang, Liang Lin, Keze Wang
Finally, it guides LLMs to use the previously generated major and minor premises to perform syllogistic deductive reasoning to derive the answer to the original question.
1 code implementation • CVPR 2025 • Rong Qin, Xingyu Liu, Jinglei Shi, Liang Lin, Jufeng Yang
Over the last decade, significant efforts have been dedicated to designing efficient models for the challenge of ultra-high resolution (UHR) semantic segmentation.
1 code implementation • CVPR 2025 • Weicheng Wang, Guoli Jia, Zhongqi Zhang, Liang Lin, Jufeng Yang
The effect of the former is estimated through intrinsic image decomposition, and the region of the latter is predicted in an additional background effect control branch.
1 code implementation • CVPR 2025 • Rong Qin, Xin Liu, Xingyu Liu, Jiaxuan Liu, Jinglei Shi, Liang Lin, Jufeng Yang
Over the last decade, many notable methods have emerged to tackle the computational resource challenge of the high resolution image recognition (HRIR).
no code implementations • CVPR 2025 • Ziliang Chen, Xin Huang, Xiaoxuan Fan, Keze Wang, Yuyu Zhou, Quanlong Guan, Liang Lin
We propose LAION-Beyond benchmark to isolate the evaluation of OOP concepts from pre-training knowledge, with regards to OpenCLIP and its reproducible variants derived from LAION datasets.
no code implementations • CVPR 2025 • Xinshuai Song, Weixing Chen, Yang Liu, Vincent Chan, Guanbin Li, Liang Lin
Existing Vision-Language Navigation (VLN) methods primarily focus on single-stage navigation, limiting their effectiveness in multi-stage and long-horizon tasks within complex and dynamic environments.
no code implementations • 9 Dec 2024 • Haijing Liu, Tao Pu, Hefeng Wu, Keze Wang, Liang Lin
The proposed framework consists of two complementary modules, i. e., intra-category semantic refinement (ISR) module and inter-category semantic transfer (IST) module.
no code implementations • CVPR 2025 • Jingyu Zhuang, Di Kang, Linchao Bao, Liang Lin, Guanbin Li
Text-driven avatar generation has gained significant attention owing to its convenience.
no code implementations • 15 Nov 2024 • Hossein Hassani, Roozbeh Razavi-Far, Mehrdad Saif, Liang Lin
Our findings denote that a majority of recent research works have dealt with the aforementioned challenges by utilizing human-in-the-loop and sim-to-real strategies for the efficient transfer of knowledge from source domains to the target domain under the transfer learning scheme.
no code implementations • 25 Oct 2024 • Zhenming Yu, Liming Cheng, Hongyu Huang, Wei zhang, Liang Lin, Kun Xu
Herein, we propose a novel framework that integrates communication and computational imaging (ICCI) to break through the inherent isolation between communication and computational imaging for remote perception.
no code implementations • 10 Aug 2024 • Weizhi Zhong, Junfan Lin, Peixin Chen, Liang Lin, Guanbin Li
Some previous methods focus on learning a direct mapping from audio to visual content.
no code implementations • 10 Aug 2024 • Weizhi Zhong, Jichang Li, Yinqi Cai, Ming Li, Feng Gao, Liang Lin, Guanbin Li
Specifically, we first develop an advanced Transformer-based model adept at predicting lip motion corresponding to the input audio, augmented by the style information aggregated through cross-attention layers from style reference video.
no code implementations • 8 Aug 2024 • Hefeng Wu, Hao Jiang, Keze Wang, Ziyi Tang, Xianghuan He, Liang Lin
The pursuit of greater interpretability in neural networks often results in a degradation of their original performance.
1 code implementation • 8 Aug 2024 • Junbin Xiao, Nanxin Huang, Hangyu Qin, Dongyang Li, Yicong Li, Fengbin Zhu, Zhulin Tao, Jianxing Yu, Liang Lin, Tat-Seng Chua, Angela Yao
Video Large Language Models (Video-LLMs) are flourishing and has advanced many video-language tasks.
1 code implementation • 31 Jul 2024 • Kuo Wang, Lechao Cheng, Weikai Chen, Pingping Zhang, Liang Lin, Fan Zhou, Guanbin Li
Learning from pseudo-labels that generated with VLMs~(Vision Language Models) has been shown as a promising solution to assist open vocabulary detection (OVD) in recent studies.
no code implementations • 29 Jul 2024 • Cong Liu, Xiaojun Quan, Yan Pan, Liang Lin, Weigang Wu, Xu Chen
We focus on the problem of fusing two or more heterogeneous large language models (LLMs) to facilitate their complementary strengths.
1 code implementation • 20 Jul 2024 • Yukai Shi, Zhipeng Weng, Yupei Lin, Cidan Shi, Xiaojun Yang, Liang Lin
Ignoring the domain gap between different data, former de-hazing methods simply adopt multiple datasets for explicit large-scale training, which often makes the methods themselves be violated.
1 code implementation • 15 Jul 2024 • Zijian He, Peixin Chen, Guangrun Wang, Guanbin Li, Philip H. S. Torr, Liang Lin
Video virtual try-on aims to generate realistic sequences that maintain garment identity and adapt to a person's pose and body shape in source videos.
no code implementations • 10 Jul 2024 • Ming-Liang Zhang, Zhong-Zhi Li, Fei Yin, Liang Lin, Cheng-Lin Liu
In modal fusion, we leverage textual clauses to express fine-grained structural and semantic content of geometry diagram, and fuse diagram with textual problem efficiently through structural-semantic pre-training.
1 code implementation • 9 Jul 2024 • Tianshui Chen, Weihang Wang, Tao Pu, Jinghui Qin, Zhijing Yang, Jie Liu, Liang Lin
To overcome these limitations, we propose the Dynamic Correlation Learning and Regularization (DCLR) algorithm, which leverages multi-grained semantic correlations to better model semantic confusion for adaptive regularization.
1 code implementation • 9 Jul 2024 • Yang Liu, Weixing Chen, Yongjie Bai, Xiaodan Liang, Guanbin Li, Wen Gao, Liang Lin
In this survey, we give a comprehensive exploration of the latest advancements in Embodied AI.
1 code implementation • 5 Jun 2024 • Gexin Huang, Chenfei Wu, Mingjie Li, Xiaojun Chang, Ling Chen, Ying Sun, Shen Zhao, Xiaodan Liang, Liang Lin
(b) A knowledge association module that fuses linguistic and biomedical knowledge into gene priors by transformer-based graph representation learning, capturing the intrinsic relationships between different genes' mutations.
1 code implementation • 2 Jun 2024 • Yukai Shi, Yupei Lin, Pengxu Wei, Xiaoyu Xian, Tianshui Chen, Liang Lin
Large-scale trained diffusion models have a strong generative prior that enables real-world modeling of images to generate diverse and realistic images.
no code implementations • CVPR 2024 • Jiaming Li, Jiacheng Zhang, Jichang Li, Ge Li, Si Liu, Liang Lin, Guanbin Li
Specifically, we devise three modules: Background Category-specific Prompt, Background Object Discovery, and Inference Probability Rectification, to empower the detector to discover, represent, and leverage implicit object knowledge explored from background proposals.
no code implementations • 20 May 2024 • Siyu Lou, Yuntian Chen, Xiaodan Liang, Liang Lin, Quanshi Zhang
In this study, we propose an axiomatic system to define and quantify the precise memorization and in-context reasoning effects used by the large language model (LLM) for language generation.
no code implementations • 16 May 2024 • Junpeng Zhang, Qing Li, Liang Lin, Quanshi Zhang
This paper investigates the dynamics of a deep neural network (DNN) learning interactions.
1 code implementation • 24 Apr 2024 • Yang Liu, Binglin Chen, Yongsen Zheng, Lechao Cheng, Guanbin Li, Liang Lin
Metro Origin-Destination (OD) prediction is a crucial yet challenging spatial-temporal prediction task in urban computing, which aims to accurately forecast cross-station ridership for optimizing metro scheduling and enhancing overall transport efficiency.
no code implementations • 23 Apr 2024 • Weifeng Chen, Jiacheng Zhang, Jie Wu, Hefeng Wu, Xuefeng Xiao, Liang Lin
The rapid development of diffusion models has triggered diverse applications.
no code implementations • 22 Apr 2024 • Yiming Liu, Kezhao Liu, Yao Xiao, Ziyi Dong, Xiaogang Xu, Pengxu Wei, Liang Lin
To further enhance the robustness of DBP models, we introduce Adversarial Denoising Diffusion Training (ADDT), which incorporates classifier-guided adversarial perturbations into diffusion training, thereby strengthening the DBP models' ability to purify adversarial perturbations.
no code implementations • 7 Apr 2024 • Yuanfeng Xu, Yuhao Chen, Zhongzhan Huang, Zijian He, Guangrun Wang, Philip Torr, Liang Lin
In this paper, we present AnimateZoo, a zero-shot diffusion-based video generator to address this challenging cross-species animation issue, aiming to accurately produce animal animations while preserving the background.
1 code implementation • 18 Mar 2024 • Meilin Wang, Yexing Song, Pengxu Wei, Xiaoyu Xian, Yukai Shi, Liang Lin
IDF-CR consists of a pixel space cloud removal module (Pixel-CR) and a latent space iterative noise diffusion network (IND).
no code implementations • 9 Mar 2024 • Bingqian Lin, Yanxin Long, Yi Zhu, Fengda Zhu, Xiaodan Liang, Qixiang Ye, Liang Lin
For encouraging the agent to well capture the difference brought by perturbation, a perturbation-aware contrastive learning mechanism is further developed by contrasting perturbation-free trajectory encodings and perturbation-based counterparts.
1 code implementation • 8 Mar 2024 • Yahao Lu, Yupei Lin, Han Wu, Xiaoyu Xian, Yukai Shi, Liang Lin
The quality, quantity, and diversity of the infrared dataset are critical to the detection of small targets.
1 code implementation • 2 Mar 2024 • Guangrun Wang, Changlin Li, Liuchun Yuan, Jiefeng Peng, Xiaoyu Xian, Xiaodan Liang, Xiaojun Chang, Liang Lin
Addressing this problem, we modularize a large search space into blocks with small search spaces and develop a family of models with the distilling neural architecture (DNA) techniques.
1 code implementation • 28 Feb 2024 • Cidan Shi, Lihuang Fang, Han Wu, Xiaoyu Xian, Yukai Shi, Liang Lin
Specifically, we introduce cooperative learning between visible and infrared images captured by different sensors.
1 code implementation • CVPR 2024 • Tao Tang, Guangrun Wang, Yixing Lao, Peng Chen, Jie Liu, Liang Lin, Kaicheng Yu, Xiaodan Liang
Through extensive experiments across various datasets and scenes, we demonstrate the effectiveness of our approach in facilitating better interaction between LiDAR and camera modalities within a unified neural field.
1 code implementation • 17 Feb 2024 • Shanshan Zhong, Zhongzhan Huang, Daifeng Li, Wushao Wen, Jinghui Qin, Liang Lin
This strategy can implicitly enhance the model's robustness during the optimization process, mitigating instability risks arising from multimodal information inputs.
1 code implementation • 1 Feb 2024 • Yang Liu, Xinshuai Song, Kaixuan Jiang, Weixing Chen, Jingzhou Luo, Guanbin Li, Liang Lin
To overcome this limitation, we introduce the Multimodal Embodied Interactive Agent (MEIA), capable of translating high-level tasks expressed in natural language into a sequence of executable actions.
no code implementations • 26 Jan 2024 • Jingyu Zhuang, Di Kang, Yan-Pei Cao, Guanbin Li, Liang Lin, Ying Shan
To this end, we propose a 3D scene editing framework, TIPEditor, that accepts both text and image prompts and a 3D bounding box to specify the editing region.
1 code implementation • 20 Jan 2024 • Yuefang Gao, Yuhao Xie, Zeke Zexi Hu, Tianshui Chen, Liang Lin
Specifically, the framework consists of separate global-local adversarial learning modules that learn domain-invariant global and local features independently.
Cross-Domain Facial Expression Recognition
Model Optimization
+2
no code implementations • 13 Jan 2024 • Hefeng Wu, Guangzhi Ye, Ziyang Zhou, Ling Tian, Qing Wang, Liang Lin
Specifically, an instance-view data hallucination module hallucinates each sample of a novel class to generate new data by employing local semantic correlated attention and global semantic feature fusion derived from base classes.
no code implementations • 6 Jan 2024 • Yupei Lin, Xiaoyu Xian, Yukai Shi, Liang Lin
By using a target text prompt for domain adaption, the diffusion model is able to implement zero-shot image-to-image translation advantageously.
1 code implementation • CVPR 2024 • Tianshui Chen, Jianman Lin, Zhijing Yang, Chunmei Qing, Liang Lin
To capitalize on this insight we propose a novel adaptive spatial coherent correlation learning (ASCCL) algorithm which models the aforementioned correlation as an explicit metric and integrates the metric to supervise manipulating facial expression and meanwhile better preserving the facial animation of spoken contents.
no code implementations • 1 Jan 2024 • Jingyu Zhuang, Kuo Wang, Liang Lin, Guanbin Li
Credible Teacher adopts an interactive teaching mechanism using flexible labels to prevent uncertain pseudo labels from misleading the model and gradually reduces its uncertainty through the guidance of other credible pseudo labels.
no code implementations • 15 Dec 2023 • Ziliang Chen, Yongsen Zheng, Zhao-Rong Lai, Quanlong Guan, Liang Lin
Invariant representation learning (IRL) encourages the prediction from invariant causal features to labels de-confounded from the environments, advancing the technical roadmap of out-of-distribution (OOD) generalization.
1 code implementation • CVPR 2024 • Shanshan Zhong, Zhongzhan Huang, ShangHua Gao, Wushao Wen, Liang Lin, Marinka Zitnik, Pan Zhou
To this end, we study LLMs on the popular Oogiri game which needs participants to have good creativity and strong associative thinking for responding unexpectedly and humorously to the given image, text, or both, and thus is suitable for LoT study.
no code implementations • 29 Nov 2023 • Zeqing Wang, Wentao Wan, Qiqing Lao, Runmeng Chen, Minjie Lang, Keze Wang, Liang Lin
Attempt to overcome this limitation and inspired by the human top-down reasoning process, i. e., systematically exploring relevant issues to derive a comprehensive answer, this work introduces a novel, explainable multi-agent collaboration framework by leveraging the expansive knowledge of Large Language Models (LLMs) to enhance the capabilities of VLMs themselves.
1 code implementation • 16 Nov 2023 • Hefeng Wu, Yandong Chen, Lingbo Liu, Tianshui Chen, Keze Wang, Liang Lin
In the localization stage, the Scale-aware Multi-head Localization (SAML) module utilizes the query tensor to predict the confidence, location, and size of each potential object.
1 code implementation • 15 Nov 2023 • Hefeng Wu, Weifeng Chen, Zhibin Liu, Tianshui Chen, Zhiguang Chen, Liang Lin
Moreover, we propose a proximity data generation (PDG) module to automatically produce more diverse data for cross-modal training.
2 code implementations • NeurIPS 2023 • Zhongzhan Huang, Pan Zhou, Shuicheng Yan, Liang Lin
Besides, we also observe the theoretical benefits of the LSC coefficient scaling of UNet in the stableness of hidden features and gradient and also robustness.
1 code implementation • 11 Oct 2023 • Jinghui Qin, Lihuang Fang, Ruitao Lu, Liang Lin, Yukai Shi
Deep learning-based hyperspectral image (HSI) super-resolution, which aims to generate high spatial resolution HSI (HR-HSI) by fusing hyperspectral image (HSI) and multispectral image (MSI) with deep neural networks (DNNs), has attracted lots of attention.
1 code implementation • 23 Sep 2023 • Tao Pu, Tianshui Chen, Hefeng Wu, Yongyi Lu, Liang Lin
In this work, we propose a spatial-temporal knowledge-embedded transformer (STKET) that incorporates the prior spatial-temporal knowledge into the multi-head cross-attention mechanism to learn more representative relationship representations.
no code implementations • 18 Sep 2023 • Wentao Wan, Nan Kang, Zeqing Wang, Zhuojie Yang, Liang Lin, Keze Wang
Specifically, our CLVP distills the capabilities of well-trained task-specific models into the visual sub-modules in a stepwise and anti-forgetting manner.
1 code implementation • ICCV 2023 • Pengxu Wei, Yujing Sun, Xingbei Guo, Chang Liu, Jie Chen, Xiangyang Ji, Liang Lin
Despite substantial advances, single-image super-resolution (SISR) is always in a dilemma to reconstruct high-quality images with limited information from one input image, especially in realistic scenarios.
2 code implementations • 23 Aug 2023 • Ziyi Tang, Ruilin Wang, Weixing Chen, Yongsen Zheng, Zechuan Chen, Yang Liu, Keze Wang, Tianshui Chen, Liang Lin
Drawing inspiration from the orchestration of diverse specialized agents collaborating to tackle intricate tasks, we propose a framework named Causal-Consistency Chain-of-Thought (CaCo-CoT) that harnesses multi-agent collaboration to bolster the faithfulness and causality of foundation models, involving a set of reasoners and evaluators.
no code implementations • 23 Aug 2023 • Junyi Chen, Longteng Guo, Jia Sun, Shuai Shao, Zehuan Yuan, Liang Lin, Dongyu Zhang
Owing to the combination of the unified architecture and pre-training task, EVE is easy to scale up, enabling better downstream performance with fewer resources and faster training speed.
no code implementations • ICCV 2023 • Xujie Zhang, BinBin Yang, Michael C. Kampffmeyer, Wenqing Zhang, Shiyue Zhang, Guansong Lu, Liang Lin, Hang Xu, Xiaodan Liang
Cross-modal garment synthesis and manipulation will significantly benefit the way fashion designers generate garments and modify their designs via flexible linguistic interfaces. Current approaches follow the general text-to-image paradigm and mine cross-modal relations via simple cross-attention modules, neglecting the structural correspondence between visual and textual representations in the fashion design domain.
no code implementations • ICCV 2023 • Haoyuan Li, Haoye Dong, Hanchao Jia, Dong Huang, Michael C. Kampffmeyer, Liang Lin, Xiaodan Liang
Multi-person 3D mesh recovery from videos is a critical first step towards automatic perception of group behavior in virtual reality, physical therapy and beyond.
no code implementations • ICCV 2023 • Zhongzhan Huang, Mingfu Liang, Jinghui Qin, Shanshan Zhong, Liang Lin
The self-attention mechanism (SAM) is widely used in various fields of artificial intelligence and has successfully boosted the performance of different models.
no code implementations • ICCV 2023 • BinBin Yang, Yi Luo, Ziliang Chen, Guangrun Wang, Xiaodan Liang, Liang Lin
Thanks to the rapid development of diffusion models, unprecedented progress has been witnessed in image synthesis.
1 code implementation • ICCV 2023 • Hong Yan, Yang Liu, Yushen Wei, Zhen Li, Guanbin Li, Liang Lin
Moreover, these methods ignore how to utilize the fine-grained dependencies among different skeleton joints to pre-train an efficient skeleton sequence learning model that can generalize well across different datasets.
2 code implementations • 30 Jun 2023 • Yang Liu, Weixing Chen, Guanbin Li, Liang Lin
We present CausalVLR (Causal Visual-Linguistic Reasoning), an open-source toolbox containing a rich set of state-of-the-art causal relation discovery and causal inference methods for various visual-linguistic reasoning tasks, such as VQA, image/video captioning, medical report generation, model generalization and robustness, etc.
no code implementations • 30 Jun 2023 • Ganlong Zhao, Guanbin Li, Yipeng Qin, Jinjin Zhang, Zhenhua Chai, Xiaolin Wei, Liang Lin, Yizhou Yu
In this paper, we address a complex but practical scenario in semi-supervised learning (SSL) named open-set SSL, where unlabeled data contain both in-distribution (ID) and out-of-distribution (OOD) samples.
1 code implementation • 23 Jun 2023 • Jingyu Zhuang, Chen Wang, Lingjie Liu, Liang Lin, Guanbin Li
Neural fields have achieved impressive advancements in view synthesis and scene reconstruction.
1 code implementation • 13 Jun 2023 • Junfan Lin, Yuying Zhu, Lingbo Liu, Yang Liu, Guanbin Li, Liang Lin
1) The travel time of a vehicle is delayed feedback on the effectiveness of TSC policy at each traffic intersection since it is obtained after the vehicle has left the road network.
no code implementations • 30 May 2023 • Yang Zhang, Lingbo Liu, Xinyu Xiong, Guanbin Li, Guoli Wang, Liang Lin
In this work, we propose a novel end-to-end wind power forecasting model named Hierarchical Spatial-Temporal Transformer Network (HSTTN) to address the long-term WPF problems.
1 code implementation • 23 May 2023 • Weifeng Chen, Yatai Ji, Jie Wu, Hefeng Wu, Pan Xie, Jiashi Li, Xin Xia, Xuefeng Xiao, Liang Lin
Recent advances in text-to-image (T2I) diffusion models have enabled impressive image generation capabilities guided by text prompts.
1 code implementation • CVPR 2023 • Weizhi Zhong, Chaowei Fang, Yinqi Cai, Pengxu Wei, Gangming Zhao, Liang Lin, Guanbin Li
Prior landmark characteristics of the speaker's face are employed to make the generated landmarks coincide with the facial outline of the speaker.
1 code implementation • 9 May 2023 • Shanshan Zhong, Zhongzhan Huang, Wushao Wen, Jinghui Qin, Liang Lin
Our approach can make text-to-image diffusion models easier to use with better user experience, which demonstrates our approach has the potential for further advancing the development of user-friendly text-to-image generation models by bridging the semantic gap between simple narrative prompts and complex keyword-based prompts.
2 code implementations • 7 May 2023 • Yushen Wei, Yang Liu, Hong Yan, Guanbin Li, Liang Lin
Our VCSR involves two essential modules: i) the Question-Guided Refiner (QGR) module, which refines consecutive video frames guided by the question semantics to obtain more representative segment features for causal front-door intervention; ii) the Causal Scene Separator (CSS) module, which discovers a collection of visual causal and non-causal scenes based on the visual-linguistic causal relevance and estimates the causal effect of the scene-separating intervention in a contrastive learning manner.
no code implementations • 6 May 2023 • Yang Wu, Zhibin Liu, Hefeng Wu, Liang Lin
In this paper, we study video synthesis with emphasis on simplifying the generation conditions.
no code implementations • 13 Apr 2023 • Shanshan Zhong, Zhongzhan Huang, Wushao Wen, Jinghui Qin, Liang Lin
This technique enables the mitigation of the extra costs for performance improvement during training, such as parameter size and inference time, through these transformations during inference, and therefore SRP has great potential for industrial and practical applications.
no code implementations • 20 Mar 2023 • Junyang Chen, Xiaoyu Xian, Zhijing Yang, Tianshui Chen, Yongyi Lu, Yukai Shi, Jinshan Pan, Liang Lin
In open-world conditions, the pose transfer task raises various independent signals: OOD appearance and skeleton, which need to be extracted and distributed in speciality.
no code implementations • 17 Mar 2023 • Kuo Wang, Lingbo Liu, Yang Liu, Guanbin Li, Fan Zhou, Liang Lin
The prediction of traffic flow is a challenging yet crucial problem in spatial-temporal analysis, which has recently gained increasing interest.
2 code implementations • 16 Mar 2023 • Weixing Chen, Yang Liu, Ce Wang, Jiarui Zhu, Shen Zhao, Guanbin Li, Cheng-Lin Liu, Liang Lin
Medical report generation (MRG) is essential for computer-aided diagnosis and medication guidance, which can relieve the heavy burden of radiologists by automatically generating the corresponding medical reports according to the given radiology image.
1 code implementation • CVPR 2023 • Yao Xiao, Ziyi Tang, Pengxu Wei, Cong Liu, Liang Lin
In this paper, based on causal analysis of the aforementioned problems, we propose a novel fine-tuning method, which uses masked images as counterfactual samples that help improve the robustness of the fine-tuning model.
no code implementations • 13 Feb 2023 • Bingqian Lin, Yi Zhu, Xiaodan Liang, Liang Lin, Jianzhuang Liu
Vision-Language Navigation (VLN) is a challenging task which requires an agent to align complex visual observations to language instructions to reach the goal position.
1 code implementation • 5 Feb 2023 • Zhongzhan Huang, Mingfu Liang, Shanshan Zhong, Liang Lin
We propose the attention-inspired numerical solver (AttNS), a concise method that helps the generalization and robustness issues faced by the AI-Hybrid numerical solver in solving differential equations due to limited data.
2 code implementations • 3 Jan 2023 • Zhijing Yang, Junyang Chen, Yukai Shi, Hao Li, Tianshui Chen, Liang Lin
Image Virtual try-on aims at replacing the cloth on a personal image with a garment image (in-shop clothes), which has attracted increasing attention from the multimedia and computer vision communities.
no code implementations • 2 Jan 2023 • Ziyi Tang, Ruimao Zhang, Zhanglin Peng, Jinrui Chen, Liang Lin
We further introduce the Attribute-Aware and Identity-Aware Proxy embedding modules (AAP and IAP) to extract the informative and discriminative feature representations at different stages.
no code implementations • ICCV 2023 • Jie Ma, Chuan Wang, Yang Liu, Liang Lin, Guanbin Li
As a mainstream framework in the field of semi-supervised learning (SSL), self-training via pseudo labeling and its variants have witnessed impressive progress in semi-supervised semantic segmentation with the recent advance of deep neural networks.
no code implementations • ICCV 2023 • Ziliang Chen, Xin Huang, Quanlong Guan, Liang Lin, Weiqi Luo
The vision community is undergoing the unprecedented progress with the emergence of Vision-Language Pretraining Models (VLMs).
no code implementations • ICCV 2023 • Ziyi Zhang, Weikai Chen, Chaowei Fang, Zhen Li, Lechao Chen, Liang Lin, Guanbin Li
Confidence-wise, we propose a novel sample selection strategy based on confidence representation voting instead of the widely-used small-loss criterion.
2 code implementations • 6 Dec 2022 • Jiaqi Chen, Tong Li, Jinghui Qin, Pan Lu, Liang Lin, Chongyu Chen, Xiaodan Liang
Naturally, we also present a unified multi-task Geometric Transformer framework, Geoformer, to tackle calculation and proving problems simultaneously in the form of sequence generation, which finally shows the reasoning ability can be improved on both two tasks by unifying formulation.
Ranked #5 on
Mathematical Reasoning
on PGPS9K
no code implementations • 21 Nov 2022 • Ziyi Dong, Pengxu Wei, Liang Lin
To tackle this problem, we propose a simple yet effective framework, namely DreamArtist, which adopts a novel positive-negative prompt-tuning learning strategy on the pre-trained diffusion model, and it has shown to well handle the trade-off between the accurate controllability and fidelity of image generation with only one reference example.
no code implementations • 15 Nov 2022 • Tao Pu, Qianru Lao, Hefeng Wu, Tianshui Chen, Liang Lin
To reject noisy labels, recent works regard large loss samples as noise but ignore the semantic correlation different multi-label images.
no code implementations • 12 Nov 2022 • Xipeng Chen, Guangrun Wang, Dizhong Zhu, Xiaodan Liang, Philip H. S. Torr, Liang Lin
In this paper, we propose a novel Neural Sewing Machine (NSM), a learning-based framework for structure-preserving 3D garment modeling, which is capable of learning representations for garments with diverse shapes and topologies and is successfully applied to 3D garment reconstruction and controllable manipulation.
2 code implementations • 12 Nov 2022 • Ziyi Zhang, Weikai Chen, Hui Cheng, Zhen Li, Siyuan Li, Liang Lin, Guanbin Li
We investigate a practical domain adaptation task, called source-free domain adaptation (SFUDA), where the source-pretrained model is adapted to the target domain without access to the source data.
Ranked #6 on
Source-Free Domain Adaptation
on VisDA-2017
1 code implementation • CVPR 2023 • Junfan Lin, Jianlong Chang, Lingbo Liu, Guanbin Li, Liang Lin, Qi Tian, Chang Wen Chen
During inference, instead of changing the motion generator, our method reformulates the input text into a masked motion as the prompt for the motion generator to ``reconstruct'' the motion.
no code implementations • 27 Oct 2022 • Zhongzhan Huang, Senwei Liang, Mingfu Liang, Liang Lin
The self-attention mechanism has emerged as a critical component for improving the performance of various backbone neural networks.
no code implementations • 22 Aug 2022 • Lingbo Liu, Jianlong Chang, Bruce X. B. Yu, Liang Lin, Qi Tian, Chang-Wen Chen
Previous methods usually fine-tuned the entire networks for each specific dataset, which will be burdensome to store massive parameters of these networks.
1 code implementation • 7 Aug 2022 • Zhongzhan Huang, Senwei Liang, Hong Zhang, Haizhao Yang, Liang Lin
The large-scale simulation of dynamical systems is critical in numerous scientific and engineering disciplines.
1 code implementation • 31 Jul 2022 • Jiutao Yue, Haofeng Li, Pengxu Wei, Guanbin Li, Liang Lin
Since the frequency masking may not only destroys the adversarial perturbations but also affects the sharp details in a clean image, we further develop an adversarial sample classifier based on the frequency domain of images to determine if applying the proposed mask module.
2 code implementations • 26 Jul 2022 • Yang Liu, Guanbin Li, Liang Lin
Existing visual question answering methods often suffer from cross-modal spurious correlations and oversimplified event-level reasoning processes that fail to capture event temporality, causality, and dynamics spanning over the video.
no code implementations • 16 Jul 2022 • Zhongzhan Huang, Senwei Liang, Mingfu Liang, wei he, Haizhao Yang, Liang Lin
Recently many plug-and-play self-attention modules (SAMs) are proposed to enhance the model generalization by exploiting the internal information of deep convolutional neural networks (CNNs).
1 code implementation • 13 Jul 2022 • Ziyi Dong, Pengxu Wei, Liang Lin
In this work, we empirically explore the model training for adversarial robustness in object detection, which greatly attributes to the conflict between learning clean images and adversarial images.
no code implementations • 4 Jul 2022 • Yinya Huang, Lemao Liu, Kun Xu, Meng Fang, Liang Lin, Xiaodan Liang
In this work, we propose logic structural-constraint modeling to solve the logical reasoning QA and introduce discourse-aware graph networks (DAGNs).
1 code implementation • 6 Jun 2022 • Hao Li, Jinghui Qin, Zhijing Yang, Pengxu Wei, Jinshan Pan, Liang Lin, Yukai Shi
Real-world image super-resolution is a practical image restoration problem that aims to obtain high-quality images from in-the-wild input, has recently received considerable attention with regard to its tremendous application potentials.
1 code implementation • 26 May 2022 • Tao Pu, Tianshui Chen, Hefeng Wu, Yukai Shi, Zhijing Yang, Liang Lin
Specifically, an instance-perspective representation blending (IPRB) module is designed to blend the representations of the known labels in an image with the representations of the corresponding unknown labels in another image to complement these unknown labels.
1 code implementation • 23 May 2022 • Tianshui Chen, Tao Pu, Lingbo Liu, Yukai Shi, Zhijing Yang, Liang Lin
Multi-label image recognition with partial labels (MLR-PL), in which some labels are known while others are unknown for each image, may greatly reduce the cost of annotation and thus facilitate large-scale MLR.
Multi-Label Image Recognition
Multi-label Image Recognition with Partial Labels
2 code implementations • 17 May 2022 • Zhicheng Yang, Jinghui Qin, Jiaqi Chen, Liang Lin, Xiaodan Liang
To address this issue and make a step towards interpretable MWP solving, we first construct a high-quality MWP dataset named InterMWP which consists of 11, 495 MWPs and annotates interpretable logical formulas based on algebraic knowledge as the grounded linguistic logic of each solution equation.
1 code implementation • CVPR 2022 • Xiaoqian Xu, Pengxu Wei, Weikai Chen, Mingzhi Mao, Liang Lin, Guanbin Li
To address this issue, we propose an unsupervised domain adaptation mechanism for real-world SR, named Dual ADversarial Adaptation (DADA), which only requires LR images in the target domain with available real paired data from a source camera.
1 code implementation • CVPR 2022 • BinBin Yang, Xinchi Deng, Han Shi, Changlin Li, Gengwei Zhang, Hang Xu, Shen Zhao, Liang Lin, Xiaodan Liang
To make ROSETTA automatically determine which experience is available and useful, a prototypical task correlation guided Gating Diversity Controller(GDC) is introduced to adaptively adjust the diversity of gates for the new task based on class-specific prototypes.
no code implementations • 26 Apr 2022 • Yang Liu, Yushen Wei, Hong Yan, Guanbin Li, Liang Lin
Visual representation learning is ubiquitous in various real-world applications, including visual comprehension, video understanding, multi-modal analysis, human-computer interaction, and urban computing.
no code implementations • 8 Apr 2022 • Tao Pu, Mingzhan Sun, Hefeng Wu, Tianshui Chen, Ling Tian, Liang Lin
We also design an object erasing (OE) module to implicitly learn semantic dependency among categories by erasing semantic-aware regions to regularize the network training.
no code implementations • 7 Mar 2022 • Jingyu Zhuang, Ziliang Chen, Pengxu Wei, Guanbin Li, Liang Lin
In Open Set Domain Adaptation (OSDA), large amounts of target samples are drawn from the implicit categories that never appear in the source domain.
1 code implementation • 4 Mar 2022 • Tao Pu, Tianshui Chen, Hefeng Wu, Liang Lin
However, these algorithms depend on sufficient multi-label annotations to train the models, leading to poor performance especially with low known label proportion.
Multi-Label Image Recognition
Multi-label Image Recognition with Partial Labels
1 code implementation • 26 Feb 2022 • Pengxiang Yan, Ziyi Wu, Mengmeng Liu, Kun Zeng, Liang Lin, Guanbin Li
To relieve the burden of labor-intensive labeling, deep unsupervised SOD methods have been proposed to exploit noisy labels generated by handcrafted saliency methods.
1 code implementation • CVPR 2022 • Guangrun Wang, Yansong Tang, Liang Lin, Philip H.S. Torr
Inspired by perceptual learning that could use cross-view learning to perceive concepts and semantics, we propose a novel AE that could learn semantic-aware representation via cross-view image reconstruction.
1 code implementation • 21 Dec 2021 • Tianshui Chen, Tao Pu, Hefeng Wu, Yuan Xie, Liang Lin
To reduce the annotation cost, we propose a structured semantic transfer (SST) framework that enables training multi-label recognition models with partial labels, i. e., merely some labels are known while other labels are missing (also called unknown labels) per image.
Multi-Label Image Recognition
Multi-label Image Recognition with Partial Labels
2 code implementations • 7 Dec 2021 • Yang Liu, Keze Wang, Lingbo Liu, Haoyuan Lan, Liang Lin
To overcome these limitations, we take advantage of the multi-scale temporal dependencies within videos and proposes a novel video self-supervised learning framework named Temporal Contrastive Graph Learning (TCGL), which jointly models the inter-snippet and intra-snippet temporal dependencies for temporal representation learning with a hybrid graph contrastive learning strategy.
no code implementations • 30 Nov 2021 • Lingbo Liu, Zewei Yang, Guanbin Li, Kuo Wang, Tianshui Chen, Liang Lin
Land remote sensing analysis is a crucial research in earth science.
Ranked #2 on
Semantic Segmentation
on BJRoad
no code implementations • 8 Nov 2021 • Junying Huang, Fan Chen, Keze Wang, Liang Lin, Dongyu Zhang
Aiming at recognizing the samples from novel categories with few reference samples, few-shot learning (FSL) is a challenging problem.
no code implementations • 27 Oct 2021 • Bowen Wu, Zhenyu Xie, Xiaodan Liang, Yubei Xiao, Haoye Dong, Liang Lin
The integration of human parsing and appearance flow effectively guides the generation of video frames with realistic appearance.
no code implementations • 16 Oct 2021 • Yang Wu, Shirui Feng, Guanbin Li, Liang Lin
PEMR includes a "looking ahead" process, \textit{i. e.} a visual feature extractor module that estimates feasible paths for gathering 3D navigational information, which is mimicking the human sense of direction.
1 code implementation • 29 Sep 2021 • Lingbo Liu, Mengmeng Liu, Guanbin Li, Ziyi Wu, Junfan Lin, Liang Lin
Furthermore, we take the road network feature as a query to capture the long-range spatial distribution of traffic flow with a transformer architecture.
no code implementations • Findings (EMNLP) 2021 • Guolin Zheng, Yubei Xiao, Ke Gong, Pan Zhou, Xiaodan Liang, Liang Lin
Specifically, we unify a pre-trained acoustic model (wav2vec 2. 0) and a language model (BERT) into an end-to-end trainable framework.
1 code implementation • ICCV 2021 • Jiefeng Peng, Jiqi Zhang, Changlin Li, Guangrun Wang, Xiaodan Liang, Liang Lin
We attribute this ranking correlation problem to the supernet training consistency shift, including feature shift and parameter shift.
no code implementations • ICCV 2021 • Junkai Huang, Chaowei Fang, Weikai Chen, Zhenhua Chai, Xiaolin Wei, Pengxu Wei, Liang Lin, Guanbin Li
Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data.
no code implementations • 9 Aug 2021 • Jie Wu, Wei zhang, Guanbin Li, Wenhao Wu, Xiao Tan, YingYing Li, Errui Ding, Liang Lin
In this paper, we introduce a novel task, referred to as Weakly-Supervised Spatio-Temporal Anomaly Detection (WSSTAD) in surveillance video.
1 code implementation • 23 Jul 2021 • Bingqian Lin, Yi Zhu, Yanxin Long, Xiaodan Liang, Qixiang Ye, Liang Lin
Specifically, we propose a Dynamic Reinforced Instruction Attacker (DR-Attacker), which learns to mislead the navigator to move to the wrong target by destroying the most instructive information in instructions at different timesteps.
1 code implementation • ACL 2021 • Jinghui Qin, Xiaodan Liang, Yining Hong, Jianheng Tang, Liang Lin
Previous math word problem solvers following the encoder-decoder paradigm fail to explicitly incorporate essential math symbolic constraints, leading to unexplainable and unreasonable predictions.
1 code implementation • 2 Jul 2021 • Lingbo Liu, Yuying Zhu, Guanbin Li, Ziyi Wu, Lei Bai, Liang Lin
In this work, we proposed a novel neural network module termed Heterogeneous Information Aggregation Machine (HIAM), which fully exploits heterogeneous information of historical data (e. g., incomplete OD matrices, unfinished order vectors, and DO matrices) to jointly learn the evolutionary patterns of OD and DO ridership.
1 code implementation • 17 Jun 2021 • Shuai Lin, Pan Zhou, Zi-Yuan Hu, Shuojia Wang, Ruihui Zhao, Yefeng Zheng, Liang Lin, Eric Xing, Xiaodan Liang
However, since for a query, its negatives are uniformly sampled from all graphs, existing methods suffer from the critical sampling bias issue, i. e., the negatives likely having the same semantic structure with the query, leading to performance degradation.
1 code implementation • ACL 2021 • Zheng Ye, Liucun Lu, Lishan Huang, Liang Lin, Xiaodan Liang
To address these limitations, we propose Quantifiable Dialogue Coherence Evaluation (QuantiDCE), a novel framework aiming to train a quantifiable dialogue coherence metric that can reflect the actual human rating standards.
1 code implementation • Findings (ACL) 2021 • Jiaqi Chen, Jianheng Tang, Jinghui Qin, Xiaodan Liang, Lingbo Liu, Eric P. Xing, Liang Lin
Therefore, we propose a Geometric Question Answering dataset GeoQA, containing 4, 998 geometric problems with corresponding annotated programs, which illustrate the solving process of the given problems.
Ranked #6 on
Mathematical Reasoning
on PGPS9K
1 code implementation • ICCV 2021 • Guangrun Wang, Keze Wang, Guangcong Wang, Philip H. S. Torr, Liang Lin
In this paper, we reveal two contradictory phenomena in contrastive learning that we call under-clustering and over-clustering problems, which are major obstacles to learning efficiency.
Ranked #1 on
Self-Supervised Person Re-Identification
on SYSU-30k
no code implementations • 31 Mar 2021 • Guangrun Wang, Liang Lin, Rongcong Chen, Guangcong Wang, Jiqi Zhang
In this work, we prove that dynamically adapting network architectures tailored for each domain task along with weight finetuning benefits in both efficiency and effectiveness, compared to the existing image recognition pipeline that only tunes the weights regardless of the architecture.
no code implementations • 1 Feb 2021 • Yukai Shi, Sen Zhang, Chenxing Zhou, Xiaodan Liang, Xiaojun Yang, Liang Lin
Non-parallel text style transfer has attracted increasing research interests in recent years.
2 code implementations • 26 Jan 2021 • Liang Lin, Yiming Gao, Ke Gong, Meng Wang, Xiaodan Liang
Prior highly-tuned image parsing models are usually studied in a certain domain with a specific set of semantic labels and can hardly be adapted into other scenarios (e. g., sharing discrepant label granularity) without extensive re-training.
Ranked #1 on
Human Parsing
on 4D-DRESS
(using extra training data)
no code implementations • 9 Jan 2021 • Fuyu Wang, Xiaodan Liang, Lin Xu, Liang Lin
Beyond generating long and topic-coherent paragraphs in traditional captioning tasks, the medical image report composition task poses more task-oriented challenges by requiring both the highly-accurate medical term diagnosis and multiple heterogeneous forms of information including impression and findings.
no code implementations • 4 Jan 2021 • Yang Liu, Keze Wang, Haoyuan Lan, Liang Lin
To model multi-scale temporal dependencies, our TCGL integrates the prior knowledge about the frame and snippet orders into graph structures, i. e., the intra-/inter- snippet temporal contrastive graphs.
no code implementations • 1 Jan 2021 • Fuyu Wang, Pan Zhou, Xiaodan Liang, Liang Lin
To solve this issue, we propose a novel DynamIc Self-sUperviSed Erasure (DISUSE) which adaptively erases redundant and artifactual clues in the context and questions to learn and establish the correct corresponding pair relations between the questions and their clues.
no code implementations • 1 Jan 2021 • Junfan Lin, Lin Xu, Ziliang Chen, Liang Lin
To this end, we propose a novel DSMAD agent, INS-DS (Introspective Diagnosis System) comprising of two separate yet cooperative modules, i. e., an inquiry module for proposing symptom-inquiries and an introspective module for deciding when to inform a disease.
no code implementations • 1 Jan 2021 • Hongjun Wang, Guanbin Li, Liang Lin
To protect the security of machine learning models against adversarial examples, adversarial training becomes the most popular and powerful strategy against various adversarial attacks by injecting adversarial examples into training data.
no code implementations • ICCV 2021 • Qingxing Cao, Wentao Wan, Keze Wang, Xiaodan Liang, Liang Lin
The experimental results show that our proposed method can improve current VQA models on OOD split without losing performance on the in-domain test data.
no code implementations • 1 Jan 2021 • Junfan Lin, Changxin Huang, Xiaodan Liang, Liang Lin
The curiosity is added to the target entropy to increase the entropy temperature for unfamiliar states and decrease the target entropy for familiar states.
1 code implementation • 29 Dec 2020 • Tao Pu, Tianshui Chen, Yuan Xie, Hefeng Wu, Liang Lin
In this work, we explore the correlations among the action units and facial expressions, and devise an AU-Expression Knowledge Constrained Representation Learning (AUE-CRL) framework to learn the AU representations without AU annotations and adaptively use representations to facilitate facial expression recognition.
Facial Expression Recognition
Facial Expression Recognition (FER)
+1
no code implementations • 24 Dec 2020 • Yinya Huang, Meng Fang, Xunlin Zhan, Qingxing Cao, Xiaodan Liang, Liang Lin
It is crucial since the quality of the evidence is the key to answering commonsense questions, and even determines the upper bound on the QA systems performance.
1 code implementation • 22 Dec 2020 • Shuai Lin, Pan Zhou, Xiaodan Liang, Jianheng Tang, Ruihui Zhao, Ziliang Chen, Liang Lin
Besides, we develop a Graph-Evolving Meta-Learning (GEML) framework that learns to evolve the commonsense graph for reasoning disease-symptom correlations in a new disease, which effectively alleviates the needs of a large number of dialogues.
no code implementations • 22 Dec 2020 • Yubei Xiao, Ke Gong, Pan Zhou, Guolin Zheng, Xiaodan Liang, Liang Lin
When sampling tasks in MML-ASR, AMS adaptively determines the task sampling probability for each source language.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
1 code implementation • 14 Dec 2020 • Qingxing Cao, Bailin Li, Xiaodan Liang, Keze Wang, Liang Lin
Specifically, we generate the question-answer pair based on both the Visual Genome scene graph and an external knowledge base with controlled programs to disentangle the knowledge from other biases.
1 code implementation • CVPR 2021 • Lingbo Liu, Jiaqi Chen, Hefeng Wu, Guanbin Li, Chenglong Li, Liang Lin
Extensive experiments conducted on the RGBT-CC benchmark demonstrate the effectiveness of our framework for RGBT crowd counting.
1 code implementation • 30 Nov 2020 • Junfan Lin, Zhongzhan Huang, Keze Wang, Xiaodan Liang, Weiwei Chen, Liang Lin
Although deep reinforcement learning (RL) has been successfully applied to a variety of robotic control tasks, it's still challenging to apply it to real-world tasks, due to the poor sample efficiency.
2 code implementations • NeurIPS 2020 • Yangxin Wu, Gengwei Zhang, Hang Xu, Xiaodan Liang, Liang Lin
In this work, we propose an efficient, cooperative and highly automated framework to simultaneously search for all main components including backbone, segmentation branches, and feature fusion module in a unified panoptic segmentation pipeline based on the prevailing one-shot Network Architecture Search (NAS) paradigm.
no code implementations • 15 Oct 2020 • Hongjun Wang, Guanbin Li, Xiaobai Liu, Liang Lin
Although deep convolutional neural networks (CNNs) have demonstrated remarkable performance on multiple computer vision tasks, researches on adversarial learning have shown that deep models are vulnerable to adversarial examples, which are crafted by adding visually imperceptible perturbations to the input images.
1 code implementation • EMNLP 2020 • Jinghui Qin, Lihui Lin, Xiaodan Liang, Rumin Zhang, Liang Lin
A practical automatic textual math word problems (MWPs) solver should be able to solve various textual MWPs while most existing works only focused on one-unknown linear MWPs.
Ranked #10 on
Math Word Problem Solving
on ALG514
1 code implementation • EMNLP 2020 • Lishan Huang, Zheng Ye, Jinghui Qin, Liang Lin, Xiaodan Liang
Capitalized on the topic-level dialogue graph, we propose a new evaluation metric GRADE, which stands for Graph-enhanced Representations for Automatic Dialogue Evaluation.
no code implementations • 25 Sep 2020 • Pengxu Wei, Hannan Lu, Radu Timofte, Liang Lin, WangMeng Zuo, Zhihong Pan, Baopu Li, Teng Xi, Yanwen Fan, Gang Zhang, Jingtuo Liu, Junyu Han, Errui Ding, Tangxin Xie, Liang Cao, Yan Zou, Yi Shen, Jialiang Zhang, Yu Jia, Kaihua Cheng, Chenhuan Wu, Yue Lin, Cen Liu, Yunbo Peng, Xueyi Zou, Zhipeng Luo, Yuehan Yao, Zhenyu Xu, Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Tongtong Zhao, Shanshan Zhao, Yoseob Han, Byung-Hoon Kim, JaeHyun Baek, HaoNing Wu, Dejia Xu, Bo Zhou, Wei Guan, Xiaobo Li, Chen Ye, Hao Li, Yukai Shi, Zhijing Yang, Xiaojun Yang, Haoyu Zhong, Xin Li, Xin Jin, Yaojun Wu, Yingxue Pang, Sen Liu, Zhi-Song Liu, Li-Wen Wang, Chu-Tak Li, Marie-Paule Cani, Wan-Chi Siu, Yuanbo Zhou, Rao Muhammad Umer, Christian Micheloni, Xiaofeng Cong, Rajat Gupta, Keon-Hee Ahn, Jun-Hyuk Kim, Jun-Ho Choi, Jong-Seok Lee, Feras Almasri, Thomas Vandamme, Olivier Debeir
This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020.
no code implementations • 20 Sep 2020 • Tianshui Chen, Liang Lin, Riquan Chen, Xiaolu Hui, Hefeng Wu
The framework exploits prior knowledge to guide adaptive information propagation among different categories to facilitate multi-label analysis and reduce the dependency of training samples.
no code implementations • 18 Sep 2020 • Jie Wu, Guanbin Li, Xiaoguang Han, Liang Lin
Temporal grounding of natural language in untrimmed videos is a fundamental yet challenging multimedia task facilitating cross-media visual content retrieval.
1 code implementation • ECCV 2020 • Ganlong Zhao, Guanbin Li, Ruijia Xu, Liang Lin
Domain adaptation for object detection tries to adapt the detector from labeled datasets to unlabeled ones for better performance.
no code implementations • 17 Sep 2020 • Haofeng Li, Yirui Zeng, Guanbin Li, Liang Lin, Yizhou Yu
The field of computer vision has witnessed phenomenal progress in recent years partially due to the development of deep convolutional neural networks.
1 code implementation • 1 Sep 2020 • Yang Liu, Keze Wang, Guanbin Li, Liang Lin
In this paper, we propose a novel framework, named Semantics-aware Adaptive Knowledge Distillation Networks (SAKDN), to enhance action recognition in vision-sensor modality (videos) by adaptively transferring and distilling the knowledge from multiple wearable sensors.
no code implementations • 23 Aug 2020 • Junpeng Tan, Yukai Shi, Zhijing Yang, Caizhen Wen, Liang Lin
To ensure that we achieve effective sparse representation and clustering performance on the original data matrix, adaptive graph regularization and unsupervised clustering constraints are also incorporated in the proposed model to preserve the internal structural features of the data.
1 code implementation • ECCV 2020 • Pengxu Wei, Ziwei Xie, Hannan Lu, Zongyuan Zhan, Qixiang Ye, WangMeng Zuo, Liang Lin
Learning an SR model with conventional pixel-wise loss usually is easily dominated by flat regions and edges, and fails to infer realistic details of complex textures.
1 code implementation • 3 Aug 2020 • Tianshui Chen, Tao Pu, Hefeng Wu, Yuan Xie, Lingbo Liu, Liang Lin
Although each declares to achieve superior performance, fair comparisons are lacking due to the inconsistent choices of the source/target datasets and feature extractors.
Ranked #1 on
Cross-Domain Facial Expression Recognition
on Source: AFE, Target: CK+, JAFFE, SFEW2.0, FER2013, ExpW
Cross-Domain Facial Expression Recognition
Domain Adaptation
+3
1 code implementation • 3 Aug 2020 • Yuan Xie, Tianshui Chen, Tao Pu, Hefeng Wu, Liang Lin
However, most of these works focus on holistic feature adaptation, and they ignore local features that are more transferable across different datasets.
Cross-Domain Facial Expression Recognition
Facial Expression Recognition (FER)
1 code implementation • 21 Jul 2020 • Jie Wu, Tianshui Chen, Hefeng Wu, Zhi Yang, Guangchun Luo, Liang Lin
This is primarily due to (i) the conservative characteristic of traditional training objectives that drives the model to generate correct but hardly discriminative captions for similar images and (ii) the uneven word distribution of the ground-truth captions, which encourages generating highly frequent words/phrases while suppressing the less frequent but more concrete ones.
1 code implementation • ECCV 2020 • Bailin Li, Bowen Wu, Jiang Su, Guangrun Wang, Liang Lin
Many algorithms try to predict model performance of the pruned sub-nets by introducing various evaluation methods.
no code implementations • 3 May 2020 • Kai Zhang, Shuhang Gu, Radu Timofte, Taizhang Shang, Qiuju Dai, Shengchen Zhu, Tong Yang, Yandong Guo, Younghyun Jo, Sejong Yang, Seon Joo Kim, Lin Zha, Jiande Jiang, Xinbo Gao, Wen Lu, Jing Liu, Kwangjin Yoon, Taegyun Jeon, Kazutoshi Akita, Takeru Ooba, Norimichi Ukita, Zhipeng Luo, Yuehan Yao, Zhenyu Xu, Dongliang He, Wenhao Wu, Yukang Ding, Chao Li, Fu Li, Shilei Wen, Jianwei Li, Fuzhi Yang, Huan Yang, Jianlong Fu, Byung-Hoon Kim, JaeHyun Baek, Jong Chul Ye, Yuchen Fan, Thomas S. Huang, Junyeop Lee, Bokyeung Lee, Jungki Min, Gwantae Kim, Kanghyu Lee, Jaihyun Park, Mykola Mykhailych, Haoyu Zhong, Yukai Shi, Xiaojun Yang, Zhijing Yang, Liang Lin, Tongtong Zhao, Jinjia Peng, Huibing Wang, Zhi Jin, Jiahao Wu, Yifu Chen, Chenming Shang, Huanrong Zhang, Jeongki Min, Hrishikesh P. S, Densen Puthussery, Jiji C. V
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results.
no code implementations • 24 Apr 2020 • Zhongzhan Huang, Wenqi Shao, Xinjiang Wang, Liang Lin, Ping Luo
Channel pruning is a popular technique for compressing convolutional neural networks (CNNs), where various pruning criteria have been proposed to remove the redundant filters.
no code implementations • CVPR 2020 • Yangxin Wu, Gengwei Zhang, Yiming Gao, Xiajun Deng, Ke Gong, Xiaodan Liang, Liang Lin
We introduce a Bidirectional Graph Reasoning Network (BGRNet), which incorporates graph structure into the conventional panoptic segmentation network to mine the intra-modular and intermodular relations within and between foreground things and background stuff classes.
1 code implementation • CVPR 2020 • Hongjun Wang, Guangrun Wang, Ya Li, Dongyu Zhang, Liang Lin
To examine the robustness of ReID systems is rather important because the insecurity of ReID systems may cause severe losses, e. g., the criminals may use the adversarial perturbations to cheat the CCTV systems.
2 code implementations • 23 Mar 2020 • Lingbo Liu, Jiaqi Chen, Hefeng Wu, Tianshui Chen, Guanbin Li, Liang Lin
Crowd counting is an application-oriented task and its inference efficiency is crucial for real-world applications.
no code implementations • 23 Mar 2020 • Qingxing Cao, Xiaodan Liang, Keze Wang, Liang Lin
Inspired by the property of a capsule network that can carve a tree structure inside a regular convolutional neural network (CNN), we propose a hierarchical compositional reasoning model called the "Linguistically driven Graph Capsule Network", where the compositional process is guided by the linguistic parse tree.
1 code implementation • 14 Mar 2020 • Junfan Lin, Keze Wang, Ziliang Chen, Xiaodan Liang, Liang Lin
To eliminate this bias and inspired by the propensity score matching technique with causal diagram, we propose a propensity-based patient simulator to effectively answer unrecorded inquiry by drawing knowledge from the other records; Bias (ii) inherently comes along with the passively collected data, and is one of the key obstacles for training the agent towards "learning how" rather than "remembering what".
1 code implementation • 25 Feb 2020 • Yukai Shi, Haoyu Zhong, Zhijing Yang, Xiaojun Yang, Liang Lin
Previous image SR methods fail to exhibit similar performance on Real-SR as the image data is not aligned inherently.
no code implementations • 22 Jan 2020 • Haofeng Li, Guanbin Li, BinBin Yang, Guanqi Chen, Liang Lin, Yizhou Yu
The proposed algorithm for the first time achieves competitive accuracy and high inference efficiency simultaneously with a single CPU thread.
1 code implementation • 18 Jan 2020 • Jie Wu, Guanbin Li, Si Liu, Liang Lin
Temporally language grounding in untrimmed videos is a newly-raised task in video understanding.
2 code implementations • 14 Jan 2020 • Lingbo Liu, Jingwen Chen, Hefeng Wu, Jiajie Zhen, Guanbin Li, Liang Lin
To address this problem, we model a metro system as graphs with various topologies and propose a unified Physical-Virtual Collaboration Graph Network (PVCGN), which can effectively learn the complex ridership patterns from the tailor-designed graphs.
no code implementations • 18 Dec 2019 • Jihan Yang, Ruijia Xu, Ruiyu Li, Xiaojuan Qi, Xiaoyong Shen, Guanbin Li, Liang Lin
In contrast to adversarial alignment, we propose to explicitly train a domain-invariant classifier by generating and defensing against pointwise feature space adversarial perturbations.
1 code implementation • 29 Nov 2019 • Changlin Li, Jiefeng Peng, Liuchun Yuan, Guangrun Wang, Xiaodan Liang, Liang Lin, Xiaojun Chang
Moreover, we find that the knowledge of a network model lies not only in the network parameters but also in the network architecture.
1 code implementation • 21 Nov 2019 • Riquan Chen, Tianshui Chen, Xiaolu Hui, Hefeng Wu, Guanbin Li, Liang Lin
In this work, we represent the semantic correlations in the form of structured knowledge graph and integrate this graph into deep neural networks to promote few-shot learning by a novel Knowledge Graph Transfer Network (KGTN).
no code implementations • 31 Oct 2019 • Yang Wu, Pengxu Wei, Liang Lin
To solve this problem, we derive a second-order Wasserstein gradient flow of the global relative entropy from Fokker-Planck equation.
no code implementations • CVPR 2019 • Weijiang Yu, Xiaodan Liang, Ke Gong, Chenhan Jiang, Nong Xiao, Liang Lin
Each Layout-Graph Reasoning(LGR) layer aims to map feature representations into structural graph nodes via a Map-to-Node module, performs reasoning over structural graph nodes to achieve global layout coherency via a layout-graph reasoning module, and then maps graph nodes back to enhance feature representations via a Node-to-Map module.
no code implementations • 28 Sep 2019 • Xiaopeng Yan, Ziliang Chen, Anni Xu, Xiaoxi Wang, Xiaodan Liang, Liang Lin
Resembling the rapid learning capability of human, few-shot learning empowers vision systems to understand new concepts by training with few samples.
Ranked #21 on
Few-Shot Object Detection
on MS-COCO (30-shot)