no code implementations • ECCV 2020 • Jingwei Xin, Nannan Wang, Xinrui Jiang, Jie Li, Heng Huang, Xinbo Gao
Lighter model and faster inference are the focus of current single image super-resolution (SISR) research.
no code implementations • WMT (EMNLP) 2020 • Calvin Bao, Yow-Ting Shiue, Chujun Song, Jie Li, Marine Carpuat
This paper describes the University of Maryland’s submissions to the WMT20 Shared Task on Chat Translation.
1 code implementation • 23 Jun 2025 • Jie Li, Shifei Ding, Lili Guo, Xuan Li
Furthermore, we introduce a multi-modal anchor gated transformer to effectively integrate utterance-level representations across modalities.
no code implementations • 20 Jun 2025 • Penglong Zhai, Yifang Yuan, Fanyi Di, Jie Li, Yue Liu, Chen Li, Jie Huang, Sicong Wang, Yao Xu, Xin Li
Specifically, different from existing reconstruction-based strategies, SimCIT propose to use a learnable residual quantization module to align with the signals from different modalities of the items, which combines multi-modal knowledge alignment and semantic tokenization in a mutually beneficial contrastive learning framework.
no code implementations • 19 Jun 2025 • Tianle Gu, Kexin Huang, Zongqi Wang, Yixu Wang, Jie Li, Yuanqi Yao, Yang Yao, Yujiu Yang, Yan Teng, Yingchun Wang
Consequently, small shifts in hidden activations can re-trigger harmful behaviors embedded in the latent space.
no code implementations • 13 Jun 2025 • Zhaoyang Wang, Jie Li, Wen Lu, Lihuo He, Maoguo Gong, Xinbo Gao
State-of-the-art (SOTA) compressed video super-resolution (CVSR) models face persistent challenges, including prolonged inference time, complex training pipelines, and reliance on auxiliary information.
no code implementations • 13 Jun 2025 • Zhaoyang Wang, Wen Lu, Jie Li, Lihuo He, Maoguo Gong, Xinbo Gao
Free-energy-guided self-repair mechanisms have shown promising results in image quality assessment (IQA), but remain under-explored in video quality assessment (VQA), where temporal dynamics and model constraints pose unique challenges.
no code implementations • 10 Jun 2025 • Fuhan Cai, Yong Guo, Jie Li, Wenbo Li, Xiangzhong Fang, Jian Chen
Recent advancements in text-to-image (T2I) generation have led to the emergence of highly expressive models such as diffusion transformers (DiTs), exemplified by FLUX.
no code implementations • 3 Jun 2025 • Yang Yao, Lingyu Li, Jiaxin Song, Chiyu Chen, Zhenqi He, Yixu Wang, Xin Wang, Tianle Gu, Jie Li, Yan Teng, Yingchun Wang
As Multimodal Large Language Models (MLLMs) continue to evolve, their cognitive and reasoning capabilities have seen remarkable progress.
no code implementations • 26 May 2025 • Jiaxin Song, Yixu Wang, Jie Li, Rui Yu, Yan Teng, Xingjun Ma, Yingchun Wang
Vision-Language Models (VLMs) exhibit impressive performance, yet the integration of powerful vision encoders has significantly broadened their attack surface, rendering them increasingly susceptible to jailbreak attacks.
no code implementations • 25 May 2025 • Ruiyang Xia, Dawei Zhou, Decheng Liu, Lin Yuan, Jie Li, Nannan Wang, Xinbo Gao
Face swapping, recognized as a privacy and security concern, has prompted considerable defensive research.
no code implementations • 20 May 2025 • Huaijie Wang, De Cheng, Guozhang Li, Zhipeng Xu, Lingfeng He, Jie Li, Nannan Wang, Xinbo Gao
Together, StPR effectively leverages spatial semantics and temporal dynamics, achieving a unified, exemplar-free VCIL framework.
no code implementations • 20 May 2025 • Jie Li, Shengwei Tian, Long Yu, Xin Ning
To address this issue, we propose a Flexible-Weighted Chamfer Distance (FCD) to guide point cloud generation.
no code implementations • 14 May 2025 • Jie Li, Jing Li, Zhanyu Ju, Fengkui Gong, Lu Lv
As the sampling duration increases, the detection speed improves while the detection accuracy of broadcast frames termed as small targets decreases.
no code implementations • 14 May 2025 • Jianfeng Jiao, Xi Gao, Jie Li
In this work, an enhanced framework for pure component property prediction by using explainable machine learning methods is proposed.
no code implementations • 11 May 2025 • Junjie Yu, John S. Schreck, David John Gagne, Keith W. Oleson, Jie Li, Yongtu Liang, Qi Liao, Mingfei Sun, David O. Topping, Zhonghua Zheng
This study proposes an integrated framework combining RL with an urban climate model that incorporates a building energy model, aiming to evaluate the efficacy of RL-based HVAC control across different background climates, impacts of RL strategies on indoor climate and local urban climate, and the transferability of RL strategies across cities.
no code implementations • 7 May 2025 • Wei Xiong, Junming Lin, Jiangtong Li, Jie Li, Changjun Jiang
A channel encoder adaptively compresses variable channel information, a temporal encoder captures task-guided evolution, and a hybrid decoder reconstructs signals in both temporal and frequency domains.
no code implementations • 26 Apr 2025 • Tengfei Xing, Xiaodan Ren, Jie Li
This enables a multiscale analysis of the stress concentration regions at phase boundaries.
no code implementations • 26 Apr 2025 • Tengfei Xing, Xiaodan Ren, Jie Li
In this study, we propose a framework for global stress generation and spatiotemporal super-resolution in TRMs under dynamic loading.
1 code implementation • 20 Apr 2025 • Binjie Guo, Hanyu Zheng, Guowei Su, Ru Zhang, Haohan Jiang, Xurong Lin, Hongyan Wei, Aisheng Mo, Jie Li, Zhiyuan Qian, Zhuhao Zhang, Xiaoyuan Cheng
Recent years have witnessed significant progress in reinforcement learning, especially with Zero-like paradigms, which have greatly boosted the generalization and reasoning abilities of large-scale language models.
no code implementations • 15 Apr 2025 • Yaodong Song, Hongjie Chen, Jie Lian, Yuxin Zhang, Guangmin Xia, Zehan Li, Genliang Zhao, Jian Kang, Jie Li, Yongxiang Li, Xuelong Li
While large language models (LLMs) have revolutionized text-to-speech (TTS) synthesis through discrete tokenization paradigms, current architectures exhibit fundamental tensions between three critical dimensions: 1) irreversible loss of acoustic characteristics caused by quantization of speech prompts; 2) stringent dependence on precisely aligned prompt speech-text pairs that limit real-world deployment; and 3) catastrophic forgetting of the LLM's native text comprehension during optimization for speech token generation.
no code implementations • 7 Apr 2025 • Xueqing Li, Zehan Li, Boyu Zhu, Ruihao Jing, Jian Kang, Jie Li, Xiao-Lei Zhang, Xuelong Li
Its quantization error is lower-bounded by the product of rho and epsilon-kms, where epsilon-kms denotes the quantization error of a single K-means quantizer.
no code implementations • 3 Apr 2025 • Chaojun Ni, XiaoFeng Wang, Zheng Zhu, Weijie Wang, Haoyun Li, Guosheng Zhao, Jie Li, Wenkang Qin, Guan Huang, Wenjun Mei
Interactive 3D generation is gaining momentum and capturing extensive attention for its potential to create immersive virtual experiences.
no code implementations • CVPR 2025 • Kun Liu, Qi Liu, Xinchen Liu, Jie Li, Yongdong Zhang, Jiebo Luo, Xiaodong He, Wu Liu
However, human-object interaction (HOI) often cannot be precisely generated by current T2V models due to the lack of large-scale videos with accurate captions for HOI.
no code implementations • 19 Mar 2025 • Jie Li, Jing Li, Lu Lv, Peixin Zhang, Fengkui Gong
Cross-correlation is performed between locally generated ZC sequences and drone signals to derive ZC sequence-based features.
1 code implementation • 11 Mar 2025 • Zheyi Chen, Sijin Huang, Geyong Min, Zhaolong Ning, Jie Li, Yan Zhang
Mobile Edge Computing (MEC) offers low-latency and high-bandwidth support for Internet-of-Vehicles (IoV) applications.
no code implementations • 4 Mar 2025 • Yuhao Yang, Zhi Ji, Zhaopeng Li, Yi Li, Zhonglin Mo, Yue Ding, Kai Chen, Zijian Zhang, Jie Li, Shuanglong Li, Lin Liu
To address this, we introduce the Cascaded Organized Bi-Represented generAtive retrieval (COBRA) framework, which innovatively integrates sparse semantic IDs and dense vectors through a cascading process.
no code implementations • 26 Feb 2025 • Hongyi Cal, Jie Li, Wenzhen Dong
The effectiveness of instruction fine-tuning for Large Language Models is fundamentally constrained by the quality and efficiency of training datasets.
no code implementations • 13 Dec 2024 • Jing Sun, Qiangqiang Yuan, Huanfeng Shen, Jie Li, Liangpei Zhang
In this paper, we propose a novel two-step image super resolution method concatenating multi-frame super-resolution (MFSR) with single-frame super-resolution (SFSR), to progressively upsample images to the desired resolution.
1 code implementation • 1 Nov 2024 • Dong Wen, Zhongpei Liu, Tong Yang, Tao Li, Tianyun Li, Chenglong Li, Jie Li, Zhigang Sun
The programmable run-to-completion accelerators are developed for flexible inference.
no code implementations • 20 Oct 2024 • Jiayang Niu, Jie Li, Ke Deng, Mark Sanderson, Yongli Ren
We propose Counterfactual Analysis Quadratic Unconstrained Binary Optimization (CAQUBO) to solve QUBO problems for feature selection in recommender systems.
no code implementations • 26 Sep 2024 • Jingyu Song, Xudong Chen, Liupei Lu, Jie Li, Katherine A. Skinner
We propose MemFusionMap, a novel temporal fusion model with enhanced temporal reasoning capabilities for online HD map construction.
no code implementations • 14 Sep 2024 • Guang Yang, Jie Li, Xin Liu, Zhusi Zhong, Xinbo Gao
Existing methods take pixel intensity, texture and high-level vision task information as the standards to determine preservation of information, lacking enhancement for human perception.
1 code implementation • 13 Sep 2024 • Xinxu Ge, Xin Liu, Zitong Yu, Jingang Shi, Chun Qi, Jie Li, Heikki Kälviäinen
Based on our analysis, we propose DiffFAS framework, which quantifies quality as prior information input into the network to counter image quality shift, and performs diffusion-based high-fidelity cross-domain and cross-attack types generation to counter image style shift.
1 code implementation • 12 Sep 2024 • Jian Qian, Miao Sun, Ashley Lee, Jie Li, Shenglong Zhuo, Patrick Yin Chiang
The network consists of an input module for the depth map and RGB image features extraction and concatenation, a U-shaped encoder-decoder Transformer for extracting deep features, and a refinement module.
no code implementations • 10 Sep 2024 • Hongyi Cai, Mohammad Mahdinur Rahman, Mohammad Shahid Akhtar, Jie Li, Jingyu Wu, Zhili Fang
Thus, we introduce AgileIR, group shifted attention mechanism along with window attention, which sparsely simplifies the model in architecture.
1 code implementation • 13 Aug 2024 • Guangliang Pan, Qihui Wu, Bo Zhou, Jie Li, Wei Wang, Guoru Ding, David K. Y. Yau
Based on the Deep- SPred, we first propose a novel 3D spectrum prediction method combining a flow processing strategy with 3D vision Transformer (ViT, i. e., Swin) and a pyramid to serve possible applications such as spectrum monitoring task, named 3D-SwinSTB.
1 code implementation • 4 Jul 2024 • Laiyan Ding, Hualie Jiang, Jie Li, Yongquan Chen, Rui Huang
This paper proposes an efficient and consistent pose estimation design and two loss functions to enhance cross-view consistency for SSSDE.
no code implementations • 3 Jul 2024 • Jiayang Niu, Jie Li, Ke Deng, Yongli Ren
In this paper, we use Quantum Annealers to address the feature selection problem in recommendation algorithms.
no code implementations • 17 Jun 2024 • Jie Li, Yi Liu, Chongyang Liu, Xiaoning Ren, Ling Shi, Weisong Sun, Yinxing Xue
Our results show that these methods significantly improve refusal rates and reduce unsafe content, with cross-model distilling achieving refusal rates close to Claude3's 94. 51%.
no code implementations • 3 Jun 2024 • Zhusi Zhong, Helen Zhang, Fayez H. Fayad, Andrew C. Lancaster, John Sollee, Shreyas Kulkarni, Cheng Ting Lin, Jie Li, Xinbo Gao, Scott Collins, Colin Greineder, Sun H. Ahn, Harrison X. Bai, Zhicheng Jiao, Michael K. Atalay
Imaging features and/or clinical variables were then incorporated into DL models to predict survival outcomes.
no code implementations • 2 Jun 2024 • Haojun Xu, Yan Gao, Jie Li, Xinbo Gao
Significant action recognition performance is achieved when evaluated on the challenging NTU RGB+D, NTU RGB+D 120, and PKU-MMD benchmarks and validate that multi-granularity semantic features facilitate the differentiation of action clusters with similar visual features.
no code implementations • 29 May 2024 • Guangliang Pan, Jie Li, Minglei Li
The advantage of this fusion mode is that it can deeply capture the long-term dependence of multichannel spectrum data.
no code implementations • 29 May 2024 • Ziqi Ren, Jie Li, Xuetong Xue, Xin Li, Fan Yang, Zhicheng Jiao, Xinbo Gao
MindSemantix generates high-quality captions that are deeply rooted in the visual and semantic information derived from brain activity.
1 code implementation • 23 May 2024 • Zhusi Zhong, Jie Li, John Sollee, Scott Collins, Harrison Bai, Paul Zhang, Terrence Healey, Michael Atalay, Xinbo Gao, Zhicheng Jiao
In response to the worldwide COVID-19 pandemic, advanced automated technologies have emerged as valuable tools to aid healthcare professionals in managing an increased workload by improving radiology report generation and prognostic analysis.
no code implementations • 17 May 2024 • Janick Weberpals, Pamela A. Shaw, Kueiyu Joshua Lin, Richard Wyss, Joseph M Plasek, Li Zhou, Kerry Ngan, Thomas DeRamus, Sudha R. Raman, Bradley G. Hammill, Hana Lee, Sengwee Toh, John G. Connolly, Kimberly J. Dandreo, Fang Tian, Wei Liu, Jie Li, José J. Hernández-Muñoz, Sebastian Schneeweiss, Rishi J. Desai
HDMI approaches may decrease bias in studies with partially observed confounders where missingness depends on unobserved factors.
no code implementations • 10 May 2024 • Trevor J. Chan, Aarush Sahni, Yijin Fang, Jie Li, Alisha Luthra, Alison Pouch, Chamith S. Rajapakse
We introduce SAM3D, a new approach to semi-automatic zero-shot segmentation of 3D images building on the existing Segment Anything Model.
1 code implementation • 5 May 2024 • Zhusi Zhong, Jie Li, Zhuoqi Ma, Scott Collins, Harrison Bai, Paul Zhang, Terrance Healey, Xinbo Gao, Michael K. Atalay, Zhicheng Jiao
The COVID-19 pandemic has strained global public health, necessitating accurate diagnosis and intervention to control disease spread and reduce mortality rates.
no code implementations • 25 Mar 2024 • Laiyan Ding, Panwen Hu, Jie Li, Rui Huang
To address this RGB-TSDF distribution difference, we propose a two-stage network with a 3D RGB feature completion module that completes RGB features with meaningful values for occluded areas.
1 code implementation • 19 Mar 2024 • Wenjun Zou, Yao Lyu, Jie Li, Yujie Yang, Shengbo Eben Li, Jingliang Duan, Xianyuan Zhan, Jingjing Liu, Yaqin Zhang, Keqiang Li
Safe reinforcement learning (RL) offers advanced solutions to constrained optimal control problems.
no code implementations • 14 Mar 2024 • Jie Li, Jiaying Wen, Tongxin Yang, Fenglin Cai, Miao Wei, Zhiwei Zhang, Li Jiang
In this paper, we introduce a new dataset in the medical field of Traumatic Brain Injury (TBI), called TBI-IT, which includes both electronic medical records (EMRs) and head CT images.
no code implementations • 27 Feb 2024 • Haojun Jiang, Jiawei Sun, Jie Li, Chentao Wu
Graph representation learning (GRL) makes considerable progress recently, which encodes graphs with topological structures into low-dimensional embeddings.
1 code implementation • 22 Feb 2024 • Zhaoyang Wang, Bo Hu, Mingyang Zhang, Jie Li, Leida Li, Maoguo Gong, Xinbo Gao
Firstly, we devise a new diffusion restoration network that leverages the produced enhanced image and noise-containing images, incorporating nonlinear features obtained during the denoising process of the diffusion model, as high-level visual information.
no code implementations • 20 Feb 2024 • Angus Yang, Zehan Li, Jie Li
Our GenAI Coding Workshop highlights the effectiveness and accessibility of the prompting methodology developed in this study.
no code implementations • 3 Feb 2024 • Lu Chen, Shaofeng Li, Benhao Huang, Fan Yang, Zheng Li, Jie Li, Yuan Luo
However, in this work, we reveal the existence of a harmless perturbation space, in which perturbations drawn from this space, regardless of their magnitudes, leave the network output unchanged when applied to inputs.
no code implementations • 30 Jan 2024 • Jie Li, Yi Liu, Chongyang Liu, Ling Shi, Xiaoning Ren, Yaowen Zheng, Yang Liu, Yinxing Xue
To address this research gap, we conducted an extensive empirical study on Multilingual Jailbreak attacks.
1 code implementation • 29 Jan 2024 • Jie Li, Yulong Xia, Tongxin Yang, Fenglin Cai, Miao Wei, Zhiwei Zhang, Li Jiang
Index Terms-HICH, Deep learning, Intraparenchymal hemorrhage, named entity recognition, novel dataset
no code implementations • 5 Jan 2024 • Song Bai, Jie Li
Since the year 2023 an abundant amount of research papers has emerged in the domain of 3D generation.
no code implementations • 28 Dec 2023 • Yuhang Zhang, Yuang Deng, Xiaopeng Zhang, Jie Li, Robert C. Qiu, Qi Tian
In DeLR, the query is based on region-level, and we only annotate the object region that is queried; 2) Instead of directly providing both localization and recognition annotations, we separately query the two components, and thus reduce the recognition budget with the pseudo class labels provided by the model.
1 code implementation • 17 Dec 2023 • Guang Yang, Jie Li, Xinbo Gao
Specifically, we introduce a Spatial-Frequency Fusion Block to facilitate efficient interaction between dual domains and capture complementary information from input images with different exposures.
no code implementations • 14 Dec 2023 • Yan Gao, Haojun Xu, Nannan Wang, Jie Li, Xinbo Gao
In addition to the previous method of treating objects as nodes, the network innovatively treats object trajectories as nodes for information interaction, improving the graph neural network's feature representation capability.
1 code implementation • 7 Dec 2023 • Guang Yang, Jie Li, Hanxiao Lei, Xinbo Gao
In this study, we propose a multi-scale dual attention (MDA) framework for infrared and visible image fusion, which is designed to measure and integrate complementary information in both structure and loss function at the image and patch level.
no code implementations • 5 Dec 2023 • Guozhang Li, Xinpeng Ding, De Cheng, Jie Li, Nannan Wang, Xinbo Gao
To further clarify the noise of expanded boundaries, we combine mutual learning with a tailored proposal-level contrastive objective to use a learnable approach to harmonize a balance between incomplete yet clean (initial) and comprehensive yet noisy (expanded) boundaries for more precise ones.
no code implementations • 28 Nov 2023 • Jie Li, Zhixin Li, Zhi Liu, Pengyuan Zhou, Richang Hong, Qiyue Li, Han Hu
To our knowledge, this is the first comprehensive study of viewport prediction in volumetric video streaming.
no code implementations • 20 Nov 2023 • Yating Chen, Cai Wen, Yan Huang, Le Liang, Jie Li, HUI ZHANG, Wei Hong
In this paper, we formulate the precoding problem of integrated sensing and communication (ISAC) waveform as a non-convex quadratically constrainted quadratic program (QCQP), in which the weighted sum of communication multi-user interference (MUI) and the gap between dual-use waveform and ideal radar waveform is minimized with peak-to-average power ratio (PAPR) constraints.
no code implementations • 9 Nov 2023 • Yuxin Zhu, Xilei Zhu, Huiyu Duan, Jie Li, Kaiwei Zhang, Yucheng Zhu, Li Chen, Xiongkuo Min, Guangtao Zhai
Visual saliency prediction for omnidirectional videos (ODVs) has shown great significance and necessity for omnidirectional videos to help ODV coding, ODV transmission, ODV rendering, etc..
1 code implementation • 8 Nov 2023 • Zhanbo Feng, Yuanjie Wang, Jie Li, Fan Yang, Jiong Lou, Tiebin Mi, Robert. C. Qiu, Zhenyu Liao
As a result, there is a growing trend to leverage federated learning (FL) techniques to train large ML models in a distributed and collaborative manner.
1 code implementation • 7 Nov 2023 • Katie Z Luo, Xinshuo Weng, Yan Wang, Shuang Wu, Jie Li, Kilian Q Weinberger, Yue Wang, Marco Pavone
We propose a novel framework to integrate SD maps into online map prediction and propose a Transformer-based encoder, SD Map Encoder Representations from transFormers, to leverage priors in SD maps for the lane-topology prediction task.
no code implementations • 29 Oct 2023 • Jingliang Duan, Jie Li, Xuyang Chen, Kai Zhao, Shengbo Eben Li, Lin Zhao
Despite the absence of convexity, we leverage these properties to derive novel findings regarding convergence (and nearly dimension-free rate) to stationary points for three policy gradient methods, including the vanilla policy gradient method, the natural policy gradient method, and the Gauss-Newton method.
no code implementations • 11 Oct 2023 • Zeyang Li, Chuxiong Hu, Yunan Wang, Guojian Zhan, Jie Li, Shengbo Eben Li
We also show that a modified version of regularized policy iteration, i. e., with finite-step policy evaluation, is equivalent to inexact Newton method where the Newton iteration formula is solved with truncated iterations.
no code implementations • 26 Sep 2023 • Jie Li, Hancheng Cao, Laura Lin, Youyang Hou, Ruihao Zhu, Abdallah El Ali
They emphasized the unique human factors of "enjoyment" and "agency", where humans remain the arbiters of "AI alignment".
no code implementations • 18 Sep 2023 • Jie Li, Jiawei Wang, Shengbo Eben Li, Keqiang Li
Connected and automated vehicles (CAVs) technologies promise to attenuate undesired traffic disturbances.
1 code implementation • 7 Sep 2023 • Li Li, Qingqing Li, Guozheng Xu, Pengwei Zhou, Jingmin Tu, Jie Li, Mingming Li, Jian Yao
To solve this problem, we propose a boundary-aware point clustering approach in Euclidean and embedding spaces constructed by a multi-task deep network for roof plane segmentation.
1 code implementation • 30 Aug 2023 • Zhanbo Feng, Zenan Ling, Xinyu Lu, Ci Gong, Feng Zhou, Wugedele Bao, Jie Li, Fan Yang, Robert C. Qiu
The use of denoising diffusion models is becoming increasingly popular in the field of image editing.
no code implementations • 29 Aug 2023 • Lei Han, Qingxu Zhu, Jiapeng Sheng, Chong Zhang, Tingguang Li, Yizheng Zhang, He Zhang, Yuzhen Liu, Cheng Zhou, Rui Zhao, Jie Li, Yufeng Zhang, Rui Wang, Wanchao Chi, Xiong Li, Yonghui Zhu, Lingzhu Xiang, Xiao Teng, Zhengyou Zhang
Knowledge from animals and humans inspires robotic innovations.
no code implementations • 20 Aug 2023 • Shuman Fang, Zhiwen Lin, Ke Yan, Jie Li, Xianming Lin, Rongrong Ji
However, these methods ignore the relationship among humans, objects, and interactions: 1) human features are more contributive than object ones to interaction prediction; 2) interactive information disturbs the detection of objects but helps human detection.
no code implementations • 16 Aug 2023 • Mengjie Du, Xiang Fang, Jie Li
This technical report describes ChinaTelecom system for Track 1 (closed) of the VoxCeleb2023 Speaker Recognition Challenge (VoxSRC 2023).
no code implementations • 4 Aug 2023 • Shuman Fang, Shuai Liu, Jie Li, Guannan Jiang, Xianming Lin, Rongrong Ji
Human-Object Interaction (HOI) detection aims to understand the interactions between humans and objects, which plays a curtail role in high-level semantic understanding tasks.
no code implementations • CVPR 2025 • Hao Lin, Ke wu, Jie Li, Jun Li, Wu-Jun Li
To the best of our knowledge, UniAP is the first parallel method that can jointly optimize the two categories of parallel strategies to find an optimal solution.
no code implementations • 20 Jul 2023 • Zongmin Liu, Jirui Wang, Jie Li, Zufeng Li, Kai Ren, Peng Shi
Furthermore, a detection-grasping integrated algorithm based on box coordinate matching (DG-BCM) is proposed to obtain the fusion model of object detection and grasp estimation.
no code implementations • 6 Jul 2023 • Ruiyang Xia, Decheng Liu, Jie Li, Lin Yuan, Nannan Wang, Xinbo Gao
Advanced manipulation techniques have provided criminals with opportunities to make social panic or gain illicit profits through the generation of deceptive media, such as forged face images.
no code implementations • 28 Jun 2023 • Feng Xu, Shuxiang Zhang, Linjie Ma, Yong Hou, Jie Li, Andrej Denisenko, Zifu Li, Joachim Spatz, Jörg Wrachtrup, Qiang Wei, Zhiqin Chu
The constant interplay and information exchange between cells and their micro-environment are essential to their survival and ability to execute biological functions.
no code implementations • 14 Jun 2023 • Zhusi Zhong, Jie Li, Lulu Bi, Li Yang, Ihab Kamel, Rama Chellappa, Xinbo Gao, Harrison Bai, Zhicheng Jiao
Medical image segmentation based on deep learning often fails when deployed on images from a different domain.
no code implementations • 13 Jun 2023 • Bowen Li, Hanlin Gu, Ruoxin Chen, Jie Li, Chentao Wu, Na Ruan, Xueming Si, Lixin Fan
We investigate a Temporal Gradient Inversion Attack with a Robust Optimization framework, called TGIAs-RO, which recovers private data without any prior knowledge by leveraging multiple temporal gradients.
1 code implementation • 21 May 2023 • Haojun Xu, Yan Gao, Zheng Hui, Jie Li, Xinbo Gao
Also, humans have brain regions dedicated to understanding the minds of others and analyzing their intentions, such as the medial prefrontal cortex of the temporal lobe.
Ranked #3 on
Skeleton Based Action Recognition
on NTU RGB+D 120
(using extra training data)
1 code implementation • CVPR 2023 • Basile Van Hoorick, Pavel Tokmakov, Simon Stent, Jie Li, Carl Vondrick
Tracking objects with persistence in cluttered and dynamic environments remains a difficult challenge for computer vision systems.
1 code implementation • 25 Apr 2023 • Guozhang Li, De Cheng, Xinpeng Ding, Nannan Wang, Jie Li, Xinbo Gao
The proposed Bi-SCC firstly adopts a temporal context augmentation to generate an augmented video that breaks the correlation between positive actions and their co-scene actions in the inter-video; Then, a semantic consistency constraint (SCC) is used to enforce the predictions of the original video and augmented video to be consistent, hence suppressing the co-scene actions.
no code implementations • 7 Apr 2023 • Yalu Wang, Zhijie Han, Jie Li, Xin He
To address the above issue, this paper proposes a graph neural network algorithm based on behavior similarity (BS-GAT) using graph attention network.
no code implementations • 5 Apr 2023 • Kai Han, Xiaohu Huang, Yandong Li, Sagar Vaze, Jie Li, Xuhui Jia
In this paper, we reconsider the recognition problem and task a vision-language model with assigning class names to images given only a large (essentially unconstrained) vocabulary of categories as prior information.
no code implementations • 26 Mar 2023 • Yukang Zhang, Yan Yan, Jie Li, Hanzi Wang
Furthermore, to better disentangle the modality-relevant features and the modality-irrelevant features, we propose a novel Center-Quadruplet Causal (CQC) loss to encourage the network to effectively learn the modality-relevant features and the modality-irrelevant features.
1 code implementation • CVPR 2023 • Dian Chen, Jie Li, Vitor Guizilini, Rares Ambrus, Adrien Gaidon
We design view-conditioned queries at the output level, which enables the generation of multiple virtual frames during training to learn viewpoint equivariance by enforcing multi-view consistency.
no code implementations • 15 Feb 2023 • Shijing Yuan, Hongze Liu, Hongtao Lv, Zhanbo Feng, Jie Li, Hongyang Chen, Chentao Wu
To overcome these limitations, we propose a novel adaptive mechanism for cross-silo FL, towards incentivizing organizations to contribute data to maximize their long-term payoffs in a real dynamic training environment.
1 code implementation • CVPR 2023 • Ziqi Pang, Jie Li, Pavel Tokmakov, Dian Chen, Sergey Zagoruyko, Yu-Xiong Wang
It emphasizes spatio-temporal continuity and integrates both past and future reasoning for tracked objects.
no code implementations • 2 Feb 2023 • Jinjiang Guo, Jie Li
Most existing methodologies utilize either biomedical network information or molecule structural features to predict potential interaction link.
no code implementations • 8 Jan 2023 • Fengping Wang, Jie Li, Chun Qi, Lin Wang, Pan Wang
A micro-expression is a spontaneous unconscious facial muscle movement that can reveal the true emotions people attempt to hide.
no code implementations • 7 Jan 2023 • Zongmin Liu, Jirui Wang, Jie Li, Pengda Liu, Kai Ren
However, indoor scenes are usually complex and there are many types of interference factors, leading to great challenges in the multiple targets detection.
no code implementations • CVPR 2023 • Pavel Tokmakov, Jie Li, Adrien Gaidon
Yet, this important phenomenon is largely absent from existing video object segmentation (VOS) benchmarks.
no code implementations • 8 Nov 2022 • Tara Sadjadpour, Jie Li, Rares Ambrus, Jeannette Bohg
To address these issues in a unified framework, we propose to learn shape and spatio-temporal affinities between tracks and detections in consecutive frames.
1 code implementation • 7 Nov 2022 • Jie Li, Paul Fearnhead, Piotr Fryzlewicz, Tengyao Wang
We show how to automatically generate new offline detection methods based on training a neural network.
no code implementations • 27 Oct 2022 • Pan Wang, Jie Li, Jieru Chen, Lin Wang, Chun Qi
To take full exploration of the constraints between spectra, the coefficients corresponding to the convolution kernel are constrained by the L_(2, 1)norm to improve spectral accuracy.
no code implementations • 5 Oct 2022 • Dennis Park, Jie Li, Dian Chen, Vitor Guizilini, Adrien Gaidon
Our methods leverage commonly available LiDAR or RGB videos during training time to fine-tune the depth representation, which leads to improved 3D detectors.
no code implementations • 21 Sep 2022 • Han Xu, Zheming Zuo, Jie Li, Victor Chang
Situating at the core of Artificial Intelligence (AI), Machine Learning (ML), and more specifically, Deep Learning (DL) have embraced great success in the past two decades.
no code implementations • 17 Sep 2022 • Ye Bai, Jie Li, Wenjing Han, Hao Ni, Kaituo Xu, Zhuo Zhang, Cheng Yi, Xiaorui Wang
Experimental results show that the proposed model achieves competitive performance with 1/3 of the parameters of the encoder, compared with the full-parameter model.
no code implementations • 25 Jul 2022 • Jingyuan Yang, Jie Li, Leida Li, Xiumei Wang, Yuxuan Ding, Xinbo Gao
In psychology, the \textit{Object-Appraisal-Emotion} model has demonstrated that each individual's emotion is affected by his/her subjective appraisal, which is further formed by the affective memory.
1 code implementation • 12 Jul 2022 • Decheng Liu, Weijie He, Chunlei Peng, Nannan Wang, Jie Li, Xinbo Gao
The multiple branches transformer is employed to explore the inter-correlation between different attributes in similar semantic regions for attribute feature learning.
no code implementations • 12 Jul 2022 • Colton Stearns, Davis Rempe, Jie Li, Rares Ambrus, Sergey Zakharov, Vitor Guizilini, Yanchao Yang, Leonidas J Guibas
In this work, we develop a holistic representation of traffic scenes that leverages both spatial and temporal information of the actors in the scene.
1 code implementation • 3 Jul 2022 • Chang Sun, Zili Wang, Shuyou Zhang, Taotao Zhou, Jie Li, Jianrong Tan
To address this issue, a digital-twin-enhanced (DT-enhanced) metal tube bending forming real-time prediction method based on multi-source-input multi-task learning (MTL) is proposed.
1 code implementation • 16 Jun 2022 • Adam W. Harley, Zhaoyuan Fang, Jie Li, Rares Ambrus, Katerina Fragkiadaki
Building 3D perception systems for autonomous vehicles that do not rely on high-density LiDAR is a critical research problem because of the expense of LiDAR systems compared to cameras and other sensors.
Autonomous Vehicles
Bird's-Eye View Semantic Segmentation
+1
no code implementations • 7 Jun 2022 • Yifei Sun, Jie Li, Tong Zhang, Rui Wang, Xiaohui Peng, Tony Xiao Han, Haisheng Tan
At the end, we show that the reconstructed room layout can be utilized to locate a mobile device according to its AoA spectrum, even with single access point.
1 code implementation • Proceedings of the ACM Web Conference 2022 • Jie Li, Yongli Ren, Ke Deng
To fill this gap, we propose a Generative Adversarial Networks (GANs) based learning algorithm FairGAN mapping the exposure fairness issue to the problem of negative preferences in implicit feedback data.
1 code implementation • 4 Apr 2022 • Pavel Tokmakov, Allan Jabri, Jie Li, Adrien Gaidon
This paper proposes a self-supervised objective for learning representations that localize objects under occlusion - a property known as object permanence.
no code implementations • 28 Mar 2022 • Jie Li, Chao Yu, Yan Luo, Yifei Sun, Rui Wang
Relying on the passive sensing system, a dataset of received signals, where three types of hand gestures are sensed, is collected by using Line-of-Sight (LoS) and Non-Line-of-Sight (NLoS) paths as the reference channel respectively.
no code implementations • 24 Mar 2022 • Jiawei Sun, Ruoxin Chen, Jie Li, Chentao Wu, Yue Ding, Junchi Yan
Graph Contrastive Learning (GCL) has shown promising performance in graph representation learning (GRL) without the supervision of manual annotations.
1 code implementation • 29 Jan 2022 • Jie Li, Ling Han, Cong Zhang, Qiyue Li, Zhi Liu
Most of the current prediction methods combining saliency detection and FoV information neither take into account that the distortion of projected 360-degree videos can invalidate the weight sharing of traditional convolutional networks, nor do they adequately consider the difficulty of obtaining complete multi-user FoV information, which degrades the prediction performance.
no code implementations • CVPR 2022 • Yuhang Zhang, Xiaopeng Zhang, Lingxi Xie, Jie Li, Robert C. Qiu, Hengtong Hu, Qi Tian
The Yes query is treated as positive pairs of the queried category for contrastive pulling, while the No query is treated as hard negative pairs for contrastive repelling.
1 code implementation • 10 Dec 2021 • Shuman Fang, Jie Li, Xianming Lin, Rongrong Ji
By treating the attack of both specific data and a modified model as a task, we expect the adversarial perturbations to adopt enough tasks for generalization.
1 code implementation • 8 Dec 2021 • Qi Song, Jie Li, Chenghong Li, Hao Guo, Rui Huang
Recent non-local self-attention methods have proven to be effective in capturing long-range dependencies for semantic segmentation.
1 code implementation • 4 Dec 2021 • Feng Xu, Chuang Zhu, Wenqi Tang, Ying Wang, Yu Zhang, Jie Li, Hongchuan Jiang, Zhongyue Shi, Jun Liu, Mulan Jin
Conclusion: Our study provides a novel DL-based biomarker on primary tumor CNB slides to predict the metastatic status of ALN preoperatively for patients with EBC.
1 code implementation • 16 Nov 2021 • Yuanfei Huang, Jie Li, Yanting Hu, Xinbo Gao, Hua Huang
Recently, deep-learning-based super-resolution methods have achieved excellent performances, but mainly focus on training a single generalized deep network by feeding numerous samples.
no code implementations • 27 Oct 2021 • Qi Song, Jie Li, Hao Guo, Rui Huang
Without any external training data, our proposed Denoised NL can achieve the state-of-the-art performance of 83. 5\% and 46. 69\% mIoU on Cityscapes and ADE20K, respectively.
no code implementations • 25 Oct 2021 • Dehao Huang, Jintao Cheng, Rui Fan, Zhihao Su, Qiongxiong Ma, Jie Li
Therefore, it is crucial to study a robust bone marrow cell detection algorithm for a quantitative automatic analysis system.
no code implementations • 5 Oct 2021 • Jie Li, Oufan Zhang, Yingze Wang, Kunyang Sun, Xingyi Guan, Dorian Bagni, Mojtaba Haghighatlari, Fiona L. Kearns, Conor Parks, Rommie E. Amaro, Teresa Head-Gordon
The viability of a new drug molecule is a time and resource intensive task that makes computer-aided assessments a vital approach to rapid drug discovery.
1 code implementation • 27 Sep 2021 • Bowen Li, Lixin Fan, Hanlin Gu, Jie Li, Qiang Yang
To address these risks, the ownership verification of federated learning models is a prerequisite that protects federated learning model intellectual property rights (IPR) i. e., FedIPR.
no code implementations • 6 Sep 2021 • Qiuming Zhu, Fei Bai, Minghui Pang, Jie Li, Weizhi Zhong, Xiaomin Chen, Kai Mao
Line-of-sight (LoS) path is essential for the reliability of air-to-ground (A2G) communications, but the existence of LoS path is difficult to predict due to random obstacles on the ground.
no code implementations • 4 Sep 2021 • Jingyuan Yang, Jie Li, Xiumei Wang, Yuxuan Ding, Xinbo Gao
Then, we design three specific networks, i. e., Global-Net, Semantic-Net and Expression-Net, to extract distinct emotional features from different stimuli simultaneously.
no code implementations • 1 Sep 2021 • Menghui Jiang, Huanfeng Shen, Jie Li, Liangpei Zhang
Images from many remote sensing satellites, including MODIS, Landsat-8, Sentinel-1, and Sentinel-2, are utilized in the experiments.
no code implementations • ICCV 2021 • Zhijian Liu, Simon Stent, Jie Li, John Gideon, Song Han
Computer vision tasks such as object detection and semantic/instance segmentation rely on the painstaking annotation of large training datasets.
no code implementations • 13 Aug 2021 • Huanfeng Shen, Menghui Jiang, Jie Li, Chenxia Zhou, Qiangqiang Yuan, Liangpei Zhang
In this paper, we systematically investigate the coupling of model-driven and data-driven methods, which has rarely been considered in the remote sensing image restoration and fusion communities.
2 code implementations • ICCV 2021 • Dennis Park, Rares Ambrus, Vitor Guizilini, Jie Li, Adrien Gaidon
Recent progress in 3D object detection from single images leverages monocular depth estimation as a way to produce 3D pointclouds, turning cameras into pseudo-lidar sensors.
Ranked #1 on
Monocular 3D Object Detection
on KITTI Pedestrian Moderate
(using extra training data)
no code implementations • 31 Jul 2021 • Fengping Wang, Jie Li, Siqi Zhang, Chun Qi, Yun Zhang, Danmin Miao
Micro-expressions are spontaneous, unconscious facial movements that show people's true inner emotions and have great potential in related fields of psychological testing.
no code implementations • 27 Jul 2021 • Jie Li, Sheng Zhang, Kai Han, Xia Yuan, Chunxia Zhao, Yu Liu
UGV-KPNet is computationally efficient with a small number of parameters and provides pixel-level accurate keypoints detection results in real-time.
no code implementations • 21 Jul 2021 • Taichu Shi, Yang Qi, Weipeng Zhang, Paul R. Prucnal, Jie Li, Ben Wu
The ultra-fast optical pulse functions as a tweezer that collects samples of the signals at very low sampling rates, and each sample is short enough to maintain the statistical properties of the signals.
no code implementations • 20 Jul 2021 • Guoliang Li, Shuai Wang, Jie Li, Rui Wang, Fan Liu, Xiaohui Peng, Tony Xiao Han, Chengzhong Xu
Characterizing the sensing and communication performance tradeoff in integrated sensing and communication (ISAC) systems is challenging in the applications of learning-based human motion recognition.
no code implementations • 18 Jul 2021 • Liupeng Lin, Jie Li, Huanfeng Shen, Lingli Zhao, Qiangqiang Yuan, Xinghua Li
The data fusion technology aims to aggregate the characteristics of different data and obtain products with multiple data advantages.
no code implementations • 29 Jun 2021 • Jie Li, Laiyan Ding, Rui Huang
3D semantic scene completion and 2D semantic segmentation are two tightly correlated tasks that are both essential for indoor scene understanding, because they predict the same semantic classes, using positively correlated high-level features.
no code implementations • CVPR 2021 • Jingyuan Yang, Jie Li, Leida Li, Xiumei Wang, Xinbo Gao
Visual Emotion Analysis (VEA) has attracted increasing attention recently with the prevalence of sharing images on social networks.
no code implementations • CVPR 2021 • Zheng Hui, Jie Li, Xiumei Wang, Xinbo Gao
Instead of considering iterative strategy, we make the blur kernel predictor trainable in the whole blind SR model, in which AMNet is well-trained.
no code implementations • CVPR 2021 • Jingfan Guo, Jie Li, Rahul Narain, Hyun Soo Park
Inspired by the theory of optimal control, we optimize the body states such that the simulated cloth motion is matched to the point cloud measurements, and the analytic gradient of the simulator is back-propagated to update the body states.
no code implementations • CVPR 2021 • Tommi Kerola, Jie Li, Atsushi Kanehira, Yasunori Kudo, Alexis Vallet, Adrien Gaidon
We use a hierarchical Lovasz hinge loss to learn a low-dimensional embedding space structured into a unified semantic and instance hierarchy without requiring separate network branches or object proposals.
2 code implementations • 19 Jun 2021 • Jie Li, Lizhong Yao
In this paper, we introduce a new acoustic leakage dataset of gas pipelines, called as GPLA-12, which has 12 categories over 684 training/testing acoustic signals.
no code implementations • 8 Jun 2021 • Tommi Kerola, Jie Li, Atsushi Kanehira, Yasunori Kudo, Alexis Vallet, Adrien Gaidon
We use a hierarchical Lov\'asz hinge loss to learn a low-dimensional embedding space structured into a unified semantic and instance hierarchy without requiring separate network branches or object proposals.
no code implementations • 16 May 2021 • Yuhang Zhang, Xiaopeng Zhang, Robert. C. Qiu, Jie Li, Haohang Xu, Qi Tian
Semi-supervised learning acts as an effective way to leverage massive unlabeled data.
no code implementations • NeurIPS 2021 • Yixu Wang, Jie Li, Hong Liu, Yan Wang, Yongjian Wu, Feiyue Huang, Rongrong Ji
We argue this is due to the lack of rich information in the probability prediction and the overfitting caused by hard labels.
no code implementations • 24 Apr 2021 • Peng Xie, Wenyuan Tao, Jie Li, Wentao Huang, Siming Chen
The core of the approach is a subset embedding network (SEN) that represents a group of subsets as uniformly-formatted embeddings.
no code implementations • 21 Apr 2021 • Guoliang Li, Shuai Wang, Jie Li, Rui Wang, Xiaohui Peng, Tony Xiao Han
Although wireless channel models can be adopted for dataset generation, current channel models are mostly designed for communication rather than sensing.
2 code implementations • CVPR 2021 • Tianwei Lin, Zhuoqi Ma, Fu Li, Dongliang He, Xin Li, Errui Ding, Nannan Wang, Jie Li, Xinbo Gao
Inspired by the common painting process of drawing a draft and revising the details, we introduce a novel feed-forward method named Laplacian Pyramid Network (LapStyle).
no code implementations • ICCV 2021 • Vitor Guizilini, Jie Li, Rares Ambrus, Adrien Gaidon
Simulators can efficiently generate large amounts of labeled synthetic data with perfect supervision for hard-to-label tasks like semantic segmentation.
1 code implementation • 29 Mar 2021 • Yuanfei Huang, Jie Li, Yanting Hu, Xinbo Gao, Hua Huang
Being extremely dependent on iterative estimation of the degradation prior or optimization of the model from scratch, the existing blind super-resolution (SR) methods are generally time-consuming and less effective, as the estimation of degradation proceeds from a blind initialization and lacks interpretable degradation priors.
1 code implementation • ICCV 2021 • Pavel Tokmakov, Jie Li, Wolfram Burgard, Adrien Gaidon
In this work, we introduce an end-to-end trainable approach for joint object detection and tracking that is capable of such reasoning.
no code implementations • 9 Mar 2021 • Kaiming Tang, Shengbo Eben Li, Yuming Yin, Yang Guan, Jingliang Duan, Wenhan Cao, Jie Li
The equivalence holds given certain conditions about initial state distributions and policy formats, in which the system state is the estimation error, control input is the filter gain, and control objective function is the accumulated estimation error.
2 code implementations • 23 Feb 2021 • Yang Guan, Jingliang Duan, Shengbo Eben Li, Jie Li, Jianyu Chen, Bo Cheng
Formally, MPG is constructed as a weighted average of the data-driven and model-driven PGs, where the former is the derivative of the learned Q-value function, and the latter is that of the model-predictive return.
no code implementations • 9 Feb 2021 • Yutong Jin, Jie Li, Xinyu Wang, Peiyao Li, Jinjiang Guo, Junfeng Wu, Dawei Leng, Lurong Pan
The novel coronavirus (SARS-CoV-2) which causes COVID-19 is an ongoing pandemic.
1 code implementation • 8 Feb 2021 • Dawei Leng, Jinjiang Guo, Lurong Pan, Jie Li, Xinyu Wang
Graph neural networks are emerging as continuation of deep learning success w. r. t.
no code implementations • 7 Feb 2021 • Jie Li, Yu Hu
In this paper, we put forward a novel density-oriented PointNet (DPointNet) for 3D object detection in point clouds, in which the density of points increases layer by layer.
no code implementations • 4 Feb 2021 • Dong Chu, Huanfeng Shen, Xiaobin Guan, Jing M. Chen, Xinghua Li, Jie Li, Liangpei Zhang
The applications of Normalized Difference Vegetation Index (NDVI) time-series data are inevitably hampered by cloud-induced gaps and noise.
no code implementations • 28 Jan 2021 • Jinjiang Guo, Jie Li, Dawei Leng, Lurong Pan
Multi-scale biomedical knowledge networks are expanding with emerging experimental technologies that generates multi-scale biomedical big data.
1 code implementation • 10 Jan 2021 • Zheming Zuo, Jie Li, Han Xu, Noura Al Moubayed
Disruptive technologies provides unparalleled opportunities to contribute to the identifications of many aspects in pervasive healthcare, from the adoption of the Internet of Things through to Machine Learning (ML) techniques.
1 code implementation • ICCV 2021 • Jie Li, Rongrong Ji, Peixian Chen, Baochang Zhang, Xiaopeng Hong, Ruixin Zhang, Shaoxin Li, Jilin Li, Feiyue Huang, Yongjian Wu
A common practice is to start from a large perturbation and then iteratively reduce it with a deterministic direction and a random one while keeping it adversarial.
1 code implementation • 26 Dec 2020 • Hsu-kuang Chiu, Jie Li, Rares Ambrus, Jeannette Bohg
Second, we propose to learn a metric that combines the Mahalanobis and feature distances when comparing a track and a new detection in data association.
Ranked #3 on
3D Pedestrian Tracking
on nuScenes validation set
no code implementations • 23 Dec 2020 • Jie Li, Binglin Li, Min Gao
Recently, skeleton-based approaches have achieved rapid progress on the basis of great success in skeleton representation.
no code implementations • 23 Dec 2020 • Jie Li, Ruqian Wu
A new multifunctional 2D material is theoretically predicted based on systematic ab-initio calculations and model simulations for the honeycomb lattice of endohedral fullerene W@C28 molecules.
Materials Science Computational Physics
no code implementations • 21 Dec 2020 • Matthijs H. J. de Jong, Jie Li, Claus Gärtner, Richard A. Norte, Simon Gröblacher
Studying the interplay between multiple coupled mechanical resonators is a promising new direction in the field of optomechanics.
Optics Mesoscale and Nanoscale Physics
no code implementations • 17 Dec 2020 • Yuanbin Jin, Jiangwei Yan, Shah Jee Rahman, Jie Li, Xudong Yu, Jing Zhang
We measure a highest rotation frequency about 4. 3 GHz of the trapped nanoparticle without feedback cooling and a 6 GHz rotation with feedback cooling, which is the fastest mechanical rotation ever reported to date.
Optics Mesoscale and Nanoscale Physics Quantum Physics
1 code implementation • 14 Dec 2020 • Jie Li, Vasileios Giotsas, Shi Zhou
Our work provides insights into the latest deployment of M-BGP in a major ISP network and it highlights the characteristics and effectiveness of M-BGP as a means to realize load sharing.
Networking and Internet Architecture
2 code implementations • 7 Dec 2020 • Xu Yan, Jiantao Gao, Jie Li, Ruimao Zhang, Zhen Li, Rui Huang, Shuguang Cui
In practice, an initial semantic segmentation (SS) of a single sweep point cloud can be achieved by any appealing network and then flows into the semantic scene completion (SSC) module as the input.
Ranked #4 on
3D Semantic Scene Completion
on SemanticKITTI
3D Semantic Scene Completion from a single RGB image
3D Semantic Segmentation
+3
no code implementations • 27 Nov 2020 • Yi Gu, Jie Li, Yuting Gao, Ruoxin Chen, Chentao Wu, Feiyang Cai, Chao Wang, Zirui Zhang
Neural networks are susceptible to catastrophic forgetting.
no code implementations • 19 Nov 2020 • Jiang He, Jie Li, Qiangqiang Yuan, Huanfeng Shen, Liangpei Zhang
Hyperspectral images are crucial for many research works.
no code implementations • 11 Nov 2020 • Yi Gu, Yuting Gao, Jie Li, Chentao Wu, Weijia Jia
Due to the uncertainty in the distortion variation, restoring distorted images caused by liquify filter is a challenging task.
1 code implementation • 28 Oct 2020 • Steve Bryson, Michelle Kunimoto, Ravi K. Kopparapu, Jeffrey L. Coughlin, William J. Borucki, David Koch, Victor Silva Aguirre, Christopher Allen, Geert Barentsen, Natalie. M. Batalha, Travis Berger, Alan Boss, Lars A. Buchhave, Christopher J. Burke, Douglas A. Caldwell, Jennifer R. Campbell, Joseph Catanzarite, Hema Chandrasekharan, William J. Chaplin, Jessie L. Christiansen, Jorgen Christensen-Dalsgaard, David R. Ciardi, Bruce D. Clarke, William D. Cochran, Jessie L. Dotson, Laurance R. Doyle, Eduardo Seperuelo Duarte, Edward W. Dunham, Andrea K. Dupree, Michael Endl, James L. Fanson, Eric B. Ford, Maura Fujieh, Thomas N. Gautier III, John C. Geary, Ronald L Gilliland, Forrest R. Girouard, Alan Gould, Michael R. Haas, Christopher E. Henze, Matthew J. Holman, Andrew Howard, Steve B. Howell, Daniel Huber, Roger C. Hunter, Jon M. Jenkins, Hans Kjeldsen, Jeffery Kolodziejczak, Kipp Larson, David W. Latham, Jie Li, Savita Mathur, Soren Meibom, Chris Middour, Robert L. Morris, Timothy D. Morton, Fergal Mullally, Susan E. Mullally, David Pletcher, Andrej Prsa, Samuel N. Quinn, Elisa V. Quintana, Darin Ragozzine, Solange V. Ramirez, Dwight T. Sanderfer, Dimitar Sasselov, Shawn E. Seader, Megan Shabram, Avi Shporer, Jeffrey C. Smith, Jason H. Steffen, Martin Still, Guillermo Torres, John Troeltzsch, Joseph D. Twicken, Akm Kamal Uddin, Jeffrey E. Van Cleve, Janice Voss, Lauren Weiss, William F. Welsh, Bill Wohler, Khadeejah A Zamudio
We present occurrence rates for rocky planets in the habitable zones (HZ) of main-sequence dwarf stars based on the Kepler DR25 planet candidate catalog and Gaia-based stellar properties.
Earth and Planetary Astrophysics Solar and Stellar Astrophysics
1 code implementation • 28 Sep 2020 • Yuanfei Huang, Jie Li, Xinbo Gao, Yanting Hu, Wen Lu
To solve them, we propose a purposeful and interpretable detail-fidelity attention network to progressively process these smoothes and details in divide-and-conquer manner, which is a novel and specific prospect of image super-resolution for the purpose on improving the detail fidelity, instead of blindly designing or employing the deep CNNs architectures for merely feature representation in local receptive fields.
no code implementations • 18 Sep 2020 • Ruoxin Chen, Jie Li, Chentao Wu, Bin Sheng, Ping Li
Random selection based defenses can achieve certified robustness by averaging the classifiers' predictions on the sub-datasets sampled from the training set.
no code implementations • 11 Sep 2020 • Jie Li, Yu Hu
We present an improved version of PointRCNN for 3D object detection, in which a multi-branch backbone network is adopted to handle the non-uniform density of point clouds.
no code implementations • 11 Sep 2020 • Ji-Yue Wang, Pei Zhang, Wen-feng Pang, Jie Li
The experiment results confirm that the TC can help LsrKD and MrKD to boost training, especially on the networks they are failed.
no code implementations • 7 Sep 2020 • Xi Gu, Lingbin Kong, Zhicheng Wang, Jie Li, Zhaohui Yu, Gang Wei
On the DOTA dataset, CenterFPANet mAP is 64. 00%, and FPS is 22. 2, which is close to the accuracy of the anchor-based methods currently used and much faster than them.
3 code implementations • 21 Aug 2020 • Jiaming Han, Jian Ding, Jie Li, Gui-Song Xia
However most of existing methods rely on heuristically defined anchors with different scales, angles and aspect ratios and usually suffer from severe misalignment between anchor boxes and axis-aligned convolutional features, which leads to the common inconsistency between the classification score and localization accuracy.
Ranked #26 on
Object Detection In Aerial Images
on DOTA
(using extra training data)
no code implementations • 3 Aug 2020 • Kuan-Hui Lee, Matthew Kliemann, Adrien Gaidon, Jie Li, Chao Fang, Sudeep Pillai, Wolfram Burgard
In autonomous driving, accurately estimating the state of surrounding obstacles is critical for safe and robust path planning.
no code implementations • 14 Jul 2020 • Jie Li, Lei Gu, Ruqian Wu
Nanomagnets with giant magnetic anisotropy energy and long coherence time are desired for various technological innovations such as quantum information procession and storage.
Materials Science Computational Physics
no code implementations • 14 Jul 2020 • Jie Li, Shengbo Eben Li, Yang Guan, Jingliang Duan, Wenyu Li, Yuming Yin
The simulation results show that the TPI algorithm can converge to the optimal solution for the linear plant, and has high resistance to disturbances for the nonlinear plant.
no code implementations • 3 Jul 2020 • Feifei Huang, Jie Li, Xuelin Zhu
Deep convolution neural network has attracted many attentions in large-scale visual classification task, and achieves significant performance improvement compared to traditional visual analysis methods.
no code implementations • 3 Jul 2020 • Xinpeng Ding, Nannan Wang, Xinbo Gao, Jie Li, Xiaoyu Wang, Tongliang Liu
Specifically, we devise a partial segment loss regarded as a loss sampling to learn integral action parts from labeled segments.
no code implementations • 25 Jun 2020 • Zhenxi Zhang, Chunna Tian, Jie Li, Zhusi Zhong, Zhicheng Jiao, Xinbo Gao
Further, we propose a context encoding module to utilize the global predictor from the error map to enhance the feature representation and regularize the networks.
no code implementations • 25 May 2020 • Bing Cao, Nannan Wang, Xinbo Gao, Jie Li, Zhifeng Li
Heterogeneous face recognition (HFR) refers to matching face images acquired from different domains with wide applications in security scenarios.
1 code implementation • CVPR 2020 • Jie Li, Rongrong Ji, Hong Liu, Jianzhuang Liu, Bineng Zhong, Cheng Deng, Qi Tian
For reducing the solution space, we first model the adversarial perturbation optimization problem as a process of recovering frequency-sparse perturbations with compressed sensing, under the setting that random noise in the low-frequency space is more likely to be adversarial.
1 code implementation • CVPR 2020 • Jie Li, Kai Han, Peng Wang, Yu Liu, Xia Yuan
In contrast to the standard 3D convolution that is limited to a fixed 3D receptive field, our module is capable of modeling the dimensional anisotropy voxel-wisely.
no code implementations • 28 Feb 2020 • Jie Huang, Cheng-Xiang Wang, Lu Bai, Jian Sun, Yang Yang, Jie Li, Olav Tirkkonen, Ming-Tuo Zhou
This paper investigates various applications of big data analytics, especially machine learning algorithms in wireless communications and channel modeling.
1 code implementation • ICLR 2020 • Vitor Guizilini, Rui Hou, Jie Li, Rares Ambrus, Adrien Gaidon
Instead of using semantic labels and proxy losses in a multi-task approach, we propose a new architecture leveraging fixed pretrained semantic segmentation networks to guide self-supervised representation learning via pixel-adaptive convolutions.
no code implementations • 17 Feb 2020 • Yu Liu, Jie Li, Qingsen Yan, Xia Yuan, Chunxia Zhao, Ian Reid, Cesar Cadena
This paper tackles the problem of data fusion in the semantic scene completion (SSC) task, which can simultaneously deal with semantic labeling and scene completion.
Ranked #15 on
3D Semantic Scene Completion
on NYUv2
no code implementations • 16 Feb 2020 • Jingwei Xin, Nannan Wang, Xinrui Jiang, Jie Li, Xinbo Gao, Zhifeng Li
In the SR processing, we first generated a group of FACs from the input LR face, and then reconstructed the HR face from this group of FACs.
no code implementations • 15 Feb 2020 • Jingwei Xin, Nannan Wang, Jie Li, Xinbo Gao, Zhifeng Li
Current state-of-the-art CNN methods usually treat the VSR problem as a large number of separate multi-frame super-resolution tasks, at which a batch of low resolution (LR) frames is utilized to generate a single high resolution (HR) frame, and running a slide window to select LR frames over the entire video would obtain a series of HR frames.
3 code implementations • 7 Feb 2020 • Zheng Hui, Jie Li, Xiumei Wang, Xinbo Gao
Besides, we devise a geometrical alignment constraint item to compensate for the pixel-based distance between prediction features and ground-truth ones.
1 code implementation • 29 Jan 2020 • Yu Liu, Jie Li, Xia Yuan, Chunxia Zhao, Roland Siegwart, Ian Reid, Cesar Cadena
We propose PALNet, a novel hybrid network for SSC based on single depth.
3 code implementations • 16 Jan 2020 • Hsu-kuang Chiu, Antonio Prioletti, Jie Li, Jeannette Bohg
Our method estimates the object states by adopting a Kalman Filter.
no code implementations • MDPI Remote Sensing 2020 • Jianhao Gao, Qiangqiang Yuan, Jie Li, Hai Zhang, Xin Su
The approach can be roughly divided into two steps: in the first step, a specially designed convolutional neural network (CNN) translates the synthetic aperture radar (SAR) images into simulated optical images in an object-to-object manner; in the second step, the simulated optical image, together with the SAR image and the optical image corrupted by clouds, is fused to reconstruct the corrupted area by a generative adversarial network (GAN) with a particular loss function.
Ranked #8 on
Cloud Removal
on SEN12MS-CR
no code implementations • 2 Jan 2020 • Zhiyun Fan, Jie Li, Shiyu Zhou, Bo Xu
We investigate different factors of SAM.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
no code implementations • 23 Dec 2019 • Yang Guan, Shengbo Eben Li, Jingliang Duan, Jie Li, Yangang Ren, Qi Sun, Bo Cheng
Reinforcement learning (RL) algorithms have been successfully applied to a range of challenging sequential decision making and control tasks.
no code implementations • CVPR 2020 • Rui Hou, Jie Li, Arjun Bhargava, Allan Raventos, Vitor Guizilini, Chao Fang, Jerome Lynch, Adrien Gaidon
Panoptic segmentation is a complex full scene parsing task requiring simultaneous instance and semantic segmentation at high resolution.
1 code implementation • 19 Nov 2019 • Kangfu Mei, Juncheng Li, Jiajie Zhang, Hao-Yu Wu, Jie Li, Rui Huang
However, plenty of studies have shown that global information is crucial for image restoration tasks like image demosaicing and enhancing.
1 code implementation • 18 Nov 2019 • Andreas Lugmayr, Martin Danelljan, Radu Timofte, Manuel Fritsche, Shuhang Gu, Kuldeep Purohit, Praveen Kandula, Maitreya Suin, A. N. Rajagopalan, Nam Hyung Joon, Yu Seung Won, Guisik Kim, Dokyeong Kwon, Chih-Chung Hsu, Chia-Hsiang Lin, Yuanfei Huang, Xiaopeng Sun, Wen Lu, Jie Li, Xinbo Gao, Sefi Bell-Kligler
For training, only one set of source input images is therefore provided in the challenge.
1 code implementation • 22 Oct 2019 • Yalong Liu, Jie Li, Miaomiao Wang, Zhicheng Jiao, Jian Yang, Xianjun Li
In this paper, a novel spatiotemporal transformation deep learning method called Trident Segmentation CNN (TS-CNN) is proposed to segment PWML in MR images.
no code implementations • 4 Oct 2019 • Vitor Guizilini, Jie Li, Rares Ambrus, Sudeep Pillai, Adrien Gaidon
Dense depth estimation from a single image is a key problem in computer vision, with exciting applications in a multitude of robotic tasks.