no code implementations • ECCV 2020 • Lezi Wang, Dong Liu, Rohit Puri, Dimitris N. Metaxas
We introduce a novel ranking network that utilizes the Co-Attention between movies and trailers as guidance to generate the training pairs, where the moments highly corrected with trailers are expected to be scored higher than the uncorrelated moments.
no code implementations • ECCV 2020 • Jiayong Peng, Zhiwei Xiong, Xin Huang, Zheng-Ping Li, Dong Liu, Feihu Xu
Photon-efficient imaging has enabled a number of applications relying on single-photon sensors that can capture a 3D image with as few as one photon per pixel.
no code implementations • 1 Feb 2025 • Runxiong Wu, Dong Liu, Xueqin Wang, Andi Wang
This discovery reveals key connections between the two classes of algorithms: CoCoA can be interpreted as a special case of proximal ADMM for solving the dual problem, while consensus ADMM is closely related to a proximal ADMM algorithm.
no code implementations • 30 Jan 2025 • Niklas Freymuth, Dong Liu, Thomas Ricatte, Saab Mansour
Dense retrieval methods typically target unstructured text data represented as flat strings.
1 code implementation • 22 Jan 2025 • Bohao Yang, Yingji Zhang, Dong Liu, André Freitas, Chenghua Lin
While multimodal large language models (MLLMs) enable direct visual processing, they face limitations in handling scientific tables due to fixed input image resolutions and insufficient numerical reasoning capabilities.
no code implementations • 21 Jan 2025 • Haotian Zhang, Dong Liu
Lossy image coding is the art of computing that is principally bounded by the image's rate-distortion function.
no code implementations • 13 Jan 2025 • Dong Liu, Esther Lopez Ramos
Semantic retrieval (also known as dense retrieval) based on textual data has been extensively studied for both web search and product search application fields, where the relevance of a query and a potential target document is computed by their dense vector representation comparison.
1 code implementation • 6 Jan 2025 • YiFan Li, Zhixin Lai, Wentao Bao, Zhen Tan, Anh Dao, Kewei Sui, Jiayi Shen, Dong Liu, Huan Liu, Yu Kong
Visual-language models (VLM) have emerged as a powerful tool for learning a unified embedding space for vision and language.
no code implementations • 20 Dec 2024 • Yiheng Jiang, Haotian Zhang, Li Li, Dong Liu, Zhu Li
In this paper, motivated by the recent success of learned image compression, we propose a new framework that uses sparse point clouds to assist in learned image compression in the autonomous driving scenario.
no code implementations • 9 Dec 2024 • Yong He, Zeyu Li, Dong Liu, Kangxiang Qin, Jiahui Xie
We propose to transfer representational knowledge from multiple sources to a target noisy matrix completion task by aggregating singular subspaces information.
no code implementations • 28 Nov 2024 • Haotian Zhang, Li Li, Dong Liu
Probabilistic models with more parameters, such as the Gaussian mixture models, can fit the distribution of latent variables more precisely, but the corresponding complexity will also be higher.
no code implementations • 24 Nov 2024 • Lianghao Tan, Xiaoyi Liu, Dong Liu, Shubing Liu, Weixi Wu, Huangqi Jiang
To improve the convergence speed and optimization accuracy of the Dung Beetle Optimizer (DBO), this paper proposes an improved algorithm based on circle mapping and longitudinal-horizontal crossover strategy (CICRDBO).
no code implementations • 23 Nov 2024 • Menglin Zhang, Xin Luo, Yunwei Lan, Chang Liu, Rui Li, Kaidong Zhang, Ganlin Yang, Dong Liu
The limitations manifest in two critical aspects: the inadequate capture of geometric information by pretrained diffusion models and the suboptimal guidance provided by existing Score Distillation Sampling (SDS) methods.
1 code implementation • 17 Nov 2024 • Chang Liu, Rui Li, Kaidong Zhang, Yunwei Lan, Dong Liu
Recent advancements of generative AI have significantly promoted content creation and editing, where prevailing studies further extend this exciting progress to video editing.
no code implementations • 17 Sep 2024 • Tianyu Zhang, Haotian Zhang, Yuqi Li, Li Li, Dong Liu
Learned image compression (LIC) has achieved state-of-the-art rate-distortion performance, deemed promising for next-generation image compression techniques.
no code implementations • 13 Sep 2024 • Zhuoyuan Li, Junqi Liao, Chuanbo Tang, Haotian Zhang, Yuqi Li, Yifan Bian, Xihua Sheng, Xinmin Feng, Yao Li, Changsheng Gao, Li Li, Dong Liu, Feng Wu
Image/video coding has been a remarkable research area for both academia and industry for many years.
no code implementations • 6 Sep 2024 • Bowen Tong, Junwu Wang, Dong Liu
Electrical Impedance Tomography (EIT) is a non-invasive imaging technique that reconstructs conductivity distributions within a body from boundary measurements.
1 code implementation • 3 Sep 2024 • Dong Liu, Yanxuan Yu, Zhixin Lai, Yite Wang, Jing Wu, Zhongwei Wan, Sina Alinejad, Benjamin Lengerich, Ying Nian Wu
This paper focuses on modern efficient training and inference technologies on foundation models and illustrates them from two perspectives: model and system design.
no code implementations • 16 Aug 2024 • Xihua Sheng, Li Li, Dong Liu, Shiqi Wang
In this paper, we introduce a bi-directional deep contextual video compression scheme tailored for B-frames, termed DCVC-B, to improve the compression performance of deep B-frame coding.
no code implementations • 28 Jul 2024 • Xihua Sheng, Chuanbo Tang, Li Li, Dong Liu, Feng Wu
Based on a small baseline model, we gradually scale up the model sizes of its different coding parts, including the motion encoder-decoder, motion entropy model, contextual encoder-decoder, contextual entropy model, and temporal context mining module, and analyze the influence of model sizes on video compression performance.
no code implementations • 16 Jul 2024 • Zhuoyuan Li, Yao Li, Chuanbo Tang, Li Li, Dong Liu, Feng Wu
To address these issues, we introduce a uniformly accelerated motion model (UAMM) to exploit motion-related elements (velocity, acceleration) of moving objects between the video frames, and further combine them to assist the inter prediction methods to handle the variable motion in the temporal domain.
no code implementations • 15 Jul 2024 • Zhuoyuan Li, Jiacheng Li, Yao Li, Li Li, Dong Liu, Feng Wu
Recently, neural network-based in-loop filtering methods achieve remarkable coding gains beyond the capability of advanced video coding standards, which becomes a powerful coding tool candidate for future video coding standards.
no code implementations • 10 Jul 2024 • Ganlin Yang, Kaidong Zhang, Jingjing Fu, Dong Liu
Aliasing artifacts in renderings produced by Neural Radiance Field (NeRF) is a long-standing but complex issue in the field of 3D implicit representation, which arises from a multitude of intricate causes and was mitigated by designing more advanced but complex scene parameterization methods before.
1 code implementation • 9 Jul 2024 • Rui Li, Dong Liu
DecoMotion explicitly decomposes video content into static scenes and dynamic objects, either of which uses a quasi-3D canonical volume to represent.
no code implementations • 29 Jun 2024 • Junqi Liao, Yao Li, Zhuoyuan Li, Li Li, Dong Liu
To meet the real-time analysis requirements of video streaming applications, we propose an inter-relation-aware video complexity analyzer (IVCA) as an extension to VCA.
1 code implementation • 28 Jun 2024 • Dong Liu, Kaiser Pister
Currently, there are many quantization methods appeared for LLM quantization, yet few are user-friendly and easy to be deployed locally.
1 code implementation • 26 Jun 2024 • Dong Liu, Yanxuan Yu
MT2ST is designed to enhance training efficiency and accuracy in word embedding tasks, showcasing its value as a practical application of efficient ML.
1 code implementation • 25 Jun 2024 • Dong Liu, Meng Jiang
These methods address the limitations of static node representations and fixed aggregation schemes in traditional GNNs, offering a more nuanced approach to modeling complex and dynamic graph topologies.
1 code implementation • 25 Jun 2024 • Bohao Yang, Dong Liu, Chenghao Xiao, Kun Zhao, Chen Tang, Chao Li, Lin Yuan, Guang Yang, Lanxiao Huang, Chenghua Lin
Large Language Models (LLMs) demonstrate remarkable ability to comprehend instructions and generate human-like text, enabling sophisticated agent simulation beyond basic behavior replication.
1 code implementation • 25 Jun 2024 • Dong Liu, Roger Waleffe, Meng Jiang, Shivaram Venkataraman
In our recent research, we have developed a framework called GraphSnapShot, which has been proven an useful tool for graph learning acceleration.
no code implementations • 20 Jun 2024 • Xihua Sheng, Li Li, Dong Liu, Houqiang Li
With these filters, our codec can adapt to different reference qualities, making it easier to achieve the target reconstruction quality and reduce the reconstruction error propagation.
1 code implementation • 27 May 2024 • Yinda Chen, Haoyuan Shi, Xiaoyu Liu, Te Shi, Ruobing Zhang, Dong Liu, Zhiwei Xiong, Feng Wu
Autoregressive next-token prediction is a standard pretraining method for large-scale language models, but its application to vision tasks is hindered by the non-sequential nature of image data, leading to cumulative errors.
no code implementations • 7 May 2024 • Changsheng Gao, Yiheng Jiang, Li Li, Dong Liu, Feng Wu
To maintain the feature discriminability of reconstructed features, we introduce a discrimination metric for feature compression.
1 code implementation • CVPR 2024 • Yifan Yang, Dong Liu, Shuhai Zhang, Zeshuai Deng, Zixiong Huang, Mingkui Tan
We empirically find that the high-frequency (HF) and low-frequency (LF) information from a parametric model has the potential to enhance geometry details and improve robustness to noise, respectively.
1 code implementation • 1 Apr 2024 • Bohao Yang, Kun Zhao, Chen Tang, Dong Liu, Liang Zhan, Chenghua Lin
Trainable evaluation metrics, typically trained with true positive and randomly selected negative responses, tend to assign higher scores to responses that share greater content similarity with a given context.
1 code implementation • 20 Mar 2024 • Huali Zhou, Yuke Lin, Dong Liu, Ming Li
This work aims to promote Chinese opera research in both musical and speech domains, with a primary focus on overcoming the data limitations.
no code implementations • 18 Mar 2024 • Zhuoyuan Li, Zikun Yuan, Li Li, Dong Liu, Xiaohu Tang, Feng Wu
Moreover, the segmentation mask is considered in the joint rate-distortion optimization for motion estimation and partition estimation to derive the motion vector of different regions and partition more accurately.
no code implementations • 15 Mar 2024 • Yu Du, Yu Song, Ce Guo, Xiaojing Tian, Dong Liu, Ming Cong
Due to their complex spatial structure and diverse geometric features, achieving high-precision and robust point cloud registration for complex Die Castings has been a significant challenge in the die-casting industry.
no code implementations • 9 Mar 2024 • Cunhui Dong, Haichuan Ma, Haotian Zhang, Changsheng Gao, Li Li, Dong Liu
Neural network-based image coding has been developing rapidly since its birth.
no code implementations • 29 Jan 2024 • Xihua Sheng, Li Li, Dong Liu, Houqiang Li
With the SDD-based motion model and long short-term temporal contexts fusion, our proposed learned video codec can obtain more accurate inter prediction.
no code implementations • 8 Jan 2024 • Minjie Zhu, Yichen Zhu, Jinming Li, Junjie Wen, Zhiyuan Xu, Zhengping Che, Chaomin Shen, Yaxin Peng, Dong Liu, Feifei Feng, Jian Tang
The language-conditioned robotic manipulation aims to transfer natural language instructions into executable actions, from simple pick-and-place to tasks requiring intent recognition and visual reasoning.
no code implementations • 5 Jan 2024 • Junjie Wen, Yichen Zhu, Minjie Zhu, Jinming Li, Zhiyuan Xu, Zhengping Che, Chaomin Shen, Yaxin Peng, Dong Liu, Feifei Feng, Jian Tang
Humans interpret scenes by recognizing both the identities and positions of objects in their observations.
no code implementations • 13 Dec 2023 • Zhuoyao Xin, Christopher Wu, Dong Liu, Chunming Gu, Jia Guo, Jun Hua
Image segmentation, real-value prediction, and cross-modal translation are critical challenges in medical imaging.
1 code implementation • 16 Oct 2023 • Yang Wu, Shenglong Hu, Huihui Song, Kaihua Zhang, Bo Liu, Dong Liu
To simultaneously consider the uncertainty introduced by irrelevant images and the consensus features of the remaining relevant images in the group, we designed a latent variable generator branch and CoSOD transformer branch.
no code implementations • 29 Sep 2023 • Haotian Zhang, Li Li, Dong Liu
In principle, we find two factors crucial: one is the discrepancy between the surrogate and rounding, leading to train-test mismatch; the other is gradient estimation risk due to the surrogate, which consists of bias and variance of the gradient estimation.
1 code implementation • ICCV 2023 • Rui Li, Shenglong Zhou, Dong Liu
We address the problem of learning features for establishing pixel-wise correspondences.
no code implementations • 4 Aug 2023 • Haowen Wang, Zhipeng Fan, Zhen Zhao, Zhengping Che, Zhiyuan Xu, Dong Liu, Feifei Feng, Yakun Huang, XIUQUAN QIAO, Jian Tang
We introduce a pose regression module that shares the deformation features and template codes from the fields to estimate the accurate 6D pose of each object in the scene.
1 code implementation • ICCV 2023 • Xin Luo, Yunan Zhu, Shunxin Xu, Dong Liu
We tackle this issue by examining the spectral discriminators in the context of perceptual image super-resolution (i. e., GAN-based SR), as SR image quality is susceptible to spectral changes.
Image Super-Resolution
No-Reference Image Quality Assessment
no code implementations • 11 Jul 2023 • Chuanbo Tang, Xihua Sheng, Zhuoyuan Li, Haotian Zhang, Li Li, Dong Liu
In the offline stage, we fine-tune a trained optical flow estimation network with the motion information provided by a traditional (non-deep) video compression scheme, e. g. H. 266/VVC, as we believe the motion information of H. 266/VVC achieves a better rate-distortion trade-off.
no code implementations • 19 Jun 2023 • Xihua Sheng, Li Li, Dong Liu, Houqiang Li
Such compact representations need to be decoded back to pixels before being displayed to humans and - as usual - before being enhanced/analyzed by machine vision algorithms.
1 code implementation • 7 Jun 2023 • Kaidong Zhang, Ziyang Gan, Dong Liu, Xifu Shang
For THA, it is of clinical significance to analyze the bone structure from the CT images, especially to observe the structure of the acetabulum and femoral head, before the surgical procedure.
1 code implementation • 1 Jun 2023 • Chang Liu, Shunxin Xu, Jialun Peng, Kaidong Zhang, Dong Liu
To address this problem, we propose a two-stage image inpainting method termed SketchRefiner.
no code implementations • 22 May 2023 • Hongbin Lin, Mingkui Tan, Yifan Zhang, Zhen Qiu, Shuaicheng Niu, Dong Liu, Qing Du, Yanxia Liu
To address this issue, we study a more practical SF-UDA task, termed imbalance-agnostic SF-UDA, where the class distributions of both the unseen source domain and unlabeled target domain are unknown and could be arbitrarily skewed.
1 code implementation • 19 May 2023 • Chang Liu, Rui Li, Kaidong Zhang, Xin Luo, Dong Liu
To offer more controllability for the generation process, existing studies, termed as early-constraint methods in this paper, leverage extra conditions and incorporate them into pre-trained diffusion models.
Ranked #1 on
Conditional Text-to-Image Synthesis
on COCO 2017 val
Conditional Image Generation
Conditional Text-to-Image Synthesis
1 code implementation • 26 Apr 2023 • Kaidong Zhang, Dong Liu
Different from the previous methods, SAMed is built upon the large-scale image segmentation model, Segment Anything Model (SAM), to explore the new research paradigm of customizing large-scale models for medical image segmentation.
1 code implementation • 11 Apr 2023 • Ganlin Yang, Guoqiang Wei, Zhizheng Zhang, Yan Lu, Dong Liu
Most Neural Radiance Fields (NeRFs) exhibit limited generalization capabilities, which restrict their applicability in representing multiple scenes using a single model.
2 code implementations • CVPR 2023 • Jiarui Lei, Xiaobo Hu, Yue Wang, Dong Liu
During industrial processing, unforeseen defects may arise in products due to uncontrollable factors.
Ranked #7 on
Anomaly Detection
on BTAD
(using extra training data)
2 code implementations • 24 Jan 2023 • Kaidong Zhang, Jialun Peng, Jingjing Fu, Dong Liu
Transformers have been widely used for video processing owing to the multi-head self attention (MHSA) mechanism.
Ranked #1 on
Video Inpainting
on DAVIS
(SSIM (square) metric)
no code implementations • ICCV 2023 • Tiankang Su, Huihui Song, Dong Liu, Bo Liu, Qingshan Liu
We integrate our offline training and online fine-tuning in a unified framework for unsupervised video object segmentation and dub our method Online Adversarial Self-Tuning (OAST).
no code implementations • CVPR 2023 • Yang Wu, Huihui Song, Bo Liu, Kaihua Zhang, Dong Liu
To address this issue, this paper presents a group exchange-masking (GEM) strategy for robust CoSOD model learning.
1 code implementation • CVPR 2023 • Rui Li, Dong Liu
Specifically, we firstly extract spatial features from unlabeled images via contrastive learning, and secondly enhance the features by exploiting the temporal cues in unlabeled videos via reconstructive learning.
1 code implementation • 14 Aug 2022 • Kaidong Zhang, Jingjing Fu, Dong Liu
Especially in spatial transformer, we design a dual perspective spatial MHSA, which integrates the global tokens to the window-based attention.
no code implementations • 12 Jul 2022 • Shuai Huo, Dong Liu, Li Li, Siwei Ma, Feng Wu, Wen Gao
Our idea is to provide multiple discrete starting points in the global space and optimize the local optimum around each point by numerical algorithm efficiently.
1 code implementation • CVPR 2022 • Mingxing Li, Li Hu, Zhiwei Xiong, Bang Zhang, Pan Pan, Dong Liu
In this paper, we propose a Recurrent Dynamic Embedding (RDE) to build a memory bank of constant size.
Ranked #16 on
Semi-Supervised Video Object Segmentation
on MOSE
no code implementations • CVPR 2022 • Cong Huang, Jiahao Li, Bin Li, Dong Liu, Yan Lu
The temporal features usually contain various noisy and uncorrelated information, and they may interfere with the restoration of the current frame.
no code implementations • 11 Mar 2022 • Dongmei Xue, Haichuan Ma, Li Li, Dong Liu, Zhiwei Xiong
Volumetric image compression has become an urgent task to effectively transmit and store images produced in biological research and clinical practice.
1 code implementation • 3 Feb 2022 • Mingxing Li, Shenglong Zhou, Chang Chen, Yueyi Zhang, Dong Liu, Zhiwei Xiong
Accurate retinal vessel segmentation is challenging because of the complex texture of retinal vessels and low imaging contrast.
1 code implementation • ICCV 2021 • Rui Li, Yiheng Zhang, Zhaofan Qiu, Ting Yao, Dong Liu, Tao Mei
To this end, we compose a duet of exploiting the motion for data augmentation and feature learning in the regime of contrastive learning.
1 code implementation • CVPR 2022 • Kaidong Zhang, Jingjing Fu, Dong Liu
We propose a flow completion network to align and aggregate flow features from the consecutive flow sequences based on the inertia prior.
no code implementations • 1 Dec 2021 • Xihua Sheng, Li Li, Dong Liu, Zhiwei Xiong
In this paper, we propose a Multi-Scale Graph Attention Network (MS-GAT) to remove the artifacts of point cloud attributes compressed by G-PCC.
1 code implementation • 27 Nov 2021 • Xihua Sheng, Jiahao Li, Bin Li, Li Li, Dong Liu, Yan Lu
From the stored propagated features, we propose to learn multi-scale temporal contexts, and re-fill the learned temporal contexts into the modules of our compression scheme, including the contextual encoder-decoder, the frame generator, and the temporal context encoder.
no code implementations • 28 Oct 2021 • Dong Liu, Jiankang Zhang, Jingjing Cui, Soon-Xin Ng, Robert G. Maunder, Lajos Hanzo
Furthermore, we extend the DL-aided routing algorithm to a multi-objective scenario, where we aim for simultaneously minimizing the delay, maximizing the path capacity, and maximizing the path lifetime.
no code implementations • 28 Oct 2021 • Dong Liu, Jingjing Cui, Jiankang Zhang, Chenyang Yang, Lajos Hanzo
Data packet routing in aeronautical ad-hoc networks (AANETs) is challenging due to their high-dynamic topology.
no code implementations • 28 Oct 2021 • Dong Liu, Jiankang Zhang, Jingjing Cui, Soon-Xin Ng, Robert G. Maunder, Lajos Hanzo
Current maritime communications mainly rely on satellites having meager transmission resources, hence suffering from poorer performance than modern terrestrial wireless networks.
no code implementations • 30 Sep 2021 • Haichuan Ma, Dong Liu, Cunhui Dong, Li Li, Feng Wu
However, this nature was seldom considered in previous studies on image compression, which usually chose one possible image as reconstruction, e. g. the one with the maximal a posteriori probability.
1 code implementation • ICLR 2022 • Lu Miao, Xiaolong Luo, Tianlong Chen, Wuyang Chen, Dong Liu, Zhangyang Wang
Conventional methods often require (iterative) pruning followed by re-training, which not only incurs large overhead beyond the original DNN training but also can be sensitive to retraining hyperparameters.
no code implementations • 18 Sep 2021 • Dongmei Xue, Haichuan Ma, Li Li, Dong Liu, Zhiwei Xiong
With the rapid development of whole brain imaging technology, a large number of brain images have been produced, which puts forward a great demand for efficient brain image compression methods.
1 code implementation • ICCV 2021 • Size Wu, Sheng Jin, Wentao Liu, Lei Bai, Chen Qian, Dong Liu, Wanli Ouyang
Following the top-down paradigm, we decompose the task into two stages, i. e. person localization and pose estimation.
Ranked #2 on
3D Multi-Person Pose Estimation
on Panoptic
(using extra training data)
1 code implementation • 1 Aug 2021 • Zeyuan Chen, Yifan Jiang, Dong Liu, Zhangyang Wang
We present \underline{C}oordinated \underline{E}nhancement for \underline{R}eal-world \underline{L}ow-light Noisy Images (CERL), that seamlessly integrates light enhancement and noise suppression parts into a unified and physics-grounded optimization framework.
1 code implementation • 14 Jul 2021 • Haisheng Fu, Feng Liang, Jianping Lin, Bing Li, Mohammad Akbari, Jie Liang, Guohe Zhang, Dong Liu, Chengjie Tu, Jingning Han
However, due to the vast diversity of images, it is not optimal to use one model for all images, even different regions within one image.
no code implementations • DCASE workshop 2021 • Weiqiang Yuan ∗, Qichen Han∗, Dong Liu, Xiang Li, Zhen Yang
Our solution focuses on solving two problems in automated audio captioning: data insufficiency and word selection indeterminacy.
Ranked #3 on
Audio captioning
on Clotho
(using extra training data)
1 code implementation • 1 Jul 2021 • Anubhab Ghosh, Antoine Honoré, Dong Liu, Gustav Eje Henter, Saikat Chatterjee
For a standard speech phone classification setup involving 39 phones (classes) and the TIMIT dataset, we show that the use of standard features called mel-frequency-cepstral-coeffcients (MFCCs), the proposed generative models, and the decision fusion together can achieve $86. 6\%$ accuracy by generative training only.
no code implementations • CVPR 2021 • Zhen Cheng, Zhiwei Xiong, Chang Chen, Dong Liu, Zheng-Jun Zha
To fill this gap, we propose a zero-shot learning framework for light field SR, which learns a mapping to super-resolve the reference view with examples extracted solely from the input low-resolution light field itself.
no code implementations • CVPR 2021 • Hao Wang, Zheng-Jun Zha, Liang Li, Dong Liu, Jiebo Luo
In particular, for cross-modal interaction, we interact the sentence-level query with the whole moment while interact the word-level query with content and boundary, as in a coarse-to-fine manner.
1 code implementation • CVPR 2021 • Zeyuan Chen, Yangchao Wang, Yang Yang, Dong Liu
Deep learning-based methods have achieved remarkable performance for image dehazing.
no code implementations • 7 May 2021 • Jiawei Liu, Zhipeng Huang, Kecheng Zheng, Dong Liu, Xiaoyan Sun, Zheng-Jun Zha
It describes unseen target domain as a combination of the known source ones, and explicitly learns domain-specific representation with target distribution to improve the model's generalization by a meta-learning pipeline.
1 code implementation • 31 Mar 2021 • Wenyu Han, Chen Feng, Haoran Wu, Alexander Gao, Armand Jordana, Dong Liu, Lerrel Pinto, Ludovic Righetti
We need intelligent robots for mobile construction, the process of navigating in an environment and modifying its structure according to a geometric design.
2 code implementations • CVPR 2021 • Jialun Peng, Dong Liu, Songcen Xu, Houqiang Li
We propose a two-stage model for diverse inpainting, where the first stage generates multiple coarse results each of which has a different structure, and the second stage refines each coarse result separately by augmenting texture.
no code implementations • 24 Feb 2021 • Shunxin Xu, Ke Sun, Dong Liu, Zhiwei Xiong, Zheng-Jun Zha
We observe that not only denoising helps combat the drop of segmentation accuracy due to noise, but also pixel-wise semantic information boosts the capability of denoising.
no code implementations • 15 Feb 2021 • Anubhab Ghosh, Antoine Honoré, Dong Liu, Gustav Eje Henter, Saikat Chatterjee
We test the robustness of a maximum-likelihood (ML) based classifier where sequential data as observation is corrupted by noise.
no code implementations • ICCV 2021 • Kaihua Zhang, Zicheng Zhao, Dong Liu, Qingshan Liu, Bo Liu
The popular unsupervised video object segmentation methods fuse the RGB frame and optical flow via a two-stream network.
Ranked #8 on
Unsupervised Video Object Segmentation
on FBMS test
no code implementations • 14 Dec 2020 • Danny Smyl, Tyler N. Tallman, Dong Liu, Andreas Hauptmann
Here we present a highly efficient data-driven Quasi-Newton method applicable to nonlinear inverse problems.
no code implementations • 19 Aug 2020 • Lezi Wang, Dong Liu, Rohit Puri, Dimitris N. Metaxas
A movie's key moments stand out of the screenplay to grab an audience's attention and make movie browsing efficient.
6 code implementations • Interspeech 2020 • Jingjing Chen, Qirong Mao, Dong Liu
By introduces a improved transformer, elements in speech sequences can interact directly, which enables DPTNet can model for the speech sequences with direct context-awareness.
Ranked #16 on
Speech Separation
on WSJ0-2mix
Speech Separation
Audio and Speech Processing
Sound
1 code implementation • 11 Jul 2020 • Andrea Scotti, Nima N. Moghadam, Dong Liu, Karl Gafvert, Jinliang Huang
In this paper, we innovately use graph neural networks (GNNs) to learn a message-passing solution for the inference task of massive multiple multiple-input multiple-output (MIMO) detection in wireless communication.
1 code implementation • 28 Jun 2020 • Ke Sun, Zigang Geng, Depu Meng, Bin Xiao, Dong Liu, Zhao-Xiang Zhang, Jingdong Wang
The typical bottom-up human pose estimation framework includes two stages, keypoint detection and grouping.
1 code implementation • 27 Jun 2020 • Dong Liu, Minh Thành Vu, Zuxing Li, Lars K. Rasmussen
To gain a better understanding of BP in general graphs, we derive an interpretable belief propagation algorithm that is motivated by minimization of a localized $\alpha$-divergence.
1 code implementation • 21 Jun 2020 • Hengrui Zhao, Dong Liu, Houqiang Li
Considering the tradeoff between activation quantization error and network learning ability, we set an empirical rule to tune the bound of each Bounded ReLU.
1 code implementation • 17 Jun 2020 • Dong Liu, Ragnar Thobaben, Lars K. Rasmussen
We term our model Region-based Energy Neural Network (RENN).
no code implementations • 16 Jun 2020 • Joya Chen, Qi Wu, Dong Liu, Tong Xu
Recent years have witnessed the remarkable developments made by deep learning techniques for object detection, a fundamentally challenging problem of computer vision.
no code implementations • CVPR 2020 • Yiheng Zhang, Zhaofan Qiu, Ting Yao, Chong-Wah Ngo, Dong Liu, Tao Mei
In the view of extremely expensive expert labeling, recent research has shown that the models trained on photo-realistic synthetic data (e. g., computer games) with computer-generated annotations can be adapted to real images.
Ranked #19 on
Domain Adaptation
on SYNTHIA-to-Cityscapes
1 code implementation • CVPR 2020 • Jianping Lin, Dong Liu, Houqiang Li, Feng Wu
To compensate for the compression error of the auto-encoders, we further design a MV refinement network and a residual refinement network, taking use of the multiple reference frames as well.
no code implementations • 21 Mar 2020 • Dong Liu, Jianyu Zhao, Chenyang Yang, Lajos Hanzo
Predictive power allocation is conceived for energy-efficient video streaming over mobile networks using deep reinforcement learning.
no code implementations • 13 Mar 2020 • Kaihua Zhang, Long Wang, Dong Liu, Bo Liu, Qingshan Liu, Zhu Li
We present an end-to-end network which stores short- and long-term video sequence information preceding the current frame as the temporal memories to address the temporal modeling in VOS.
no code implementations • 13 Mar 2020 • Haochen Zhang, Dong Liu, Zhiwei Xiong
Recent advances of deep learning lead to great success of image and video super-resolution (SR) methods that are based on convolutional neural networks (CNN).
1 code implementation • 3 Mar 2020 • Dong Liu, Baptiste Cavarec, Lars K. Rasmussen, Jing Yue
In this paper, we study the characteristics of dominant interference power with directional reception in a random network modelled by a Poisson Point Process.
Information Theory Signal Processing Information Theory
no code implementations • 3 Jan 2020 • Dong Liu, Chengjian Sun, Chenyang Yang, Lajos Hanzo
If the objective and constraint functions are unavailable, reinforcement learning can be applied to find the solution of a functional optimization problem, which is however not tailored to optimization problems in wireless networks.
no code implementations • 30 Oct 2019 • Antoine Honore, Dong Liu, David Forsberg, Karen Coste, Eric Herlenius, Saikat Chatterjee, Mikael Skoglund
We explore the use of traditional and contemporary hidden Markov models (HMMs) for sequential physiological data analysis and sepsis prediction in preterm infants.
no code implementations • 21 Oct 2019 • Danny Smyl, Dong Liu
Further, it is found that the use of optimized electrode positions computed using the approach derived herein can reduce errors in EIT reconstructions as well as improve the distinguishability of EIT measurements.
1 code implementation • 13 Oct 2019 • Dong Liu, Antoine Honoré, Saikat Chatterjee, Lars K. Rasmussen
In the proposed GenHMM, each HMM hidden state is associated with a neural network based generative model that has tractability of exact likelihood and provides efficient likelihood computation.
14 code implementations • 11 Sep 2019 • Joya Chen, Dong Liu, Tong Xu, Shiwei Wu, Yifei Cheng, Enhong Chen
In this paper, we challenge the necessity of such hard/soft sampling methods for training accurate deep object detectors.
no code implementations • 9 Sep 2019 • Jiaying Liu, Dong Liu, Wenhan Yang, Sifeng Xia, Xiaoshuai Zhang, Yuanying Dai
We present a comprehensive study and evaluation of existing single image compression artifacts removal algorithms, using a new 4K resolution benchmark including diversified foreground objects and background scenes with rich structures, called Large-scale Ideal Ultra high definition 4K (LIU4K) benchmark.
no code implementations • CVPR 2019 • Yiheng Zhang, Zhaofan Qiu, Jingen Liu, Ting Yao, Dong Liu, Tao Mei
As a result, our CAS is able to search an optimized architecture with customized constraints.
no code implementations • 24 Aug 2019 • Joya Chen, Dong Liu, Bin Luo, Xuezheng Peng, Tong Xu, Enhong Chen
For a long time, object detectors have suffered from extreme imbalance between foregrounds and backgrounds.
no code implementations • 23 Aug 2019 • Dong Liu, Nima N. Moghadam, Lars K. Rasmussen, Jinliang Huang, Saikat Chatterjee
Belief propagation (BP) can do exact inference in loop-free graphs, but its performance could be poor in graphs with loops, and the understanding of its solution is limited.
42 code implementations • 20 Aug 2019 • Jingdong Wang, Ke Sun, Tianheng Cheng, Borui Jiang, Chaorui Deng, Yang Zhao, Dong Liu, Yadong Mu, Mingkui Tan, Xinggang Wang, Wenyu Liu, Bin Xiao
High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection.
Ranked #1 on
Object Detection
on COCO test-dev
(Hardware Burden metric)
1 code implementation • 31 Jul 2019 • Dong Liu, Minh Thành Vu, Saikat Chatterjee, Lars K. Rasmussen
A single latent variable is used as the common input to all the neural networks.
no code implementations • 30 Jul 2019 • Chengjian Sun, Dong Liu, Chenyang Yang
In many optimization problems in wireless communications, the expressions of objective function or constraints are hard or even impossible to derive, which makes the solutions difficult to find.
no code implementations • 25 Jul 2019 • Dong Liu, Rohit Puri, Nagendra Kamath, Subhabrata Bhattachary
In this work, we propose to model the image composition information as the mutual dependency of its local regions, and design a novel architecture to leverage such information to boost the performance of aesthetics assessment.
no code implementations • 17 May 2019 • Saikat Chatterjee, Alireza M. Javid, Mostafa Sadeghi, Shumpei Kikuta, Dong Liu, Partha P. Mitra, Mikael Skoglund
We design a self size-estimating feed-forward network (SSFN) using a joint optimization approach for estimation of number of layers, number of nodes and learning of weight matrices.
1 code implementation • 29 Apr 2019 • Dong Liu, Yue Li, Jianping Lin, Houqiang Li, Feng Wu
For deep schemes, pixel probability modeling and auto-encoder are the two approaches, that can be viewed as predictive coding scheme and transform coding scheme, respectively.
Multimedia Image and Video Processing
no code implementations • NeurIPS 2019 • Dong Liu, Haochen Zhang, Zhiwei Xiong
In this paper, we extend the previous perception-distortion tradeoff to the case of classification-distortion-perception (CDP) tradeoff, where we introduced the classification error rate of the restored signal in addition to distortion and perceptual difference.
39 code implementations • 9 Apr 2019 • Ke Sun, Yang Zhao, Borui Jiang, Tianheng Cheng, Bin Xiao, Dong Liu, Yadong Mu, Xinggang Wang, Wenyu Liu, Jingdong Wang
The proposed approach achieves superior results to existing single-model networks on COCO object detection.
Ranked #7 on
Semantic Segmentation
on LIP val
1 code implementation • ICCV 2019 • Haochen Zhang, Dong Liu, Zhiwei Xiong
Tailored for two-stream action recognition networks, we propose two video SR methods for the spatial and temporal streams respectively.
39 code implementations • CVPR 2019 • Ke Sun, Bin Xiao, Dong Liu, Jingdong Wang
We start from a high-resolution subnetwork as the first stage, gradually add high-to-low resolution subnetworks one by one to form more stages, and connect the mutli-resolution subnetworks in parallel.
Ranked #1 on
3D Pose Estimation
on HARPER
no code implementations • 16 Nov 2018 • Dong Liu, Minh Thành Vu, Saikat Chatterjee, Lars K. Rasmussen
We investigate the use of entropy-regularized optimal transport (EOT) cost in developing generative models to learn implicit distributions.
no code implementations • 11 Sep 2018 • Hongmin Wu, Shuangqi Luo, Longxin Chen, Shuangda Duan, Sakmongkon Chumkamon, Dong Liu, Yisheng Guan, Juan Rojas
Robot manipulation is increasingly poised to interact with humans in co-shared workspaces.
2 code implementations • 29 Aug 2018 • Xiaofeng Zhang, Zhangyang Wang, Dong Liu, Qing Ling
Given insufficient data, while many techniques have been developed to help combat overfitting, the challenge remains if one tries to train deep networks, especially in the ill-posed extremely low data regimes: only a small set of labeled data are available, and nothing -- including unlabeled data -- else.
3 code implementations • 1 Jun 2018 • Ke Sun, Mingjie Li, Dong Liu, Jingdong Wang
In this paper, we are interested in building lightweight and efficient convolutional neural networks.
no code implementations • CVPR 2018 • Yiheng Zhang, Zhaofan Qiu, Ting Yao, Dong Liu, Tao Mei
The recent advances in deep neural networks have convincingly demonstrated high capability in learning vision models on large datasets.
1 code implementation • 28 Feb 2018 • Dong Liu, Ke Sun, Zhangyang Wang, Runsheng Liu, Zheng-Jun Zha
We propose an interpretable deep structure namely Frank-Wolfe Network (F-W Net), whose architecture is inspired by unrolling and truncating the Frank-Wolfe algorithm for solving an $L_p$-norm constrained problem with $p\geq 1$.
no code implementations • 22 Jan 2018 • Dong Liu, Chenyang Yang
We then formulate a joint caching and recommendation problem maximizing the successful offloading probability, which is a mixed integer programming problem.
no code implementations • ICCV 2017 • Ke Sun, Cuiling Lan, Junliang Xing, Wen-Jun Zeng, Dong Liu, Jingdong Wang
We present a two-stage normalization scheme, human body normalization and limb normalization, to make the distribution of the relative joint locations compact, resulting in easier learning of convolutional spatial models and more accurate pose estimation.
no code implementations • 18 Sep 2017 • Rui Song, Dong Liu, Houqiang Li, Feng Wu
In this paper, we propose an arithmetic coding strategy by training neural networks, and make preliminary studies on coding of the intra prediction modes in HEVC.
Multimedia
no code implementations • CVPR 2017 • Zhiwei Xiong, Lizhi Wang, Huiqun Li, Dong Liu, Feng Wu
This paper presents the first snapshot hyperspectral light field imager in practice.
no code implementations • 10 Mar 2017 • Ning Yan, Dong Liu, Houqiang Li, Feng Wu
To further improve the coding efficiency, sub-pel motion compensation has been utilized, which requires interpolation of fractional samples.
Multimedia
no code implementations • 22 Feb 2017 • Yue Li, Dong Liu, Houqiang Li, Li Li, Feng Wu, Hong Zhang, Haitao Yang
A block can be down-sampled before being compressed by normal intra coding, and then up-sampled to its original resolution.
Multimedia
1 code implementation • 24 Aug 2016 • Yuanying Dai, Dong Liu, Feng Wu
Lossy image and video compression algorithms yield visually annoying artifacts including blocking, blurring, and ringing, especially at low bit-rates.
Multimedia
no code implementations • CVPR 2016 • Chenyi Lei, Dong Liu, Weiping Li, Zheng-Jun Zha, Houqiang Li
In many image-related tasks, learning expressive and discriminative representations of images is essential, and deep learning has been studied for automating the learning of such representations.
no code implementations • 8 Jun 2015 • Guangnan Ye, Yitong Li, Hongliang Xu, Dong Liu, Shih-Fu Chang
Extensive experiments over the zero-shot event retrieval task when no training samples are available show that the EventNet concept library consistently and significantly outperforms the state-of-the-art (such as the 20K ImageNet concepts trained with CNN) by a large margin up to 207%.
no code implementations • 29 Mar 2014 • Yin Cui, Dong Liu, Jiawei Chen, Shih-Fu Chang
In this paper, we propose to build Concept Bank, the largest concept library consisting of 4, 876 concepts specifically designed to cover 631 real-world events.
no code implementations • 4 Jun 2013 • Felix X. Yu, Dong Liu, Sanjiv Kumar, Tony Jebara, Shih-Fu Chang
We study the problem of learning with label proportions in which the training data is provided in groups and only the proportion of each class in each group is known.
no code implementations • CVPR 2013 • Xin Guo, Dong Liu, Brendan Jou, Mojun Zhu, Anni Cai, Shih-Fu Chang
Object co-detection aims at simultaneous detection of objects of the same category from a pool of related images by exploiting consistent visual patterns present in candidate objects in the images.
no code implementations • CVPR 2013 • Go Irie, Dong Liu, Zhenguo Li, Shih-Fu Chang
nary learning methods rely on image descriptors alone or together with class labels.
no code implementations • CVPR 2013 • Dong Liu, Kuan-Ting Lai, Guangnan Ye, Ming-Syan Chen, Shih-Fu Chang
However, the existing methods generally use a fixed fusion weight for all the scores of a classifier, and thus fail to optimally determine the fusion weight for the individual samples.