no code implementations • 29 Apr 2024 • Wenbo Wang, Hsuan-I Ho, Chen Guo, Boxiang Rong, Artur Grigorev, Jie Song, Juan Jose Zarate, Otmar Hilliges
Addressing this gap, we introduce 4D-DRESS, the first real-world 4D dataset advancing human clothing research with its high-quality 4D textured scans and garment meshes.
no code implementations • 28 Mar 2024 • HUI ZHANG, Sammy Christen, Zicong Fan, Otmar Hilliges, Jie Song
Moreover, we show that our framework can be deployed to different dexterous hands and work with reconstructed or generated objects.
1 code implementation • 21 Mar 2024 • Qihan Huang, Jie Song, Jingwen Hu, Haofei Zhang, Yong Wang, Mingli Song
Concept Bottleneck Models (CBMs), which break down the reasoning process into the input-to-concept mapping and the concept-to-label prediction, have garnered significant attention due to their remarkable interpretability achieved by the interpretable concept bottleneck.
no code implementations • 11 Mar 2024 • Jiameng Bai, Sai Wu, Jie Song, Junbo Zhao, Gang Chen
As a fundamental problem in transfer learning, model selection aims to rank off-the-shelf pre-trained models and select the most suitable one for the new target task.
1 code implementation • 4 Mar 2024 • Zhengqi Xu, Ke Yuan, Huiqiong Wang, Yong Wang, Mingli Song, Jie Song
Furthermore, the visualization of the merged model within the multi-task loss landscape reveals that MuDSC enables the merged model to reside in the overlapping segment, featuring a unified lower loss for each task.
no code implementations • 5 Jan 2024 • KaiXuan Chen, Wei Luo, Shunyu Liu, Yaoquan Wei, Yihe Zhou, Yunpeng Qing, Quan Zhang, Jie Song, Mingli Song
In this paper, we present a novel transformer architecture tailored for learning robust power system state representations, which strives to optimize power dispatch for the power flow adjustment across different transmission sections.
no code implementations • 28 Nov 2023 • Yaoquan Wei, Shunyu Liu, Jie Song, Tongya Zheng, KaiXuan Chen, Yong Wang, Mingli Song
Instead, we employ a proxy model to extract state features that are both discriminative (adaptive to the agent) and generally applicable (robust to agent noise).
1 code implementation • 27 Nov 2023 • Hsuan-I Ho, Jie Song, Otmar Hilliges
For the former, we employ a powerful generative diffusion model to hallucinate unseen back-view appearance based on the input images.
Ranked #1 on 3D Human Reconstruction on CustomHumans
no code implementations • 16 Nov 2023 • Yangze Zhou, Qingsong Wen, Jie Song, Xueyuan Cui, Yi Wang
Accurate load forecasting serves as the foundation for the flexible operation of multi-energy systems (MES).
no code implementations • 9 Nov 2023 • Sammy Christen, Lan Feng, Wei Yang, Yu-Wei Chao, Otmar Hilliges, Jie Song
In this paper, we introduce a framework that can generate plausible human grasping motions suitable for training the robot.
no code implementations • 1 Nov 2023 • Ruiyang Jin, Yujie Tang, Jie Song
Distributed demand response is a typical distributed optimization problem that requires coordination among multiple agents to satisfy demand response requirements.
no code implementations • 11 Oct 2023 • Hongwei Ren, Yue Zhou, Yulong Huang, Haotian Fu, Xiaopeng Lin, Jie Song, Bojun Cheng
Moreover, it also achieves SOTA performance across all methods on three datasets, utilizing approximately 0. 3\% of the parameters and 0. 5\% of power consumption employed by artificial neural networks (ANNs).
1 code implementation • ICCV 2023 • Jie Song, Zhengqi Xu, Sai Wu, Gang Chen, Mingli Song
The last decade has witnessed the success of deep learning and the surge of publicly released trained models, which necessitates the quantification of the model functional distance for various purposes.
no code implementations • 7 Sep 2023 • HUI ZHANG, Sammy Christen, Zicong Fan, Luocheng Zheng, Jemin Hwangbo, Jie Song, Otmar Hilliges
ArtiGrasp leverages reinforcement learning and physics simulations to train a policy that controls the global and local hand pose.
1 code implementation • ICCV 2023 • Manuel Kaufmann, Jie Song, Chen Guo, Kaiyue Shen, Tianjian Jiang, Chengcheng Tang, Juan Zarate, Otmar Hilliges
EMDB is a novel dataset that contains high-quality 3D SMPL pose and shape parameters with global body and camera trajectories for in-the-wild videos.
no code implementations • 24 Jul 2023 • Pan Tan, Mingchen Li, Yuanxi Yu, Fan Jiang, Lirong Zheng, Banghao Wu, Xinyu Sun, Liqi Kang, Jie Song, Liang Zhang, Yi Xiong, Wanli Ouyang, Zhiqiang Hu, Guisheng Fan, Yufeng Pei, Liang Hong
Designing protein mutants with high stability and activity is a critical yet challenging task in protein engineering.
1 code implementation • 27 May 2023 • Yihe Zhou, Shunyu Liu, Yunpeng Qing, KaiXuan Chen, Tongya Zheng, Yanhao Huang, Jie Song, Mingli Song
Despite the encouraging results achieved, CTDE makes an independence assumption on agent policies, which limits agents to adopt global cooperative information from each other during centralized training.
Multi-agent Reinforcement Learning reinforcement-learning +2
1 code implementation • CVPR 2023 • Hsuan-I Ho, Lixin Xue, Jie Song, Otmar Hilliges
To this end, we construct a trainable feature codebook to store local geometry and texture features on the vertices of a deformable body model, thus exploiting its consistent topology under articulation.
1 code implementation • 15 Apr 2023 • Tongya Zheng, Xinchao Wang, Zunlei Feng, Jie Song, Yunzhi Hao, Mingli Song, Xingen Wang, Xinyu Wang, Chun Chen
The whole temporal neighborhood of nodes reveals the varying preferences of nodes.
no code implementations • ICCV 2023 • Yiming Zhao, Denys Rozumnyi, Jie Song, Otmar Hilliges, Marc Pollefeys, Martin R. Oswald
The key idea is to tackle the inverse problem of image deblurring by modeling the forward problem with a 3D human model, a texture map, and a sequence of poses to describe human motion.
1 code implementation • CVPR 2023 • Yifei Yin, Chen Guo, Manuel Kaufmann, Juan Jose Zarate, Jie Song, Otmar Hilliges
We propose Hi4D, a method and dataset for the automatic analysis of physically close human-human interaction under prolonged contact.
1 code implementation • CVPR 2023 • Tianli Zhang, Mengqi Xue, Jiangtao Zhang, Haofei Zhang, Yu Wang, Lechao Cheng, Jie Song, Mingli Song
Most existing online knowledge distillation(OKD) techniques typically require sophisticated modules to produce diverse knowledge for improving students' generalization ability.
1 code implementation • 12 Mar 2023 • Haofei Zhang, Mengqi Xue, Xiaokang Liu, KaiXuan Chen, Jie Song, Mingli Song
In this paper, we study a novel inference paradigm, termed as schema inference, that learns to deductively infer the explainable predictions by rebuilding the prior deep neural network (DNN) forwarding scheme, guided by the prevalent philosophical cognitive concept of schema.
1 code implementation • CVPR 2023 • Kaiyue Shen, Chen Guo, Manuel Kaufmann, Juan Jose Zarate, Julien Valentin, Jie Song, Otmar Hilliges
Our method models bodies, hands, facial expressions and appearance in a holistic fashion and can be learned from either full 3D scans or RGB-D data.
no code implementations • 28 Feb 2023 • Xinjiang Chen, Yu Yang, Jianxiao Wang, Jie Song, Guannan He
Battery swapping as a business model for battery energy storage (BES) has great potential in future integrated low-carbon energy and transportation systems.
1 code implementation • CVPR 2023 • Chen Guo, Tianjian Jiang, Xu Chen, Jie Song, Otmar Hilliges
Specifically, we define a temporally consistent human representation in canonical space and formulate a global optimization over the background model, the canonical human shape and texture, and per-frame human pose parameters.
no code implementations • 14 Jan 2023 • Zipeng Zhong, Jie Song, Zunlei Feng, Tiantao Liu, Lingxiang Jia, Shaolun Yao, Tingjun Hou, Mingli Song
Afterwards, we analyze these methods in terms of their mechanism and performance, and introduce popular evaluation metrics for them, in which we also provide a detailed comparison among representative methods on several public datasets.
no code implementations • CVPR 2023 • Tianjian Jiang, Xu Chen, Jie Song, Otmar Hilliges
To achieve this efficiency we propose a carefully designed and engineered system, that leverages emerging acceleration structures for neural fields, in combination with an efficient empty space-skipping strategy for dynamic scenes.
no code implementations • 15 Dec 2022 • Jie Song, Marc Cheah-Mane, Eduardo Prieto-Araujo, Oriol Gomis-Bellmunt
A novel methodology has been presented to identify short-circuit equilibrium point of the studied system considering the operation and limitations of power converters.
1 code implementation • ICCV 2023 • Qihan Huang, Mengqi Xue, Wenqi Huang, Haofei Zhang, Jie Song, Yongcheng Jing, Mingli Song
Part-prototype networks (e. g., ProtoPNet, ProtoTree, and ProtoPool) have attracted broad research interest for their intrinsic interpretability and comparable accuracy to non-interpretable counterparts.
1 code implementation • 28 Nov 2022 • Xu Chen, Tianjian Jiang, Jie Song, Max Rietmann, Andreas Geiger, Michael J. Black, Otmar Hilliges
A key challenge in making such methods applicable to articulated objects, such as the human body, is to model the deformation of 3D locations between the rest pose (a canonical space) and the deformed space.
1 code implementation • 23 Nov 2022 • Shunyu Liu, Yihe Zhou, Jie Song, Tongya Zheng, KaiXuan Chen, Tongtian Zhu, Zunlei Feng, Mingli Song
Value Decomposition (VD) aims to deduce the contributions of agents for decentralized policies in the presence of only global rewards, and has recently emerged as a powerful credit assignment paradigm for tackling cooperative Multi-Agent Reinforcement Learning (MARL) problems.
1 code implementation • 12 Nov 2022 • Yunpeng Qing, Shunyu Liu, Jie Song, Huiqiong Wang, Mingli Song
In this survey, we provide a comprehensive review of existing works on eXplainable RL (XRL) and introduce a new taxonomy where prior works are clearly categorized into model-explaining, reward-explaining, state-explaining, and task-explaining methods.
1 code implementation • 9 Oct 2022 • Rang Meng, Xianfeng Li, WeiJie Chen, Shicai Yang, Jie Song, Xinchao Wang, Lei Zhang, Mingli Song, Di Xie, ShiLiang Pu
Under this guidance, a novel Attention Diversification framework is proposed, in which Intra-Model and Inter-Model Attention Diversification Regularization are collaborated to reassign appropriate attention to diverse task-related features.
1 code implementation • 7 Sep 2022 • Haoling Li, Jie Song, Mengqi Xue, Haofei Zhang, Jingwen Ye, Lechao Cheng, Mingli Song
This survey aims to present a comprehensive review of NTs and attempts to identify how they enhance the model interpretability.
1 code implementation • 22 Aug 2022 • Mengqi Xue, Qihan Huang, Haofei Zhang, Lechao Cheng, Jie Song, Minghui Wu, Mingli Song
The global prototypes are adopted to provide the global view of objects to guide local prototypes to concentrate on the foreground while eliminating the influence of the background.
1 code implementation • 27 Jul 2022 • Donglin Xie, Ruonan Yu, Gongfan Fang, Jie Song, Zunlei Feng, Xinchao Wang, Li Sun, Mingli Song
The goal of FedSA is to train a student model for a new task with the help of several decentralized teachers, whose pre-training tasks and data are different and agnostic.
1 code implementation • 17 Jul 2022 • Jingwen Ye, Yifang Fu, Jie Song, Xingyi Yang, Songhua Liu, Xin Jin, Mingli Song, Xinchao Wang
Life-long learning aims at learning a sequence of tasks without forgetting the previously acquired knowledge.
1 code implementation • 8 Jul 2022 • Shunyu Liu, Jie Song, Yihe Zhou, Na Yu, KaiXuan Chen, Zunlei Feng, Mingli Song
In this work, we introduce a novel interactiOn Pattern disenTangling (OPT) method, to disentangle not only the joint value function into agent-wise value functions for decentralized execution, but also the entity interactions into interaction prototypes, each of which represents an underlying interaction pattern within a subgroup of the entities.
Multi-agent Reinforcement Learning reinforcement-learning +1
1 code implementation • 5 Jul 2022 • Shunyu Liu, KaiXuan Chen, Na Yu, Jie Song, Zunlei Feng, Mingli Song
Despite the promising results achieved, state-of-the-art interactive reinforcement learning schemes rely on passively receiving supervision signals from advisor experts, in the form of either continuous monitoring or pre-defined rules, which inevitably result in a cumbersome and expensive learning process.
1 code implementation • CVPR 2022 • Rang Meng, WeiJie Chen, Shicai Yang, Jie Song, Luojun Lin, Di Xie, ShiLiang Pu, Xinchao Wang, Mingli Song, Yueting Zhuang
In this paper, we introduce a simple framework, Slimmable Domain Adaptation, to improve cross-domain generalization with a weight-sharing model bank, from which models of different capacities can be sampled to accommodate different accuracy-efficiency trade-offs.
3 code implementations • CVPR 2022 • Binbin Chen, WeiJie Chen, Shicai Yang, Yunyi Xuan, Jie Song, Di Xie, ShiLiang Pu, Mingli Song, Yueting Zhuang
To remedy this issue, we present a novel label assignment mechanism for self-training framework, namely proposal self-assignment, which injects the proposals from student into teacher and generates accurate pseudo labels to match each proposal in the student model accordingly.
2 code implementations • 13 Jun 2022 • Meilin Chen, WeiJie Chen, Shicai Yang, Jie Song, Xinchao Wang, Lei Zhang, Yunfeng Yan, Donglian Qi, Yueting Zhuang, Di Xie, ShiLiang Pu
In addition, we conduct anchor adaptation in parallel with localization adaptation, since anchor can be regarded as a learnable parameter.
1 code implementation • 12 May 2022 • KaiXuan Chen, Shunyu Liu, Na Yu, Rong Yan, Quan Zhang, Jie Song, Zunlei Feng, Mingli Song
As the topology of the power system is in the form of graph structure, graph neural network based representation learning is naturally suitable for learning the status of the power system.
2 code implementations • 5 May 2022 • Jie Song, Ying Chen, Jingwen Ye, Mingli Song
Knowledge distillation (KD) has become a well established paradigm for compressing deep neural networks.
no code implementations • 25 Apr 2022 • Jie Song, Meiyu Liang, Zhe Xue, Feifei Kou, Ang Li
There is a complex correlation among the data of scientific papers.
no code implementations • 31 Mar 2022 • Jie Song, Meiyu Liang, Zhe Xue, Junping Du, Kou Feifei
in the heterogeneous graph of scientific papers.
1 code implementation • CVPR 2022 • Mengqi Xue, Haofei Zhang, Jie Song, Mingli Song
Continual learning is a longstanding research topic due to its crucial role in tackling continually arriving tasks.
1 code implementation • 22 Mar 2022 • Zipeng Zhong, Jie Song, Zunlei Feng, Tiantao Liu, Lingxiang Jia, Shaolun Yao, Min Wu, Tingjun Hou, Mingli Song
Chemical reaction prediction, involving forward synthesis and retrosynthesis prediction, is a fundamental problem in organic synthesis.
1 code implementation • 7 Mar 2022 • Haofei Zhang, Feng Mao, Mengqi Xue, Gongfan Fang, Zunlei Feng, Jie Song, Mingli Song
Moreover, the transformer-based students excel in learning amalgamated knowledge, as they have mastered heterogeneous detection tasks rapidly and achieved superior or at least comparable performance to those of the teachers in their specializations.
no code implementations • CVPR 2022 • Zijian Dong, Chen Guo, Jie Song, Xu Chen, Andreas Geiger, Otmar Hilliges
We present a novel method to learn Personalized Implicit Neural Avatars (PINA) from a short RGB-D sequence.
no code implementations • 17 Jan 2022 • Jie Song, Huawei Yi, Wenqian Xu, Xiaohui Li, Bo Li, Yuanyuan Liu
The proposal of perceptual loss solves the problem that per-pixel difference loss function causes the reconstructed image to be overly-smooth, which acquires a significant progress in the field of single image super-resolution reconstruction.
no code implementations • CVPR 2022 • Xu Chen, Tianjian Jiang, Jie Song, Jinlong Yang, Michael J. Black, Andreas Geiger, Otmar Hilliges
Furthermore, we show that our method can be used on the task of fitting human models to raw scans, outperforming the previous state-of-the-art.
2 code implementations • 12 Dec 2021 • Gongfan Fang, Kanya Mo, Xinchao Wang, Jie Song, Shitao Bei, Haofei Zhang, Mingli Song
At the heart of our approach is a novel strategy to reuse the shared common features in training data so as to synthesize different data instances.
no code implementations • 11 Dec 2021 • Yeye He, Jie Song, Yue Wang, Surajit Chaudhuri, Vishal Anil, Blake Lassiter, Yaron Goland, Gaurav Malhotra
As data lakes become increasingly popular in large enterprises today, there is a growing need to tag or classify data assets (e. g., files and databases) in data lakes with additional metadata (e. g., semantic column-types), as the inferred metadata can enable a range of downstream applications like data governance (e. g., GDPR compliance), and dataset search.
1 code implementation • 9 Dec 2021 • Zunlei Feng, Jiacong Hu, Sai Wu, Xiaotian Yu, Jie Song, Mingli Song
The aggregate gradient strategy is a versatile module for mainstream CNN classifiers.
1 code implementation • CVPR 2022 • Haofei Zhang, Jiarui Duan, Mengqi Xue, Jie Song, Li Sun, Mingli Song
Recently, vision Transformers (ViTs) are developing rapidly and starting to challenge the domination of convolutional neural networks (CNNs) in the realm of computer vision (CV).
no code implementations • 6 Dec 2021 • Qihan Huang, Haofei Zhang, Mengqi Xue, Jie Song, Mingli Song
Although few-shot learning and zero-shot learning have been extensively explored in the field of image classification, it is indispensable to design new methods for object detection in the data-scarce scenario since object detection has an additional challenging localization task.
1 code implementation • 5 Dec 2021 • Jingwen Ye, Yining Mao, Jie Song, Xinchao Wang, Cheng Jin, Mingli Song
In other words, all users may employ a model in SDB for inference, but only authorized users get access to KD from the model.
1 code implementation • CVPR 2022 • Sammy Christen, Muhammed Kocabas, Emre Aksan, Jemin Hwangbo, Jie Song, Otmar Hilliges
We introduce the dynamic grasp synthesis task: given an object with a known 6D pose and a grasp reference, our goal is to generate motions that move the object to a target 6D pose.
1 code implementation • 29 Nov 2021 • Chen Guo, Xu Chen, Jie Song, Otmar Hilliges
In this work, we propose a method capable of capturing the dynamic 3D human shape from a monocular video featuring challenging body poses, without any additional input.
1 code implementation • 1 Nov 2021 • Hsuan-I Ho, Xu Chen, Jie Song, Otmar Hilliges
We propose to address these issues in a motion-guided frame-upsampling framework that is capable of producing realistic human motion and appearance.
2 code implementations • NeurIPS 2021 • Gongfan Fang, Yifan Bao, Jie Song, Xinchao Wang, Donglin Xie, Chengchao Shen, Mingli Song
Knowledge distillation~(KD) aims to craft a compact student model that imitates the behavior of a pre-trained teacher in a target domain.
no code implementations • ICCV 2021 • Zijian Dong, Jie Song, Xu Chen, Chen Guo, Otmar Hilliges
In this paper we contribute a simple yet effective approach for estimating 3D poses of multiple people from multi-view images.
Ranked #16 on 3D Multi-Person Pose Estimation on Shelf
3D Multi-Person Pose Estimation Multi-Person Pose Estimation
1 code implementation • 29 Sep 2021 • KaiXuan Chen, Jie Song, Shunyu Liu, Na Yu, Zunlei Feng, Gengshi Han, Mingli Song
A DKEPool network de facto disassembles representation learning into two stages, structure learning and distribution learning.
no code implementations • CVPR 2021 • Jie Song, Haofei Zhang, Xinchao Wang, Mengqi Xue, Ying Chen, Li Sun, DaCheng Tao, Mingli Song
Knowledge distillation pursues a diminutive yet well-behaved student network by harnessing the knowledge learned by a cumbersome teacher model.
3 code implementations • 18 May 2021 • Gongfan Fang, Jie Song, Xinchao Wang, Chengchao Shen, Xingen Wang, Mingli Song
In this paper, we propose Contrastive Model Inversion~(CMI), where the data diversity is explicitly modeled as an optimizable objective, to alleviate the mode collapse issue.
1 code implementation • 10 May 2021 • Mengqi Xue, Jie Song, Xinchao Wang, Ying Chen, Xingen Wang, Mingli Song
Knowledge distillation (KD) has recently emerged as an efficacious scheme for learning compact deep neural networks (DNNs).
no code implementations • 10 Apr 2021 • Jie Song, Yeye He
Complex data pipelines are increasingly common in diverse applications such as BI reporting and ML modeling.
no code implementations • 15 Mar 2021 • Yang Liu, Tu Zheng, Jie Song, Deng Cai, Xiaofei He
In this paper, we argue that a Mutual Nearest Neighbor (MNN) relation should be established to explicitly select the query descriptors that are most relevant to each task and discard less relevant ones from aggregative clutters in FSL.
no code implementations • 5 Mar 2021 • Yonghong Luo, Chao Lu, Lipeng Zhu, Jie Song
The proposed STGCN utilizes graph convolution to integrate network topology information into the learning model to exploit spatial information.
1 code implementation • CVPR 2021 • Chengchao Shen, Youtan Yin, Xinchao Wang, Xubin Li, Jie Song, Mingli Song
Based on the adversarial losses of the generator and discriminator, we categorize GANs into two classes, Symmetric GANs and Asymmetric GANs, and introduce a novel gradient decomposition method to unify the two, allowing us to train both classes in one stage and hence alleviate the training effort.
no code implementations • ICCV 2021 • Ying Chen, Feng Mao, Jie Song, Xinchao Wang, Huiqiong Wang, Mingli Song
Neural trees aim at integrating deep neural networks and decision trees so as to bring the best of the two worlds, including representation learning from the former and faster inference from the latter.
1 code implementation • ICCV 2021 • Manuel Kaufmann, Yi Zhao, Chengcheng Tang, Lingling Tao, Christopher Twigg, Jie Song, Robert Wang, Otmar Hilliges
To this end, we present a method to estimate SMPL parameters from 6-12 EM sensors.
2 code implementations • 9 Dec 2020 • Chengchao Shen, Xinchao Wang, Youtan Yin, Jie Song, Sihui Luo, Mingli Song
In this paper, we investigate the practical few-shot knowledge distillation scenario, where we assume only a few samples without human annotations are available for each category.
1 code implementation • 22 Oct 2020 • Manuel Kaufmann, Emre Aksan, Jie Song, Fabrizio Pece, Remo Ziegler, Otmar Hilliges
At the heart of our approach lies the idea to cast motion infilling as an inpainting problem and to train a convolutional de-noising autoencoder on image-like representations of motion sequences.
no code implementations • ECCV 2020 • Jie Song, Xu Chen, Otmar Hilliges
We propose a novel algorithm for the fitting of 3D human shape to images.
Ranked #10 on 3D Human Pose Estimation on EMDB
no code implementations • ECCV 2020 • Xu Chen, Zijian Dong, Jie Song, Andreas Geiger, Otmar Hilliges
Many object pose estimation algorithms rely on the analysis-by-synthesis framework which requires explicit representations of individual object instances.
no code implementations • 13 Aug 2020 • Jie Song, Liang Xiao, Mohsen Molaei, Zhichao Lian
In this way, rich image appearance models together with more contextual information are integrated by learning a series of decision tree ensembles.
no code implementations • 10 Jul 2020 • Gongfan Fang, Xinchao Wang, Haofei Zhang, Jie Song, Mingli Song
This network is referred to as the {\emph{Template Network}} because its filters will be used as templates to reconstruct images from the impression.
1 code implementation • CVPR 2020 • Jie Song, Yixin Chen, Jingwen Ye, Xinchao Wang, Chengchao Shen, Feng Mao, Mingli Song
In this paper, we propose the DEeP Attribution gRAph (DEPARA) to investigate the transferability of knowledge learned from PR-DNNs.
3 code implementations • 23 Dec 2019 • Gongfan Fang, Jie Song, Chengchao Shen, Xinchao Wang, Da Chen, Mingli Song
Knowledge Distillation (KD) has made remarkable progress in the last few years and become a popular paradigm for model compression and knowledge transfer.
2 code implementations • NeurIPS 2019 • Jie Song, Yixin Chen, Xinchao Wang, Chengchao Shen, Mingli Song
Exploring the transferability between heterogeneous tasks sheds light on their intrinsic interconnections, and consequently enables knowledge transfer from one task to another so as to reduce the training effort of the latter.
no code implementations • 20 Aug 2019 • Gang Hu, Lingbo Liu, DaCheng Tao, Jie Song, K. C. S. Kwok
This study used machine learning techniques to resolve the conflicting requirement between limited wind tunnel tests that produce unreliable results and a completed investigation of the interference effects that is costly and time-consuming.
2 code implementations • ICCV 2019 • Chengchao Shen, Mengqi Xue, Xinchao Wang, Jie Song, Li Sun, Mingli Song
To this end, we introduce a dual-step strategy that first extracts the task-specific knowledge from the heterogeneous teachers sharing the same sub-task, and then amalgamates the extracted knowledge to build the student network.
1 code implementation • 8 Jan 2019 • Xu Chen, Jie Song, Otmar Hilliges
This paper studies the task of full generative modelling of realistic images of humans, guided only by coarse sketch of the pose, while providing control over the specific instance or type of outfit worn by the user.
2 code implementations • ICCV 2019 • Xu Chen, Jie Song, Otmar Hilliges
The approach is self-supervised and only requires 2D images and associated view transforms for training.
no code implementations • ICCV 2019 • Jie Song, Bjoern Andres, Michael Black, Otmar Hilliges, Siyu Tang
The new optimization problem can be viewed as a Conditional Random Field (CRF) in which the random variables are associated with the binary edge labels of the initial graph and the hard constraints are introduced in the CRF as high-order potentials.
1 code implementation • 7 Nov 2018 • Chengchao Shen, Xinchao Wang, Jie Song, Li Sun, Mingli Song
We propose in this paper to study a new model-reusing task, which we term as \emph{knowledge amalgamation}.
no code implementations • ECCV 2018 • Jie Song, Chengchao Shen, Jie Lei, An-Xiang Zeng, Kairi Ou, DaCheng Tao, Mingli Song
We propose a selective zero-shot classifier based on both the human defined and the automatically discovered residual attributes.
no code implementations • CVPR 2018 • Jie Song, Chengchao Shen, Yezhou Yang, Yang Liu, Mingli Song
Most existing Zero-Shot Learning (ZSL) methods have the strong bias problem, in which instances of unseen (target) classes tend to be categorized as one of the seen (source) classes.
1 code implementation • CVPR 2018 • Adrian Spurr, Jie Song, Seonwook Park, Otmar Hilliges
Furthermore, we show that our proposed method can be used without changes on depth images and performs comparably to specialized methods.
no code implementations • 10 Apr 2017 • Partha Ghosh, Jie Song, Emre Aksan, Otmar Hilliges
Furthermore, we propose new evaluation protocols to assess the quality of synthetic motion sequences even for which no ground truth data exists.
no code implementations • CVPR 2017 • Jie Song, Li-Min Wang, Luc van Gool, Otmar Hilliges
Temporal information can provide additional cues about the location of body joints and help to alleviate these issues.
Ranked #4 on Pose Estimation on UPenn Action