no code implementations • ECCV 2020 • Ziwei Wang, Quan Zheng, Jiwen Lu, Jie zhou
n this paper, we propose a Deep Hashing method with Active Pairwise Supervision(DH-APS).
no code implementations • ECCV 2020 • Yu Zheng, Danyang Zhang, Sinan Xie, Jiwen Lu, Jie zhou
In this paper, we propose a Rotation-robust Intersection over Union ($ extit{RIoU}$) for 3D object detection, which aims to jointly learn the overlap of rotated bounding boxes.
no code implementations • ECCV 2020 • Liangliang Ren, Yangyang Song, Jiwen Lu, Jie zhou
Unlike most existing works that define room layout on a 2D image, we model the layout in 3D as a configuration of the camera and the room.
no code implementations • ECCV 2020 • Guangyi Chen, Yongming Rao, Jiwen Lu, Jie zhou
Specifically, we disentangle the video representation into the temporal coherence and motion parts and randomly change the scale of the temporal motion features as the adversarial noise.
no code implementations • ECCV 2020 • Wenzhao Zheng, Jiwen Lu, Jie zhou
We employ a metric model and a layout encoder to map the RGB images and the ground-truth layouts to the embedding space, respectively, and a layout decoder to map the embeddings to the corresponding layouts, where the whole framework is trained in an end-to-end manner.
no code implementations • ECCV 2020 • Guangyi Chen, Yuhao Lu, Jiwen Lu, Jie Zhou
Experimental results demonstrate that our DCML method explores credible and valuable training data and improves the performance of unsupervised domain adaptation.
no code implementations • 19 Mar 2025 • Yinan Liang, Ziwei Wang, Xiuwei Xu, Jie zhou, Jiwen Lu
While multimodal large language models demonstrate strong performance in complex reasoning tasks, they pose significant challenges related to model complexity during deployment, especially for resource-limited devices.
no code implementations • 18 Mar 2025 • Minglei Shi, Ziyang Yuan, Haotian Yang, Xintao Wang, Mingwu Zheng, Xin Tao, Wenliang Zhao, Wenzhao Zheng, Jie zhou, Jiwen Lu, Pengfei Wan, Di Zhang, Kun Gai
Diffusion models have demonstrated remarkable success in various image generation tasks, but their performance is often limited by the uniform processing of inputs across varying conditions and noise levels.
Ranked #15 on
Text-to-Image Generation
on GenEval
no code implementations • 13 Mar 2025 • Hang Yin, Xiuwei Xu, Lingqing Zhao, Ziwei Wang, Jie zhou, Jiwen Lu
Specifically, we conduct graph matching between the scene graph and goal graph at each time instant and propose different strategies to generate long-term goal of exploration according to different matching states.
1 code implementation • 14 Feb 2025 • Wenxuan Guo, Xiuwei Xu, Ziwei Wang, Jianjiang Feng, Jie zhou, Jiwen Lu
To this end, we propose text-guided pruning (TGP) and completion-based addition (CBA) to deeply fuse 3D scene representation and text features in an efficient way by gradual region pruning and target completion.
1 code implementation • 6 Feb 2025 • Zuyan Liu, Yuhao Dong, Jiahui Wang, Ziwei Liu, Winston Hu, Jiwen Lu, Yongming Rao
Our training pipeline begins with the most distinct modalities: image and text, then gradually expands the skill sets of the model using speech data that connects language and audio knowledge, and video data that connects all modalities.
1 code implementation • 26 Jan 2025 • Jiajun Dong, Chengkun Wang, Wenzhao Zheng, Lei Chen, Jiwen Lu, Yansong Tang
In this paper, we propose GaussianToken: An Effective Image Tokenizer with 2D Gaussian Splatting as a solution.
1 code implementation • 19 Dec 2024 • Borui Zhang, Wenzhao Zheng, Jie zhou, Jiwen Lu
Vector-quantized networks (VQNs) have exhibited remarkable performance across various tasks, yet they are prone to training instability, which complicates the training process due to the necessity for techniques such as subtle initialization and model distillation.
Ranked #2 on
Image Reconstruction
on ImageNet
1 code implementation • 13 Dec 2024 • Sicheng Zuo, Wenzhao Zheng, Yuanhui Huang, Jie zhou, Jiwen Lu
3D occupancy prediction is important for autonomous driving due to its comprehensive perception of the surroundings.
1 code implementation • 12 Dec 2024 • Wenzhao Zheng, Zetian Xia, Yuanhui Huang, Sicheng Zuo, Jie zhou, Jiwen Lu
In this paper, we explore a closed-loop framework for autonomous driving and propose a large Driving wOrld modEl (Doe-1) for unified perception, prediction, and planning.
1 code implementation • 12 Dec 2024 • Yuanhui Huang, Wenzhao Zheng, Yuan Gao, Xin Tao, Pengfei Wan, Di Zhang, Jie zhou, Jiwen Lu
As videos are observations of the underlying evolving world, we propose to model the long-term developments in a latent space and use VGMs to film them into videos.
2 code implementations • 11 Dec 2024 • Zixun Xie, Sicheng Zuo, Wenzhao Zheng, Yunpeng Zhang, Dalong Du, Jie zhou, Jiwen Lu, Shanghang Zhang
We represent each scene with ego, agent, and map tokens and formulate autonomous driving as a unified token generation problem.
1 code implementation • 9 Dec 2024 • Xin Fei, Wenzhao Zheng, Yueqi Duan, Wei Zhan, Masayoshi Tomizuka, Kurt Keutzer, Jiwen Lu
Realtime 4D reconstruction for dynamic scenes remains a crucial challenge for autonomous driving perception.
1 code implementation • 9 Dec 2024 • Dongchen Han, Yifan Pu, Zhuofan Xia, Yizeng Han, Xuran Pan, Xiu Li, Jiwen Lu, Shiji Song, Gao Huang
Widely adopted in modern Vision Transformer designs, Softmax attention can effectively capture long-range visual information; however, it incurs excessive computational cost when dealing with high-resolution inputs.
1 code implementation • 6 Dec 2024 • Lening Wang, Wenzhao Zheng, Dalong Du, Yunpeng Zhang, Yilong Ren, Han Jiang, Zhiyong Cui, Haiyang Yu, Jie zhou, Jiwen Lu, Shanghang Zhang
To address these limitations, we propose a Spatial-Temporal simulAtion for drivinG (Stag-1) model to reconstruct real-world scenes and design a controllable generative network to achieve 4D simulation.
1 code implementation • 5 Dec 2024 • Yuanhui Huang, Amonnut Thammatadatrakoon, Wenzhao Zheng, Yunpeng Zhang, Dalong Du, Jiwen Lu
To address this, we propose a probabilistic Gaussian superposition model which interprets each Gaussian as a probability distribution of its neighborhood being occupied and conforms to probabilistic multiplication to derive the overall geometry.
2 code implementations • 5 Dec 2024 • Yuqi Wu, Wenzhao Zheng, Sicheng Zuo, Yuanhui Huang, Jie zhou, Jiwen Lu
3D occupancy prediction provides a comprehensive description of the surrounding scenes and has become an essential task for 3D perception.
1 code implementation • 20 Nov 2024 • Ziyi Wang, Yanbo Wang, Xumin Yu, Jie zhou, Jiwen Lu
In our approach, we developed a mask generator based on the denoising UNet from a pre-trained diffusion model, leveraging its capability for precise textual control over dense pixel representations and enhancing the open-world adaptability of the generated masks.
1 code implementation • 24 Oct 2024 • Xin Fei, Wenzhao Zheng, Yueqi Duan, Wei Zhan, Masayoshi Tomizuka, Kurt Keutzer, Jiwen Lu
We propose PixelGaussian, an efficient feed-forward framework for learning generalizable 3D Gaussian reconstruction from arbitrary views.
1 code implementation • 14 Oct 2024 • Chengkun Wang, Wenzhao Zheng, Jie zhou, Jiwen Lu
In this paper, we propose a global image serialization method to transform the image into a sequence of causal tokens, which contain global information of the 2D image.
1 code implementation • 14 Oct 2024 • Chengkun Wang, Wenzhao Zheng, Yuanhui Huang, Jie zhou, Jiwen Lu
Mamba has garnered widespread attention due to its flexible design and efficient hardware performance to process 1D sequences based on the state space model (SSM).
1 code implementation • 10 Oct 2024 • Changyuan Wang, Ziwei Wang, Xiuwei Xu, Yansong Tang, Jie zhou, Jiwen Lu
On the contrary, we mine the cross-layer dependency that significantly influences discretization errors of the entire vision-language model, and embed this dependency into optimal quantization strategy searching with low search cost.
no code implementations • 10 Oct 2024 • Hang Yin, Xiuwei Xu, Zhenyu Wu, Jie zhou, Jiwen Lu
Existing zero-shot object navigation methods prompt LLM with the text of spatially closed objects, which lacks enough scene context for in-depth reasoning.
1 code implementation • 30 Sep 2024 • Yu Zheng, Yueqi Duan, Kangfu Zheng, Hongru Yan, Jiwen Lu, Jie zhou
In this paper, we propose a One-Point-One NeRF (OPONeRF) framework for robust scene rendering.
1 code implementation • 26 Sep 2024 • Wenliang Zhao, Minglei Shi, Xumin Yu, Jie zhou, Jiwen Lu
By integrating FlowTurbo into different flow-based models, we obtain an acceleration ratio of 53. 1%$\sim$58. 3% on class-conditional generation and 29. 8%$\sim$38. 5% on text-to-image generation.
1 code implementation • 19 Sep 2024 • Zuyan Liu, Yuhao Dong, Ziwei Liu, Winston Hu, Jiwen Lu, Yongming Rao
Visual data comes in various forms, ranging from small icons of just a few pixels to long videos spanning hours.
Ranked #1 on
Video Question Answering
on Perception Test
1 code implementation • 5 Sep 2024 • Wenliang Zhao, Haolin Wang, Jie zhou, Jiwen Lu
Diffusion probabilistic models (DPMs) have shown remarkable performance in visual synthesis but are computationally expensive due to the need for multiple evaluations during the sampling.
1 code implementation • 21 Aug 2024 • Xiuwei Xu, Huangxing Chen, Linqing Zhao, Ziwei Wang, Jie zhou, Jiwen Lu
In this paper, we aim to leverage Segment Anything Model (SAM) for real-time 3D instance segmentation in an online setting.
no code implementations • 28 Jul 2024 • Yushi Huang, Ruihao Gong, Xianglong Liu, Jing Liu, Yuhang Li, Jiwen Lu, DaCheng Tao
However, unlike traditional models, diffusion models critically rely on the time-step for the multi-round denoising.
1 code implementation • 25 Jul 2024 • Zuyan Liu, Benlin Liu, Jiahui Wang, Yuhao Dong, Guangyi Chen, Yongming Rao, Ranjay Krishna, Jiwen Lu
Surrounding less important caches are then merged with these anchors, enhancing the preservation of contextual information in the KV caches while yielding an arbitrary acceleration ratio.
1 code implementation • 21 Jun 2024 • Chubin Zhang, Hongliang Song, Yi Wei, Yu Chen, Jiwen Lu, Yansong Tang
GeoLRM tackles these issues by incorporating a novel 3D-aware transformer structure that directly processes 3D points and uses deformable cross-attention mechanisms to effectively integrate image features into 3D representations.
no code implementations • 17 Jun 2024 • Zhenyu Wu, Ziwei Wang, Xiuwei Xu, Jiwen Lu, Haibin Yan
For the task planner, we generate the feasible step-by-step plans for human goal accomplishment according to the task completion process and the known visual clues.
1 code implementation • CVPR 2024 • Yixuan Zhu, Wenliang Zhao, Ao Li, Yansong Tang, Jie zhou, Jiwen Lu
Image enhancement holds extensive applications in real-world scenarios due to complex environments and limitations of imaging devices.
1 code implementation • 30 May 2024 • Lening Wang, Wenzhao Zheng, Yilong Ren, Han Jiang, Zhiyong Cui, Haiyang Yu, Jiwen Lu
To address this, we propose a diffusion-based 4D occupancy generation model, OccSora, to simulate the development of the 3D world for autonomous driving.
1 code implementation • 27 May 2024 • Yuanhui Huang, Wenzhao Zheng, Yunpeng Zhang, Jie zhou, Jiwen Lu
To address this, we propose an object-centric representation to describe 3D scenes with sparse 3D semantic Gaussians where each Gaussian represents a flexible region of interest and its semantic features.
1 code implementation • 27 May 2024 • Shuai Zeng, Wenzhao Zheng, Jiwen Lu, Haibin Yan
While conventional methods focus on generating pseudo-labels for unlabeled samples as supplements for training, the structural nature of 3D point cloud data facilitates the composition of objects and backgrounds to synthesize realistic scenes.
1 code implementation • 6 May 2024 • Zheng Zhu, XiaoFeng Wang, Wangbo Zhao, Chen Min, Nianchen Deng, Min Dou, Yuqi Wang, Botian Shi, Kai Wang, Chi Zhang, Yang You, Zhaoxiang Zhang, Dawei Zhao, Liang Xiao, Jian Zhao, Jiwen Lu, Guan Huang
General world models represent a crucial pathway toward achieving Artificial General Intelligence (AGI), serving as the cornerstone for various applications ranging from virtual environments to decision-making systems.
1 code implementation • CVPR 2024 • Shuofeng Sun, Yongming Rao, Jiwen Lu, Haibin Yan
However, we contend that such implicit high-dimensional structure modeling approch inadequately represents the local geometric structure of point clouds due to the absence of explicit structural information.
1 code implementation • CVPR 2024 • Shiyi Zhang, Sule Bai, Guangyi Chen, Lei Chen, Jiwen Lu, Junle Wang, Yansong Tang
NAE is a more challenging task because it requires both narrative flexibility and evaluation rigor.
2 code implementations • CVPR 2023 • Shiyi Zhang, Wenxun Dai, Sujia Wang, Xiangwei Shen, Jiwen Lu, Jie zhou, Yansong Tang
Action quality assessment (AQA) has become an emerging topic since it can be extensively applied in numerous scenarios.
1 code implementation • CVPR 2024 • Yixuan Zhu, Ao Li, Yansong Tang, Wenliang Zhao, Jie zhou, Jiwen Lu
The recovery of occluded human meshes presents challenges for current methods due to the difficulty in extracting effective image features under severe occlusion.
1 code implementation • CVPR 2024 • Hancheng Ye, Chong Yu, Peng Ye, Renqiu Xia, Yansong Tang, Jiwen Lu, Tao Chen, Bo Zhang
Recent Vision Transformer Compression (VTC) works mainly follow a two-stage scheme, where the importance score of each model unit is first evaluated or preset in each submodule, followed by the sparsity score evaluation according to the target sparsity constraint.
1 code implementation • 19 Mar 2024 • Zuyan Liu, Yuhao Dong, Yongming Rao, Jie zhou, Jiwen Lu
In the realm of vision-language understanding, the proficiency of models in interpreting and reasoning over visual content has become a cornerstone for numerous applications.
Ranked #130 on
Visual Question Answering
on MM-Vet
1 code implementation • 16 Mar 2024 • Zhiheng Li, Muheng Li, Jixuan Fan, Lei Chen, Yansong Tang, Jiwen Lu, Jie zhou
The appearance embedding models the characteristics of low-resolution inputs to deal with photometric variations at different scales, and the pixel-based deformation field learns RGB differences which result from the deviations between the real-world and simulated degradations at arbitrary coordinates.
1 code implementation • 13 Mar 2024 • Guanxing Lu, Shiyi Zhang, Ziwei Wang, Changliu Liu, Jiwen Lu, Yansong Tang
Performing language-conditioned robotic manipulation tasks in unstructured environments is highly demanded for general intelligent robots.
no code implementations • CVPR 2024 • Xiuwei Xu, Chong Xia, Ziwei Wang, Linqing Zhao, Yueqi Duan, Jie zhou, Jiwen Lu
To this end, we propose an adapter-based plug-and-play module for the backbone of 3D scene perception model, which constructs memory to cache and aggregate the extracted RGB-D features to empower offline models with temporal learning ability.
1 code implementation • CVPR 2024 • JianJian Cao, Peng Ye, Shengze Li, Chong Yu, Yansong Tang, Jiwen Lu, Tao Chen
To this end, we propose a novel framework named Multimodal Alignment-Guided Dynamic Token Pruning (MADTP) for accelerating various VLTs.
1 code implementation • 19 Jan 2024 • Borui Zhang, Wenzhao Zheng, Jie zhou, Jiwen Lu
Rigorousness and clarity are both essential for interpretations of DNNs to engender human trust.
no code implementations • 18 Jan 2024 • XiaoFeng Wang, Zheng Zhu, Guan Huang, Boyuan Wang, Xinze Chen, Jiwen Lu
World models play a crucial role in understanding and predicting the dynamics of the world, which is essential for video generation.
no code implementations • CVPR 2024 • Haowen Sun, Yueqi Duan, Juncheng Yan, Yifan Liu, Jiwen Lu
Nowadays leveraging 2D images and pre-trained models to guide 3D point cloud feature representation has shown a remarkable potential to boost the performance of 3D fundamental models.
no code implementations • CVPR 2024 • Linqing Zhao, Xiuwei Xu, Ziwei Wang, Yunpeng Zhang, Borui Zhang, Wenzhao Zheng, Dalong Du, Jie zhou, Jiwen Lu
In this paper we present a tensor decomposition and low-rank recovery approach (LowRankOcc) for vision-based 3D semantic occupancy prediction.
1 code implementation • 14 Dec 2023 • Chubin Zhang, Juncheng Yan, Yi Wei, Jiaxin Li, Li Liu, Yansong Tang, Yueqi Duan, Jiwen Lu
Occupancy prediction reconstructs 3D structures of surrounding environments.
no code implementations • 12 Dec 2023 • Guanxing Lu, Ziwei Wang, Changliu Liu, Jiwen Lu, Yansong Tang
Embodied Instruction Following (EIF) requires agents to complete human instruction by interacting objects in complicated surrounding environments.
1 code implementation • CVPR 2024 • Xiaoke Huang, JianFeng Wang, Yansong Tang, Zheng Zhang, Han Hu, Jiwen Lu, Lijuan Wang, Zicheng Liu
We propose a method to efficiently equip the Segment Anything Model (SAM) with the ability to generate regional captions.
1 code implementation • 27 Nov 2023 • Wenzhao Zheng, Weiliang Chen, Yuanhui Huang, Borui Zhang, Yueqi Duan, Jiwen Lu
In this paper, we explore a new framework of learning a world model, OccWorld, in the 3D Occupancy space to simultaneously predict the movement of the ego car and the evolution of the surrounding scenes.
1 code implementation • CVPR 2024 • Yuanhui Huang, Wenzhao Zheng, Borui Zhang, Jie zhou, Jiwen Lu
Our SelfOcc outperforms the previous best method SceneRF by 58. 7% using a single frame as input on SemanticKITTI and is the first self-supervised work that produces reasonable 3D occupancy for surround cameras on nuScenes.
1 code implementation • 2 Nov 2023 • Borui Zhang, Baotong Tian, Wenzhao Zheng, Jie zhou, Jiwen Lu
Shapley values have emerged as a widely accepted and trustworthy tool, grounded in theoretical axioms, for addressing challenges posed by black-box models like deep neural networks.
1 code implementation • NeurIPS 2023 • Yinan Liang, Ziwei Wang, Xiuwei Xu, Yansong Tang, Jie zhou, Jiwen Lu
Due to the high price and heavy energy consumption of GPUs, deploying deep models on IoT devices such as microcontrollers makes significant contributions for ecological AI.
no code implementations • 9 Oct 2023 • Zhenyu Wu, Xiuwei Xu, Ziwei Wang, Chong Xia, Linqing Zhao, Jiwen Lu, Haibin Yan
Existing methods only consider fixed frames of input data for a single detector, such as monocular RGB-D images or point clouds reconstructed from dense multi-view RGB-D images.
1 code implementation • ICCV 2023 • Zhiheng Li, Wenjia Geng, Muheng Li, Lei Chen, Yansong Tang, Jiwen Lu, Jie zhou
By this means, our model explores all sorts of reliable sub-relations within an action sequence in the condensed action space.
1 code implementation • ICCV 2023 • Junlong Li, Bingyao Yu, Yongming Rao, Jie zhou, Jiwen Lu
The core of our method consists of a global instance assignment strategy and a spatio-temporal enhancement module, which improve the temporal consistency of the features from two aspects.
1 code implementation • 18 Sep 2023 • XiaoFeng Wang, Zheng Zhu, Guan Huang, Xinze Chen, Jiagang Zhu, Jiwen Lu
The established world model holds immense potential for the generation of high-quality driving videos, and driving policies for safe maneuvering.
2 code implementations • 11 Sep 2023 • Chengkun Wang, Wenzhao Zheng, Zheng Zhu, Jie zhou, Jiwen Lu
This paper proposes an introspective deep metric learning (IDML) framework for uncertainty-aware comparisons of images.
1 code implementation • 31 Aug 2023 • Sicheng Zuo, Wenzhao Zheng, Yuanhui Huang, Jie zhou, Jiwen Lu
To address this, we propose a cylindrical tri-perspective view to represent point clouds effectively and comprehensively and a PointOcc model to process them efficiently.
1 code implementation • ICCV 2023 • Ziyi Wang, Xumin Yu, Yongming Rao, Jie zhou, Jiwen Lu
In this paper, we propose a novel 3D-to-2D generative pre-training method that is adaptable to any point cloud model.
Ranked #8 on
3D Part Segmentation
on ShapeNet-Part
1 code implementation • 4 Jul 2023 • Zhenyu Wu, Ziwei Wang, Xiuwei Xu, Jiwen Lu, Haibin Yan
Equipping embodied agents with commonsense is important for robots to successfully complete complex human instructions in general environments.
1 code implementation • CVPR 2024 • Changyuan Wang, Ziwei Wang, Xiuwei Xu, Yansong Tang, Jie zhou, Jiwen Lu
On the contrary, we design group-wise quantization functions for activation discretization in different timesteps and sample the optimal timestep for informative calibration image generation, so that our quantized diffusion model can reduce the discretization errors with negligible computational overhead.
1 code implementation • 5 May 2023 • Xiuwei Xu, Zhihao Sun, Ziwei Wang, Hongmin Liu, Jie zhou, Jiwen Lu
Specifically, we theoretically derive a dynamic spatial pruning (DSP) strategy to prune the redundant spatial representation of 3D scene in a cascade manner according to the distribution of objects.
1 code implementation • 28 Apr 2023 • Yuejian Wu, Linqing Zhao, Jiwen Lu, Haibin Yan
In addition to the shape and location constraints, we design a quality-aware classification loss to adaptively supervise each positive proposal so that the discriminative power can be further boosted.
1 code implementation • 13 Apr 2023 • Ziwei Wang, Jiwen Lu, Han Xiao, Shengyu Liu, Jie zhou
On the contrary, we obtain the optimal efficient networks by directly optimizing the compression policy with an accurate performance predictor, where the ultrafast automated model compression for various computational cost constraint is achieved without complex compression policy search and evaluation.
1 code implementation • 11 Apr 2023 • Hui Li, Tianyang Xu, Xiao-Jun Wu, Jiwen Lu, Josef Kittler
In particular we adopt a learnable representation approach to the fusion task, in which the construction of the fusion network architecture is guided by the optimisation algorithm producing the learnable model.
no code implementations • CVPR 2023 • Xiuwei Xu, Ziwei Wang, Jie zhou, Jiwen Lu
In this paper, we propose binary sparse convolutional networks called BSC-Net for efficient point cloud analysis.
1 code implementation • 23 Mar 2023 • Xiaoke Huang, Yiji Cheng, Yansong Tang, Xiu Li, Jie zhou, Jiwen Lu
Moreover, only minutes of optimization is enough for plausible reconstruction results.
2 code implementations • ICCV 2023 • Yi Wei, Linqing Zhao, Wenzhao Zheng, Zheng Zhu, Jie zhou, Jiwen Lu
Towards a more comprehensive perception of a 3D scene, in this paper, we propose a SurroundOcc method to predict the 3D occupancy with multi-camera images.
1 code implementation • ICCV 2023 • XiaoFeng Wang, Zheng Zhu, Wenbo Xu, Yunpeng Zhang, Yi Wei, Xu Chi, Yun Ye, Dalong Du, Jiwen Lu, Xingang Wang
Towards a comprehensive benchmarking of surrounding perception algorithms, we propose OpenOccupancy, which is the first surrounding semantic occupancy perception benchmark.
2 code implementations • ICCV 2023 • Wenliang Zhao, Yongming Rao, Zuyan Liu, Benlin Liu, Jie zhou, Jiwen Lu
In this paper, we propose VPD (Visual Perception with a pre-trained Diffusion model), a new framework that exploits the semantic information of a pre-trained text-to-image diffusion model in visual perception tasks.
no code implementations • 23 Feb 2023 • Zhenyu Wu, Ziwei Wang, Jiwen Lu, Haibin Yan
Then we fuse the feature maps representing the visual information of multi-view RGB images and the pixel affinity learned from the clutter point cloud, where the acquired instance segmentation masks of multi-view RGB images are projected to partition the clutter point cloud.
3 code implementations • CVPR 2023 • Yuanhui Huang, Wenzhao Zheng, Yunpeng Zhang, Jie zhou, Jiwen Lu
To lift image features to the 3D TPV space, we further propose a transformer-based TPV encoder (TPVFormer) to obtain the TPV features effectively.
Ranked #1 on
Prediction Of Occupancy Grid Maps
on nuScenes
1 code implementation • NeurIPS 2023 • Wenliang Zhao, Lujia Bai, Yongming Rao, Jie zhou, Jiwen Lu
Diffusion probabilistic models (DPMs) have demonstrated a very promising ability in high-resolution image synthesis.
1 code implementation • 11 Jan 2023 • Xumin Yu, Yongming Rao, Ziyi Wang, Jiwen Lu, Jie zhou
In this paper, we present a new method that reformulates point cloud completion as a set-to-set translation problem and design a new model, called PoinTr, which adopts a Transformer encoder-decoder architecture for point cloud completion.
Ranked #2 on
Point Cloud Completion
on ShapeNet
1 code implementation • CVPR 2023 • Shuai Shen, Wenliang Zhao, Zibin Meng, Wanhua Li, Zheng Zhu, Jie zhou, Jiwen Lu
In this way, the proposed DiffTalk is capable of producing high-quality talking head videos in synchronization with the source audio, and more importantly, it can be naturally generalized across different identities without any further fine-tuning.
1 code implementation • CVPR 2023 • Chengkun Wang, Wenzhao Zheng, Junlong Li, Jie zhou, Jiwen Lu
Learning a generalizable and comprehensive similarity metric to depict the semantic discrepancies between images is the foundation of many computer vision tasks.
1 code implementation • CVPR 2023 • Wenliang Zhao, Yongming Rao, Weikang Shi, Zuyan Liu, Jie zhou, Jiwen Lu
Unlike previous work that relies on carefully designed network architectures and loss functions to fuse the information from the source and target faces, we reformulate the face swapping as a conditional inpainting task, performed by a powerful diffusion model guided by the desired face attributes (e. g., identity and landmarks).
no code implementations • ICCV 2023 • Shuai Shen, Wanhua Li, Xiaobing Wang, Dafeng Zhang, Zhezhu Jin, Jie zhou, Jiwen Lu
Furthermore, we develop a neighbor-aware proxy generator that fuses the features describing various attributes into a proxy feature to build a bridge among different sub-clusters and reduce the intra-class variance.
1 code implementation • 18 Dec 2022 • Borui Zhang, Wenzhao Zheng, Jie zhou, Jiwen Lu
Deep learning has revolutionized human society, yet the black-box nature of deep neural networks hinders further application to reliability-demanded industries.
1 code implementation • CVPR 2023 • Yansong Tang, Jinpeng Liu, Aoyang Liu, Bin Yang, Wenxun Dai, Yongming Rao, Jiwen Lu, Jie zhou, Xiu Li
With the continuously thriving popularity around the world, fitness activity analytic has become an emerging research topic in computer vision.
1 code implementation • CVPR 2023 • Muheng Li, Yueqi Duan, Jie zhou, Jiwen Lu
With the rising industrial attention to 3D virtual modeling technology, generating novel 3D content based on specified conditions (e. g. text) has become a hot issue.
1 code implementation • 17 Nov 2022 • Haojun Jiang, Jianke Zhang, Rui Huang, Chunjiang Ge, Zanlin Ni, Jiwen Lu, Jie zhou, Shiji Song, Gao Huang
However, as pre-trained models are scaling up, fully fine-tuning them on text-video retrieval datasets has a high risk of overfitting.
no code implementations • 17 Nov 2022 • Sichao Huang, Ziwei Wang, Jie zhou, Jiwen Lu
We compare our approach with existing robotic packing methods for irregular objects in a physics simulator.
1 code implementation • 15 Nov 2022 • Chengkun Wang, Wenzhao Zheng, Xian Sun, Jiwen Lu, Jie zhou
We propose to learn a global probabilistic distribution for each pixel in the patch and a probabilistic metric to model the distance between distributions.
1 code implementation • 15 Oct 2022 • An Tao, Yueqi Duan, Yingqi Wang, Jiwen Lu, Jie zhou
To address this issue, we propose a Leaded Gradient Method (LGM) and show the significant effects of the lagged gradient.
1 code implementation • ICCV 2023 • Han Xiao, Wenzhao Zheng, Zheng Zhu, Jie zhou, Jiwen Lu
Data mixing strategies (e. g., CutMix) have shown the ability to greatly improve the performance of convolutional neural networks (CNNs).
1 code implementation • ICCV 2023 • Chengkun Wang, Wenzhao Zheng, Zheng Zhu, Jie zhou, Jiwen Lu
The pretrain-finetune paradigm in modern computer vision facilitates the success of self-supervised learning, which tends to achieve better transferability than supervised learning.
1 code implementation • 22 Aug 2022 • Yunpeng Zhang, Wenzhao Zheng, Zheng Zhu, Guan Huang, Jie zhou, Jiwen Lu
First, we extract multi-scale features and generate the perspective object proposals on each monocular image.
no code implementations • 7 Aug 2022 • Quan Zheng, Ziwei Wang, Jie zhou, Jiwen Lu
Explaining deep convolutional neural networks has been recently drawing increasing attention since it helps to understand the networks' internal operations and why they make certain decisions.
1 code implementation • 4 Aug 2022 • Ziyi Wang, Xumin Yu, Yongming Rao, Jie zhou, Jiwen Lu
Nowadays, pre-training big models on large-scale datasets has become a crucial topic in deep learning.
Ranked #21 on
3D Part Segmentation
on ShapeNet-Part
8 code implementations • 28 Jul 2022 • Yongming Rao, Wenliang Zhao, Yansong Tang, Jie zhou, Ser-Nam Lim, Jiwen Lu
In this paper, we show that the key ingredients behind the vision Transformers, namely input-adaptive, long-range and high-order spatial interactions, can also be efficiently implemented with a convolution-based framework.
Ranked #23 on
Semantic Segmentation
on ADE20K
1 code implementation • 26 Jul 2022 • Cheng Ma, Jingyi Zhang, Jie zhou, Jiwen Lu
On the other hand, we propose a parallel network which includes two branches of cascaded lookup tables which process different components of the input low-resolution images.
1 code implementation • 24 Jul 2022 • Shuai Shen, Wanhua Li, Zheng Zhu, Yueqi Duan, Jie zhou, Jiwen Lu
Thus the facial radiance field can be flexibly adjusted to the new identity with few reference images.
1 code implementation • 18 Jul 2022 • Wanhua Li, Zhexuan Cao, Jianjiang Feng, Jie zhou, Jiwen Lu
As each sample is annotated with multiple attribute labels, these "words" will naturally form an unordered but meaningful "sentence", which depicts the semantic information of the corresponding sample.
1 code implementation • 17 Jul 2022 • Yansong Tang, Xingyu Liu, Xumin Yu, Danyang Zhang, Jiwen Lu, Jie zhou
Different from the conventional adversarial learning-based approaches for UDA, we utilize a self-supervision scheme to reduce the domain shift between two skeleton-based action datasets.
1 code implementation • 12 Jul 2022 • Wanhua Li, Jiwen Lu, Abudukelimu Wuerkaixi, Jianjiang Feng, Jie zhou
Unlike most existing personalized methods that learn the parameters of a personalized estimator for each person in the training set, our method learns the mapping from identity information to age estimator parameters.
Ranked #1 on
Age Estimation
on ChaLearn 2015
1 code implementation • 4 Jul 2022 • Yongming Rao, Zuyan Liu, Wenliang Zhao, Jie zhou, Jiwen Lu
We extend our method to hierarchical models including CNNs and hierarchical vision Transformers as well as more complex dense prediction tasks that require structured feature maps by formulating a more generic dynamic spatial sparsification framework with progressive sparsification and asymmetric computation for different spatial locations.
1 code implementation • CVPR 2022 • Han Xiao, Ziwei Wang, Zheng Zhu, Jie zhou, Jiwen Lu
Differentiable architecture search (DARTS) acquires the optimal architectures by optimizing the architecture parameters with gradient descent, which significantly reduces the search cost.
1 code implementation • 6 Jun 2022 • Wanhua Li, Xiaoke Huang, Zheng Zhu, Yansong Tang, Xiu Li, Jie zhou, Jiwen Lu
In this paper, we propose to learn the rank concepts from the rich semantic CLIP latent space.
Ranked #1 on
Few-shot Age Estimation
on MORPH Album2
1 code implementation • CVPR 2022 • Ziyi Wang, Yongming Rao, Xumin Yu, Jie zhou, Jiwen Lu
Conventional point cloud semantic segmentation methods usually employ an encoder-decoder architecture, where mid-level features are locally aggregated to extract geometric information.
1 code implementation • 19 May 2022 • Yunpeng Zhang, Zheng Zhu, Wenzhao Zheng, JunJie Huang, Guan Huang, Jie zhou, Jiwen Lu
Specifically, BEVerse first performs shared feature extraction and lifting to generate 4D BEV representations from multi-timestamp and multi-view images.
Ranked #15 on
Robust Camera Only 3D Object Detection
on nuScenes-C
2 code implementations • 9 May 2022 • Wenzhao Zheng, Chengkun Wang, Jie zhou, Jiwen Lu
This paper proposes an introspective deep metric learning (IDML) framework for uncertainty-aware comparisons of images.
1 code implementation • ICCV 2021 • Xianda Guo, Zheng Zhu, Tian Yang, Beibei Lin, JunJie Huang, Jiankang Deng, Guan Huang, Jie zhou, Jiwen Lu
To the best of our knowledge, this is the first large-scale dataset for gait recognition in the wild.
no code implementations • 21 Apr 2022 • Zheng Zhu, Guan Huang, Jiankang Deng, Yun Ye, JunJie Huang, Xinze Chen, Jiagang Zhu, Tian Yang, Dalong Du, Jiwen Lu, Jie zhou
For a comprehensive evaluation of face matchers, three recognition tasks are performed under standard, masked and unbiased settings, respectively.
no code implementations • CVPR 2022 • Yu Zheng, Yueqi Duan, Jiwen Lu, Jie zhou, Qi Tian
A bathtub in a library, a sink in an office, a bed in a laundry room -- the counter-intuition suggests that scene provides important prior knowledge for 3D object detection, which instructs to eliminate the ambiguous detection of similar objects.
1 code implementation • CVPR 2022 • Jinglin Xu, Yongming Rao, Xumin Yu, Guangyi Chen, Jie zhou, Jiwen Lu
Most existing action quality assessment methods rely on the deep features of an entire video to predict the score, which is less reliable due to the non-transparent inference process and poor interpretability.
1 code implementation • 7 Apr 2022 • Yi Wei, Linqing Zhao, Wenzhao Zheng, Zheng Zhu, Yongming Rao, Guan Huang, Jiwen Lu, Jie zhou
In this paper, we propose a SurroundDepth method to incorporate the information from multiple surrounding views to predict depth maps across cameras.
no code implementations • IEEE Transactions on Image Processing 2022 • Wencheng Zhu, Yucheng Han, Jiwen Lu, Jie zhou
Then, we construct a temporal graph by using the aggregated representations of spatial graphs.
Ranked #1 on
Video Summarization
on TvSum
(using extra training data)
1 code implementation • CVPR 2022 • Borui Zhang, Wenzhao Zheng, Jie zhou, Jiwen Lu
This paper proposes an attributable visual similarity learning (AVSL) framework for a more accurate and explainable similarity measure between images.
Ranked #3 on
Metric Learning
on CARS196
(using extra training data)
1 code implementation • 28 Mar 2022 • Yi Wei, Zibu Wei, Yongming Rao, Jiaxin Li, Jie zhou, Jiwen Lu
In this paper, we propose the LiDAR Distillation to bridge the domain gap induced by different LiDAR beams for 3D object detection.
no code implementations • 26 Mar 2022 • Sha Yuan, Hanyu Zhao, Shuai Zhao, Jiahong Leng, Yangxiao Liang, Xiaozhi Wang, Jifan Yu, Xin Lv, Zhou Shao, Jiaao He, Yankai Lin, Xu Han, Zhenghao Liu, Ning Ding, Yongming Rao, Yizhao Gao, Liang Zhang, Ming Ding, Cong Fang, Yisen Wang, Mingsheng Long, Jing Zhang, Yinpeng Dong, Tianyu Pang, Peng Cui, Lingxiao Huang, Zheng Liang, HuaWei Shen, HUI ZHANG, Quanshi Zhang, Qingxiu Dong, Zhixing Tan, Mingxuan Wang, Shuo Wang, Long Zhou, Haoran Li, Junwei Bao, Yingwei Pan, Weinan Zhang, Zhou Yu, Rui Yan, Chence Shi, Minghao Xu, Zuobai Zhang, Guoqiang Wang, Xiang Pan, Mengjie Li, Xiaoyu Chu, Zijun Yao, Fangwei Zhu, Shulin Cao, Weicheng Xue, Zixuan Ma, Zhengyan Zhang, Shengding Hu, Yujia Qin, Chaojun Xiao, Zheni Zeng, Ganqu Cui, Weize Chen, Weilin Zhao, Yuan YAO, Peng Li, Wenzhao Zheng, Wenliang Zhao, Ziyi Wang, Borui Zhang, Nanyi Fei, Anwen Hu, Zenan Ling, Haoyang Li, Boxi Cao, Xianpei Han, Weidong Zhan, Baobao Chang, Hao Sun, Jiawen Deng, Chujie Zheng, Juanzi Li, Lei Hou, Xigang Cao, Jidong Zhai, Zhiyuan Liu, Maosong Sun, Jiwen Lu, Zhiwu Lu, Qin Jin, Ruihua Song, Ji-Rong Wen, Zhouchen Lin, LiWei Wang, Hang Su, Jun Zhu, Zhifang Sui, Jiajun Zhang, Yang Liu, Xiaodong He, Minlie Huang, Jian Tang, Jie Tang
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.
1 code implementation • CVPR 2022 • Muheng Li, Lei Chen, Yueqi Duan, Zhilan Hu, Jianjiang Feng, Jie zhou, Jiwen Lu
The generated text prompts are paired with corresponding video clips, and together co-train the text encoder and the video encoder via a contrastive approach.
Ranked #6 on
Action Segmentation
on GTEA
(using extra training data)
1 code implementation • CVPR 2022 • Tianpei Gu, Guangyi Chen, Junlong Li, Chunze Lin, Yongming Rao, Jie zhou, Jiwen Lu
Human behavior has the nature of indeterminacy, which requires the pedestrian trajectory prediction system to model the multi-modality of future motion states.
2 code implementations • CVPR 2022 • Xiuwei Xu, Yifan Wang, Yu Zheng, Yongming Rao, Jie zhou, Jiwen Lu
In this paper, we propose a weakly-supervised approach for 3D object detection, which makes it possible to train a strong 3D detector with position-level annotations (i. e. annotations of object centers).
1 code implementation • 22 Jan 2022 • Mantang Guo, Junhui Hou, Jing Jin, Hui Liu, Huanqiang Zeng, Jiwen Lu
To this end, we propose content-aware warping, which adaptively learns the interpolation weights for pixels of a relatively large neighborhood from their contextual information via a lightweight neural network.
no code implementations • 20 Jan 2022 • Kun Song, Junwei Han, Gong Cheng, Jiwen Lu, Feiping Nie
In this paper, we reveal that metric learning would suffer from serious inseparable problem if without informative sample mining.
no code implementations • CVPR 2022 • Yunpeng Zhang, Wenzhao Zheng, Zheng Zhu, Guan Huang, Dalong Du, Jie zhou, Jiwen Lu
In this paper, we propose a general method to learn appropriate embeddings for dimension estimation in monocular 3D object detection.
2 code implementations • 22 Dec 2021 • Liang Pan, Tong Wu, Zhongang Cai, Ziwei Liu, Xumin Yu, Yongming Rao, Jiwen Lu, Jie zhou, Mingye Xu, Xiaoyuan Luo, Kexue Fu, Peng Gao, Manning Wang, Yali Wang, Yu Qiao, Junsheng Zhou, Xin Wen, Peng Xiang, Yu-Shen Liu, Zhizhong Han, Yuanjie Yan, Junyi An, Lifa Zhu, Changwei Lin, Dongrui Liu, Xin Li, Francisco Gómez-Fernández, Qinlong Wang, Yang Yang
Based on the MVP dataset, this paper reports methods and results in the Multi-View Partial Point Cloud Challenge 2021 on Completion and Registration.
1 code implementation • 17 Dec 2021 • An Tao, Yueqi Duan, He Wang, Ziyi Wu, Pengliang Ji, Haowen Sun, Jie zhou, Jiwen Lu
It results in a serious issue of lagged gradient, making the learned attack at the current step ineffective due to the architecture changes afterward.
1 code implementation • CVPR 2022 • Yongming Rao, Wenliang Zhao, Guangyi Chen, Yansong Tang, Zheng Zhu, Guan Huang, Jie zhou, Jiwen Lu
In this work, we present a new framework for dense prediction by implicitly and explicitly leveraging the pre-trained knowledge from CLIP.
2 code implementations • CVPR 2022 • Xumin Yu, Lulu Tang, Yongming Rao, Tiejun Huang, Jie zhou, Jiwen Lu
Inspired by BERT, we devise a Masked Point Modeling (MPM) task to pre-train point cloud Transformers.
Ranked #17 on
Few-Shot 3D Point Cloud Classification
on ModelNet40 5-way (10-shot)
(using extra training data)
3D Point Cloud Linear Classification
Few-Shot 3D Point Cloud Classification
+2
1 code implementation • 17 Oct 2021 • Yinghuan Shi, Jian Zhang, Tong Ling, Jiwen Lu, Yefeng Zheng, Qian Yu, Lei Qi, Yang Gao
In semi-supervised medical image segmentation, most previous works draw on the common assumption that higher entropy means higher uncertainty.
1 code implementation • 26 Sep 2021 • Cheng Ma, Yongming Rao, Jiwen Lu, Jie zhou
Firstly, we propose SPSR with gradient guidance (SPSR-G) by exploiting gradient maps of images to guide the recovery in two aspects.
no code implementations • 6 Sep 2021 • Wanhua Li, Jiwen Lu, Abudukelimu Wuerkaixi, Jianjiang Feng, Jie zhou
To address this, we propose a Star-shaped Reasoning Graph Network (S-RGN).
Ranked #1 on
Kinship Verification
on KinFaceW-I
1 code implementation • ICCV 2021 • Yi Wei, Shaohui Liu, Yongming Rao, Wang Zhao, Jiwen Lu, Jie zhou
In this work, we present a new multi-view depth estimation method that utilizes both conventional reconstruction and learning-based priors over the recently proposed neural radiance fields (NeRF).
1 code implementation • 1 Sep 2021 • Haotong Qin, Yifu Ding, Xiangguo Zhang, Jiakai Wang, Xianglong Liu, Jiwen Lu
We first give a theoretical analysis that the diversity of synthetic samples is crucial for the data-free quantization, while in existing approaches, the synthetic data completely constrained by BN statistics experimentally exhibit severe homogenization at distribution and sample levels.
1 code implementation • ICCV 2021 • Wenzhao Zheng, Borui Zhang, Jiwen Lu, Jie zhou
This paper presents a deep relational metric learning (DRML) framework for image clustering and retrieval.
1 code implementation • ICCV 2021 • Xumin Yu, Yongming Rao, Ziyi Wang, Zuyan Liu, Jiwen Lu, Jie zhou
In this paper, we present a new method that reformulates point cloud completion as a set-to-set translation problem and design a new model, called PoinTr that adopts a transformer encoder-decoder architecture for point cloud completion.
Ranked #1 on
Point Cloud Completion
on ShapeNet
(Chamfer Distance L2 metric)
1 code implementation • ICCV 2021 • Yongming Rao, Guangyi Chen, Jiwen Lu, Jie zhou
Unlike most existing methods that learn visual attention based on conventional likelihood, we propose to learn the attention with counterfactual causality, which provides a tool to measure the attention quality and a powerful supervisory signal to guide the learning process.
Ranked #2 on
Few-Shot Learning
on FGVC Aircraft
2 code implementations • ICCV 2021 • Yongming Rao, Benlin Liu, Yi Wei, Jiwen Lu, Cho-Jui Hsieh, Jie zhou
In particular, we propose to generate random layouts of a scene by making use of the objects in the synthetic CAD dataset and learn the 3D scene representation by applying object-level contrastive learning on two random scenes generated from the same set of synthetic objects.
1 code implementation • ICCV 2021 • Xumin Yu, Yongming Rao, Wenliang Zhao, Jiwen Lu, Jie zhou
Assessing action quality is challenging due to the subtle differences between videos and large variations in scores.
Ranked #2 on
Action Quality Assessment
on AQA-7
no code implementations • 16 Aug 2021 • Zheng Zhu, Guan Huang, Jiankang Deng, Yun Ye, JunJie Huang, Xinze Chen, Jiagang Zhu, Tian Yang, Jia Guo, Jiwen Lu, Dalong Du, Jie zhou
There are second phase of the challenge till October 1, 2021 and on-going leaderboard.
1 code implementation • ICCV 2021 • Wenliang Zhao, Yongming Rao, Ziyi Wang, Jiwen Lu, Jie zhou
Our method is model-agnostic, which can be applied to off-the-shelf backbone networks and metric learning methods.
Ranked #16 on
Metric Learning
on CUB-200-2011
1 code implementation • 11 Aug 2021 • Guangyi Chen, Tianpei Gu, Jiwen Lu, Jin-An Bao, Jie zhou
Experimental results demonstrate the superiority of our method, which outperforms the state-of-the-art methods by a large margin with limited computational cost.
Ranked #19 on
Person Re-Identification
on Market-1501
1 code implementation • ICCV 2021 • Ziwei Wang, Han Xiao, Jiwen Lu, Jie zhou
On the contrary, our GMPQ searches the mixed-quantization policy that can be generalized to largescale datasets with only a small amount of data, so that the search cost is significantly reduced without performance degradation.
1 code implementation • ICCV 2021 • Ziwei Wang, Yunsong Wang, Ziyi Wu, Jiwen Lu, Jie zhou
In this paper, we propose an instance similarity learning (ISL) method for unsupervised feature representation.
1 code implementation • ICCV 2021 • Guangyi Chen, Junlong Li, Nuoxing Zhou, Liangliang Ren, Jiwen Lu
In this paper, we present a distribution discrimination (DisDis) method to predict personalized motion patterns by distinguishing the potential distributions.
1 code implementation • ICCV 2021 • Guangyi Chen, Junlong Li, Jiwen Lu, Jie zhou
Most existing methods learn to predict future trajectories by behavior clues from history trajectories and interaction clues from environments.
1 code implementation • 4 Jul 2021 • Linqing Zhao, Jiwen Lu, Jie zhou
To address this, we employ a late fusion strategy where we first learn the geometric and contextual similarities between the input and back-projected (from 2D pixels) point clouds and utilize them to guide the fusion of two modalities to further exploit complementary information.
Ranked #25 on
Semantic Segmentation
on ScanNet
(test mIoU metric)
4 code implementations • NeurIPS 2021 • Yongming Rao, Wenliang Zhao, Zheng Zhu, Jiwen Lu, Jie zhou
Recent advances in self-attention and pure multi-layer perceptrons (MLP) models for vision have shown great potential in achieving promising performance with fewer inductive biases.
Ranked #1 on
Image Classification
on ImageNet
(Hardware Burden metric)
no code implementations • CVPR 2021 • Guoli Wang, Jiaqi Ma, Qian Zhang, Jiwen Lu, Jie zhou
Many of them settle it by generating fake frontal faces from extreme ones, whereas they are tough to maintain the identity information with high computational consumption and uncontrolled disturbances.
1 code implementation • CVPR 2021 • Wenzhao Zheng, Chengkun Wang, Jiwen Lu, Jie zhou
In this paper, we propose a deep compositional metric learning (DCML) framework for effective and generalizable similarity measurement between images.
1 code implementation • CVPR 2021 • Shuyan Li, Xiu Li, Jiwen Lu, Jie zhou
Most existing unsupervised video hashing methods are built on unidirectional models with less reliable training objectives, which underuse the correlations among frames and the similarity structure between videos.
1 code implementation • CVPR 2021 • Shuai Shen, Wanhua Li, Zheng Zhu, Guan Huang, Dalong Du, Jiwen Lu, Jie zhou
To address the dilemma of large-scale training and efficient inference, we propose the STructure-AwaRe Face Clustering (STAR-FC) method.
1 code implementation • NeurIPS 2021 • Yongming Rao, Wenliang Zhao, Benlin Liu, Jiwen Lu, Jie zhou, Cho-Jui Hsieh
Based on this observation, we propose a dynamic token sparsification framework to prune redundant tokens progressively and dynamically based on the input.
Ranked #1 on
Image Classification
on ImageNet
(Hardware Burden metric)
1 code implementation • 17 May 2021 • Yi Wei, Shang Su, Jiwen Lu, Jie zhou
To tackle this problem, we propose frustum-aware geometric reasoning (FGR) to detect vehicles in point clouds without any 3D annotations.
3 code implementations • CVPR 2021 • Yunpeng Zhang, Jiwen Lu, Jie zhou
The precise localization of 3D objects from a single image without depth information is a highly challenging problem.
Ranked #9 on
Monocular 3D Object Detection
on KITTI Cars Moderate
no code implementations • 6 Apr 2021 • Jiabin Zhang, Zheng Zhu, Jiwen Lu, JunJie Huang, Guan Huang, Jie zhou
To make a better trade-off between accuracy and efficiency, we propose a novel multi-person pose estimation framework, SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation (SIMPLE).
no code implementations • CVPR 2021 • Wanhua Li, Shiwei Wang, Jiwen Lu, Jianjiang Feng, Jie zhou
In the end, the samples in the unbalanced train batch are re-weighted by the learned meta-miner to optimize the kinship models.
Ranked #1 on
Kinship Verification
on KinFaceW-II
1 code implementation • CVPR 2021 • Wanhua Li, Xiaoke Huang, Jiwen Lu, Jianjiang Feng, Jie zhou
An ordinal distribution constraint is proposed to exploit the ordinal nature of regression.
Ranked #2 on
Age Estimation
on mebeblurf
Aesthetics Quality Assessment
Age And Gender Classification
+3
1 code implementation • 24 Mar 2021 • Shuai Shen, Wanhua Li, Zheng Zhu, Guan Huang, Dalong Du, Jiwen Lu, Jie zhou
To address the dilemma of large-scale training and efficient inference, we propose the STructure-AwaRe Face Clustering (STAR-FC) method.
no code implementations • CVPR 2021 • Zheng Zhu, Guan Huang, Jiankang Deng, Yun Ye, JunJie Huang, Xinze Chen, Jiagang Zhu, Tian Yang, Jiwen Lu, Dalong Du, Jie zhou
In this paper, we contribute a new million-scale face benchmark containing noisy 4M identities/260M faces (WebFace260M) and cleaned 2M identities/42M faces (WebFace42M) training data, as well as an elaborately designed time-constrained evaluation protocol.
Ranked #1 on
Face Verification
on IJB-C
(training dataset metric)
1 code implementation • 18 Feb 2021 • Wencheng Zhu, Jiahao Li, Jiwen Lu, Jie zhou
Specifically, we first compute a pixel-wise similarity matrix by using representations of reference and target pixels and then select top-rank reference pixels for target pixel classification.
no code implementations • 2 Feb 2021 • Cheng Ma, Jiwen Lu, Jie zhou
As hashing becomes an increasingly appealing technique for large-scale image retrieval, multi-label hashing is also attracting more attention for the ability to exploit multi-level semantic contents.
no code implementations • 19 Jan 2021 • Lei He, Jiwen Lu, Guanghui Wang, Shiyu Song, Jie zhou
In this paper, we first introduce the concept of semantic objectness to exploit the geometric relationship of these two tasks through an analysis of the imaging process, then propose a Semantic Object Segmentation and Depth Estimation Network (SOSD-Net) based on the objectness assumption.
Ranked #93 on
Semantic Segmentation
on NYU Depth v2
no code implementations • ICCV 2021 • Bingyao Yu, Wanhua Li, Xiu Li, Jiwen Lu, Jie zhou
In this paper, we propose a frequency-aware spatiotemporal transformers for deep In this paper, we propose a Frequency-Aware Spatiotemporal Transformer (FAST) for video inpainting detection, which aims to simultaneously mine the traces of video inpainting from spatial, temporal, and frequency domains.
1 code implementation • 18 Dec 2020 • An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie zhou
Most existing point cloud instance and semantic segmentation methods rely heavily on strong supervision signals, which require point-level labels for every point in the scene.
1 code implementation • CVPR 2021 • Yi Wei, Ziyi Wang, Yongming Rao, Jiwen Lu, Jie zhou
In this paper, we propose a Point-Voxel Recurrent All-Pairs Field Transforms (PV-RAFT) method to estimate scene flow from point clouds.
1 code implementation • 1 Dec 2020 • Wencheng Zhu, Jiwen Lu, Jiahao Li, and Jie Zhou
In this paper, we propose a Detect-to-Summarize network (DSNet) framework for supervised video summarization.
Ranked #2 on
Video Summarization
on TvSum
(using extra training data)
no code implementations • ECCV 2020 • Lijie Liu, Chufan Wu, Jiwen Lu, Lingxi Xie, Jie zhou, Qi Tian
Monocular 3D object detection aims to extract the 3D position and properties of objects from a 2D input image.
Ranked #16 on
Vehicle Pose Estimation
on KITTI Cars Hard
no code implementations • ECCV 2020 • Benlin Liu, Yongming Rao, Jiwen Lu, Jie zhou, Cho-Jui Hsieh
Knowledge Distillation (KD) has been one of the most popu-lar methods to learn a compact model.
1 code implementation • ECCV 2020 • Wanhua Li, Yueqi Duan, Jiwen Lu, Jianjiang Feng, Jie zhou
Human beings are fundamentally sociable -- that we generally organize our social lives in terms of relations with other people.
Ranked #2 on
Visual Social Relationship Recognition
on PIPA
1 code implementation • CVPR 2020 • Yansong Tang, Zanlin Ni, Jiahuan Zhou, Danyang Zhang, Jiwen Lu, Ying Wu, Jie zhou
Assessing action quality from videos has attracted growing attention in recent years.
Ranked #4 on
Action Quality Assessment
on AQA-7
no code implementations • 12 May 2020 • Shan Gu, Jianjiang Feng, Jiwen Lu, Jie zhou
Given a pair of fingerprints to match, we bypass the minutiae extraction step and take uniformly sampled points as key points.
no code implementations • 22 Apr 2020 • Wanhua Li, Yingqiang Zhang, Kangchen Lv, Jiwen Lu, Jianjiang Feng, Jie zhou
In this paper, we propose a graph-based kinship reasoning (GKR) network for kinship verification, which aims to effectively perform relational reasoning on the extracted features of an image pair.
Ranked #3 on
Kinship Verification
on KinFaceW-II
1 code implementation • CVPR 2020 • Yongming Rao, Jiwen Lu, Jie zhou
Based on this hypothesis, we propose to learn point cloud representation by bidirectional reasoning between the local structures at different abstraction hierarchies and the global shape without human supervision.
2 code implementations • CVPR 2020 • Cheng Ma, Yongming Rao, Yean Cheng, Ce Chen, Jiwen Lu, Jie zhou
In this paper, we propose a structure-preserving super resolution method to alleviate the above issue while maintaining the merits of GAN-based methods to generate perceptual-pleasant details.
Ranked #58 on
Image Super-Resolution
on Urban100 - 4x upscaling
1 code implementation • CVPR 2020 • Cheng Ma, Zhenyu Jiang, Yongming Rao, Jiwen Lu, Jie zhou
In this paper, we propose a deep face super-resolution (FSR) method with iterative collaboration between two recurrent networks which focus on facial image recovery and landmark estimation respectively.
no code implementations • 20 Mar 2020 • Yansong Tang, Jiwen Lu, Jie zhou
We believe the introduction of the COIN dataset will promote the future in-depth research on instructional video analysis for the community.
2 code implementations • CVPR 2020 • Ziwei Wang, Ziyi Wu, Jiwen Lu, Jie zhou
Conventional network binarization methods directly quantize the weights and activations in one-stage or two-stage detectors with constrained representational capacity, so that the information redundancy in the networks causes numerous false positives and degrades the performance significantly.
no code implementations • 23 Feb 2020 • Hao-Chiang Shao, Kang-Yu Liu, Chia-Wen Lin, Jiwen Lu
With their aid, DotFAN can learn a disentangled face representation and effectively generate face images of various facial attributes while preserving the identity of augmented faces.
no code implementations • 19 Dec 2019 • Peiyu Yu, Yongming Rao, Jiwen Lu, Jie zhou
Humans are able to perform fast and accurate object pose estimation even under severe occlusion by exploiting learned object model priors from everyday life.
1 code implementation • 18 Oct 2019 • Yinghuan Shi, Tiexin Qin, Yong liu, Jiwen Lu, Yang Gao, Dinggang Shen
By introducing an unified optimization goal, DeepAugNet intends to combine the data augmentation and the deep model training in an end-to-end training manner which is realized by simultaneously training a hybrid architecture of dueling deep Q-learning algorithm and a surrogate deep model.
1 code implementation • ICCV 2019 • Yongcheng Liu, Bin Fan, Gaofeng Meng, Jiwen Lu, Shiming Xiang, Chunhong Pan
Point cloud processing is very challenging, as the diverse shapes formed by irregular points are often indistinguishable.
Ranked #25 on
3D Part Segmentation
on ShapeNet-Part
no code implementations • ICLR 2019 • Shaohui Liu*, Yi Wei*, Jiwen Lu, Jie zhou
Unlike most existing evaluation frameworks which transfer the representation of ImageNet inception model to map images onto the feature space, our framework uses a specialized encoder to acquire fine-grained domain-specific representation.
no code implementations • CVPR 2019 • Lijie Liu, Jiwen Lu, Chunjing Xu, Qi Tian, Jie zhou
In this paper, we propose to learn a deep fitting degree scoring network for monocular 3D object detection, which aims to score fitting degree between proposals and object conclusively.
Ranked #7 on
Vehicle Pose Estimation
on KITTI Cars Hard
no code implementations • CVPR 2019 • Yi Wei, Shaohui Liu, Wang Zhao, Jiwen Lu, Jie zhou
In this paper, we present a new perspective towards image-based shape generation.
no code implementations • CVPR 2019 • Wanhua Li, Jiwen Lu, Jianjiang Feng, Chunjing Xu, Jie zhou, Qi Tian
Existing methods for age estimation usually apply a divide-and-conquer strategy to deal with heterogeneous data caused by the non-stationary aging process.
Ranked #2 on
Age Estimation
on FGNET
2 code implementations • CVPR 2019 • Wenzhao Zheng, Zhaodong Chen, Jiwen Lu, Jie zhou
This paper presents a hardness-aware deep metric learning (HDML) framework.
Ranked #30 on
Metric Learning
on CUB-200-2011
(using extra training data)
no code implementations • CVPR 2019 • Yansong Tang, Dajun Ding, Yongming Rao, Yu Zheng, Danyang Zhang, Lili Zhao, Jiwen Lu, Jie zhou
There are substantial instructional videos on the Internet, which enables us to acquire knowledge for completing various tasks.
no code implementations • ECCV 2018 • Chunze Lin, Jiwen Lu, Gang Wang, Jie zhou
In this paper, we propose a graininess-aware deep feature learning method for pedestrian detection.
no code implementations • ECCV 2018 • Lei Chen, Jiwen Lu, Zhanjie Song, Jie zhou
In this paper, we propose a part-activated deep reinforcement learning (PA-DRL) for action prediction.
no code implementations • ECCV 2018 • Liangliang Ren, Xin Yuan, Jiwen Lu, Ming Yang, Jie Zhou
Visual tracking is confronted by the dilemma to locate a target both}accurately and efficiently, and make decisions online whether and how to adapt the appearance model or even restart tracking.
no code implementations • ECCV 2018 • Xudong Lin, Yueqi Duan, Qiyuan Dong, Jiwen Lu, Jie zhou
Deep metric learning has been extensively explored recently, which trains a deep neural network to produce discriminative embedding features.
no code implementations • ECCV 2018 • Xin Yuan, Liangliang Ren, Jiwen Lu, Jie zhou
In this paper, we propose a simple yet effective relaxation-free method to learn more effective binary codes via policy gradient for scalable image search.
no code implementations • ECCV 2018 • Liangliang Ren, Jiwen Lu, Zifeng Wang, Qi Tian, Jie zhou
To address this, we develop a deep prediction-decision network in our C-DRL, which simultaneously detects and predicts objects under a unified network via deep reinforcement learning.
no code implementations • ECCV 2018 • Minghao Guo, Jiwen Lu, Jie zhou
In this paper, we propose a dual-agent deep reinforcement learning (DADRL) method for deformable face tracking, which generates bounding boxes and detects facial landmarks interactively from face videos.
no code implementations • CVPR 2018 • Yansong Tang, Yi Tian, Jiwen Lu, Peiyang Li, Jie zhou
In this paper, we propose a deep progressive reinforcement learning (DPRL) method for action recognition in skeleton-based videos, which aims to distil the most informative frames and discard ambiguous frames in sequences for recognizing actions.
Ranked #3 on
Skeleton Based Action Recognition
on UT-Kinect
no code implementations • CVPR 2018 • Yueqi Duan, Wenzhao Zheng, Xudong Lin, Jiwen Lu, Jie zhou
Learning an effective distance metric between image pairs plays an important role in visual analysis, where the training procedure largely relies on hard negative samples.