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.
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.
In this paper, we propose a novel 3D-to-2D generative pre-training method that is adaptable to any point cloud model.
Ranked #6 on 3D Part Segmentation on ShapeNet-Part
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.
Ranked #1 on Monocular Depth Estimation on NYU-Depth V2
Diffusion probabilistic models (DPMs) have demonstrated a very promising ability in high-resolution image synthesis.
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.
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).
With the continuously thriving popularity around the world, fitness activity analytic has become an emerging research topic in computer vision.
To solve this problem, we propose to apply optimal transport to match the vision and text modalities.
Nowadays, pre-training big models on large-scale datasets has become a crucial topic in deep learning.
Ranked #12 on 3D Point Cloud Classification on ScanObjectNN (using extra training data)
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 #20 on Semantic Segmentation on ADE20K
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.
Conventional point cloud semantic segmentation methods usually employ an encoder-decoder architecture, where mid-level features are locally aggregated to extract geometric information.
In this paper, we propose a SurroundDepth method to incorporate the information from multiple surrounding views to predict depth maps across cameras.
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.
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.
Human behavior has the nature of indeterminacy, which requires the pedestrian trajectory prediction system to model the multi-modality of future motion states.
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).
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.
In this work, we present a new framework for dense prediction by implicitly and explicitly leveraging the pre-trained knowledge from CLIP.
Inspired by BERT, we devise a Masked Point Modeling (MPM) task to pre-train point cloud Transformers.
Ranked #10 on Few-Shot 3D Point Cloud Classification on ModelNet40 5-way (10-shot) (using extra training data)
Firstly, we propose SPSR with gradient guidance (SPSR-G) by exploiting gradient maps of images to guide the recovery in two aspects.
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).
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 #7 on Fine-Grained Image Classification on FGVC Aircraft
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
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.
Assessing action quality is challenging due to the subtle differences between videos and large variations in scores.
Ranked #2 on Action Quality Assessment on MTL-AQA
Our method is model-agnostic, which can be applied to off-the-shelf backbone networks and metric learning methods.
Ranked #15 on Metric Learning on CUB-200-2011
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 #9 on Image Classification on Stanford Cars (using extra training data)
Based on this observation, we propose a dynamic token sparsification framework to prune redundant tokens progressively and dynamically based on the input.
Ranked #319 on Image Classification on ImageNet
In this paper, we propose a Point-Voxel Recurrent All-Pairs Field Transforms (PV-RAFT) method to estimate scene flow from point clouds.
Knowledge Distillation (KD) has been one of the most popu-lar methods to learn a compact model.
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.
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 #39 on Image Super-Resolution on Urban100 - 4x upscaling
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.
Humans are able to perform fast and accurate object pose estimation even under severe occlusion by exploiting learned object model priors from everyday life.
We present a generic, flexible and 3D rotation invariant framework based on spherical symmetry for point cloud recognition.
Ranked #44 on 3D Part Segmentation on ShapeNet-Part
There are substantial instructional videos on the Internet, which enables us to acquire knowledge for completing various tasks.
In this paper, we propose a simple yet effective method to learn globally optimized detector for object detection, which is a simple modification to the standard cross-entropy gradient inspired by the REINFORCE algorithm.
In this paper, we propose an attention-aware deep reinforcement learning (ADRL) method for video face recognition, which aims to discard the misleading and confounding frames and find the focuses of attention in face videos for person recognition.
In this paper, we propose a discriminative aggregation network (DAN) for video face recognition, which aims to integrate information from video frames effectively and efficiently.