420 citations · 1.2k across the 58 of their papers we have counts for
32 papers · 1 filter
Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation
Shuangrui Ding, Peisen Zhao, Xiaopeng Zhang +3
Transformers have become the primary backbone of the computer vision community due to their impressive performance. However, the unfriendly computation cost impedes their potential…
ActionPrompt: Action-Guided 3D Human Pose Estimation With Text and Pose Prompting
Hongwei Zheng, Han Li, Bowen Shi +5
Recent 2D-to-3D human pose estimation (HPE) utilizes temporal consistency across sequences to alleviate the depth ambiguity problem but ignore the action related prior knowledge hi…
Hybrid Distillation: Connecting Masked Autoencoders with Contrastive Learners
Bowen Shi, Xiaopeng Zhang, Yaoming Wang +5
Representation learning has been evolving from traditional supervised training to Contrastive Learning (CL) and Masked Image Modeling (MIM). Previous works have demonstrated their…
Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation
Han Li, Bowen Shi, Wenrui Dai +7
There has been a recent surge of interest in introducing transformers to 3D human pose estimation (HPE) due to their powerful capabilities in modeling long-term dependencies. Howev…
Lightweight network towards real-time image denoising on mobile devices
Zhuoqun Liu, Meiguang Jin, Ying Chen +3
Deep convolutional neural networks have achieved great progress in image denoising tasks. However, their complicated architectures and heavy computational cost hinder their deploym…
Motion-inductive Self-supervised Object Discovery in Videos
Shuangrui Ding, Weidi Xie, Yabo Chen +4
In this paper, we consider the task of unsupervised object discovery in videos. Previous works have shown promising results via processing optical flows to segment objects. However…
SdAE: Self-distillated Masked Autoencoder
Yabo Chen, Yuchen Liu, Dongsheng Jiang +4
With the development of generative-based self-supervised learning (SSL) approaches like BeiT and MAE, how to learn good representations by masking random patches of the input image…
Dual Contrastive Learning for Spatio-temporal Representation
Shuangrui Ding, Rui Qian, Hongkai Xiong
Contrastive learning has shown promising potential in self-supervised spatio-temporal representation learning. Most works naively sample different clips to construct positive and n…
Hierarchical Spherical CNNs with Lifting-based Adaptive Wavelets for Pooling and Unpooling
Mingxing Xu, Chenglin Li, Wenrui Dai +4
Pooling and unpooling are two essential operations in constructing hierarchical spherical convolutional neural networks (HS-CNNs) for comprehensive feature learning in the spherica…
Hybrid ISTA: Unfolding ISTA With Convergence Guarantees Using Free-Form Deep Neural Networks
Ziyang Zheng, Wenrui Dai, Duoduo Xue +3
It is promising to solve linear inverse problems by unfolding iterative algorithms (e.g., iterative shrinkage thresholding algorithm (ISTA)) as deep neural networks (DNNs) with lea…
Hierarchical Graph Networks for 3D Human Pose Estimation
Han Li, Bowen Shi, Wenrui Dai +7
Recent 2D-to-3D human pose estimation works tend to utilize the graph structure formed by the topology of the human skeleton. However, we argue that this skeletal topology is too s…
Motion-aware Contrastive Video Representation Learning via Foreground-background Merging
Shuangrui Ding, Maomao Li, Tianyu Yang +5
In light of the success of contrastive learning in the image domain, current self-supervised video representation learning methods usually employ contrastive loss to facilitate vid…
Bag of Instances Aggregation Boosts Self-supervised Distillation
Haohang Xu, Jiemin Fang, Xiaopeng Zhang +5
Recent advances in self-supervised learning have experienced remarkable progress, especially for contrastive learning based methods, which regard each image as well as its augmenta…
Multi-dataset Pretraining: A Unified Model for Semantic Segmentation
Bowen Shi, Xiaopeng Zhang, Haohang Xu +4
Collecting annotated data for semantic segmentation is time-consuming and hard to scale up. In this paper, we for the first time propose a unified framework, termed as Multi-Datase…
Seed the Views: Hierarchical Semantic Alignment for Contrastive Representation Learning
Haohang Xu, Xiaopeng Zhang, Hao Li +3
Self-supervised learning based on instance discrimination has shown remarkable progress. In particular, contrastive learning, which regards each image as well as its augmentations…
Batch Normalization with Enhanced Linear Transformation
Yuhui Xu, Lingxi Xie, Cihang Xie +5
Batch normalization (BN) is a fundamental unit in modern deep networks, in which a linear transformation module was designed for improving BN's flexibility of fitting complex data…
Center-wise Local Image Mixture For Contrastive Representation Learning
Hao Li, Xiaopeng Zhang, Hongkai Xiong
Contrastive learning based on instance discrimination trains model to discriminate different transformations of the anchor sample from other samples, which does not consider the se…
K-Shot Contrastive Learning of Visual Features with Multiple Instance Augmentations
Haohang Xu, Hongkai Xiong, Guo-Jun Qi
In this paper, we propose the -Shot Contrastive Learning (KSCL) of visual features by applying multiple augmentations to investigate the sample variations within individual inst…
Distilling Object Detectors with Task Adaptive Regularization
Ruoyu Sun, Fuhui Tang, Xiaopeng Zhang +2
Current state-of-the-art object detectors are at the expense of high computational costs and are hard to deploy to low-end devices. Knowledge distillation, which aims at training a…
Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events
Weiyao Lin, Huabin Liu, Shizhan Liu +7
Along with the development of modern smart cities, human-centric video analysis has been encountering the challenge of analyzing diverse and complex events in real scenes. A comple…
Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition
Hao Li, Xiaopeng Zhang, Hongkai Xiong +1
Collecting fine-grained labels usually requires expert-level domain knowledge and is prohibitive to scale up. In this paper, we propose Attribute Mix, a data augmentation strategy…
Latency-Aware Differentiable Neural Architecture Search
Yuhui Xu, Lingxi Xie, Xiaopeng Zhang +4
Differentiable neural architecture search methods became popular in recent years, mainly due to their low search costs and flexibility in designing the search space. However, these…
FLAT: Few-Shot Learning via Autoencoding Transformation Regularizers
Haohang Xu, Hongkai Xiong, Guojun Qi
One of the most significant challenges facing a few-shot learning task is the generalizability of the (meta-)model from the base to the novel categories. Most of existing few-shot…
AETv2: AutoEncoding Transformations for Self-Supervised Representation Learning by Minimizing Geodesic Distances in Lie Groups
Feng Lin, Haohang Xu, Houqiang Li +2
Self-supervised learning by predicting transformations has demonstrated outstanding performances in both unsupervised and (semi-)supervised tasks. Among the state-of-the-art method…