arXiv subjects

Ce Zheng

Publications and source records attributed to Ce Zheng.

54 records · Page 3Linked to original sources

arXiv2023

Deep Learning-Based Human Pose Estimation: A Survey

Human pose estimation aims to locate the human body parts and build human body representation (e.g., body skeleton) from input data such as images and videos. It has drawn increasing attention during the past decade and has been utilized in a wide range of applications including human-computer interaction, motion analysis, augmented reality, and virtual reality. Although the recently developed deep learning-based solutions have achieved high performance in human pose estimation, there still remain challenges due to insufficient training data, depth ambiguities, and occlusion. The goal of this survey paper is to provide a comprehensive review of recent deep learning-based solutions for both 2D and 3D pose estimation via a systematic analysis and comparison of these solutions based on their input data and inference procedures. More than 250 research papers since 2014 are covered in this survey. Furthermore, 2D and 3D human pose estimation datasets and evaluation metrics are included. Quantitative performance comparisons of the reviewed methods on popular datasets are summarized and discussed. Finally, the challenges involved, applications, and future research directions are concluded. A regularly updated project page is provided: \url{https://github.com/zczcwh/DL-HPE}

cs.CV↗

arXiv2023

Can Language Models Understand Physical Concepts?

Language models~(LMs) gradually become general-purpose interfaces in the interactive and embodied world, where the understanding of physical concepts is an essential prerequisite. However, it is not yet clear whether LMs can understand physical concepts in the human world. To investigate this, we design a benchmark VEC that covers the tasks of (i) Visual concepts, such as the shape and material of objects, and (ii) Embodied Concepts, learned from the interaction with the world such as the temperature of objects. Our zero (few)-shot prompting results show that the understanding of certain visual concepts emerges as scaling up LMs, but there are still basic concepts to which the scaling law does not apply. For example, OPT-175B performs close to humans with a zero-shot accuracy of 85\% on the material concept, yet behaves like random guessing on the mass concept. Instead, vision-augmented LMs such as CLIP and BLIP achieve a human-level understanding of embodied concepts. Analysis indicates that the rich semantics in visual representation can serve as a valuable source of embodied knowledge. Inspired by this, we propose a distillation method to transfer embodied knowledge from VLMs to LMs, achieving performance gain comparable with that by scaling up the parameters of LMs 134x. Our dataset is available at \url{https://github.com/TobiasLee/VEC}

cs.CL↗

arXiv2023

Can We Edit Factual Knowledge by In-Context Learning?

Previous studies have shown that large language models (LLMs) like GPTs store massive factual knowledge in their parameters. However, the stored knowledge could be false or out-dated. Traditional knowledge editing methods refine LLMs via fine-tuning on texts containing specific knowledge. However, with the increasing scales of LLMs, these gradient-based approaches bring large computation costs. The trend of model-as-a-service also makes it impossible to modify knowledge in black-box LMs. Inspired by in-context learning (ICL), a new paradigm based on demonstration contexts without parameter updating, we explore whether ICL can edit factual knowledge. To answer this question, we give a comprehensive empirical study of ICL strategies. Experiments show that in-context knowledge editing (IKE), without any gradient and parameter updating, achieves a competitive success rate compared to gradient-based methods on GPT-J (6B) but with much fewer side effects, including less over-editing on similar but unrelated facts and less knowledge forgetting on previously stored knowledge. We also apply the method to larger LMs with tens or hundreds of parameters like OPT-175B, which shows the scalability of our method. The code is available at https://github.com/Zce1112zslx/IKE.

cs.CL↗

arXiv2023

Part Aware Contrastive Learning for Self-Supervised Action Recognition

In recent years, remarkable results have been achieved in self-supervised action recognition using skeleton sequences with contrastive learning. It has been observed that the semantic distinction of human action features is often represented by local body parts, such as legs or hands, which are advantageous for skeleton-based action recognition. This paper proposes an attention-based contrastive learning framework for skeleton representation learning, called SkeAttnCLR, which integrates local similarity and global features for skeleton-based action representations. To achieve this, a multi-head attention mask module is employed to learn the soft attention mask features from the skeletons, suppressing non-salient local features while accentuating local salient features, thereby bringing similar local features closer in the feature space. Additionally, ample contrastive pairs are generated by expanding contrastive pairs based on salient and non-salient features with global features, which guide the network to learn the semantic representations of the entire skeleton. Therefore, with the attention mask mechanism, SkeAttnCLR learns local features under different data augmentation views. The experiment results demonstrate that the inclusion of local feature similarity significantly enhances skeleton-based action representation. Our proposed SkeAttnCLR outperforms state-of-the-art methods on NTURGB+D, NTU120-RGB+D, and PKU-MMD datasets.

cs.CV↗

arXiv2023

SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition

Fully supervised skeleton-based action recognition has achieved great progress with the blooming of deep learning techniques. However, these methods require sufficient labeled data which is not easy to obtain. In contrast, self-supervised skeleton-based action recognition has attracted more attention. With utilizing the unlabeled data, more generalizable features can be learned to alleviate the overfitting problem and reduce the demand of massive labeled training data. Inspired by the MAE, we propose a spatial-temporal masked autoencoder framework for self-supervised 3D skeleton-based action recognition (SkeletonMAE). Following MAE's masking and reconstruction pipeline, we utilize a skeleton-based encoder-decoder transformer architecture to reconstruct the masked skeleton sequences. A novel masking strategy, named Spatial-Temporal Masking, is introduced in terms of both joint-level and frame-level for the skeleton sequence. This pre-training strategy makes the encoder output generalizable skeleton features with spatial and temporal dependencies. Given the unmasked skeleton sequence, the encoder is fine-tuned for the action recognition task. Extensive experiments show that our SkeletonMAE achieves remarkable performance and outperforms the state-of-the-art methods on both NTU RGB+D and NTU RGB+D 120 datasets.

cs.CV↗

arXiv2023

Annotation-efficient learning for OCT segmentation

Deep learning has been successfully applied to OCT segmentation. However, for data from different manufacturers and imaging protocols, and for different regions of interest (ROIs), it requires laborious and time-consuming data annotation and training, which is undesirable in many scenarios, such as surgical navigation and multi-center clinical trials. Here we propose an annotation-efficient learning method for OCT segmentation that could significantly reduce annotation costs. Leveraging self-supervised generative learning, we train a Transformer-based model to learn the OCT imagery. Then we connect the trained Transformer-based encoder to a CNN-based decoder, to learn the dense pixel-wise prediction in OCT segmentation. These training phases use open-access data and thus incur no annotation costs, and the pre-trained model can be adapted to different data and ROIs without re-training. Based on the greedy approximation for the k-center problem, we also introduce an algorithm for the selective annotation of the target data. We verified our method on publicly-available and private OCT datasets. Compared to the widely-used U-Net model with 100% training data, our method only requires ~10% of the data for achieving the same segmentation accuracy, and it speeds the training up to ~3.5 times. Furthermore, our proposed method outperforms other potential strategies that could improve annotation efficiency. We think this emphasis on learning efficiency may help improve the intelligence and application penetration of OCT-based technologies. Our code and pre-trained model are publicly available at https://github.com/SJTU-Intelligent-Optics-Lab/Annotation-efficient-learning-for-OCT-segmentation.

cs.CV↗

arXiv2023

Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver

The main challenge of monocular 3D object detection is the accurate localization of 3D center. Motivated by a new and strong observation that this challenge can be remedied by a 3D-space local-grid search scheme in an ideal case, we propose a stage-wise approach, which combines the information flow from 2D-to-3D (3D bounding box proposal generation with a single 2D image) and 3D-to-2D (proposal verification by denoising with 3D-to-2D contexts) in a top-down manner. Specifically, we first obtain initial proposals from off-the-shelf backbone monocular 3D detectors. Then, we generate a 3D anchor space by local-grid sampling from the initial proposals. Finally, we perform 3D bounding box denoising at the 3D-to-2D proposal verification stage. To effectively learn discriminative features for denoising highly overlapped proposals, this paper presents a method of using the Perceiver I/O model to fuse the 3D-to-2D geometric information and the 2D appearance information. With the encoded latent representation of a proposal, the verification head is implemented with a self-attention module. Our method, named as MonoXiver, is generic and can be easily adapted to any backbone monocular 3D detectors. Experimental results on the well-established KITTI dataset and the challenging large-scale Waymo dataset show that MonoXiver consistently achieves improvement with limited computation overhead.

cs.CV↗

arXiv2023

PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation

Recently, transformer-based methods have gained significant success in sequential 2D-to-3D lifting human pose estimation. As a pioneering work, PoseFormer captures spatial relations of human joints in each video frame and human dynamics across frames with cascaded transformer layers and has achieved impressive performance. However, in real scenarios, the performance of PoseFormer and its follow-ups is limited by two factors: (a) The length of the input joint sequence; (b) The quality of 2D joint detection. Existing methods typically apply self-attention to all frames of the input sequence, causing a huge computational burden when the frame number is increased to obtain advanced estimation accuracy, and they are not robust to noise naturally brought by the limited capability of 2D joint detectors. In this paper, we propose PoseFormerV2, which exploits a compact representation of lengthy skeleton sequences in the frequency domain to efficiently scale up the receptive field and boost robustness to noisy 2D joint detection. With minimum modifications to PoseFormer, the proposed method effectively fuses features both in the time domain and frequency domain, enjoying a better speed-accuracy trade-off than its precursor. Extensive experiments on two benchmark datasets (i.e., Human3.6M and MPI-INF-3DHP) demonstrate that the proposed approach significantly outperforms the original PoseFormer and other transformer-based variants. Code is released at \url{https://github.com/QitaoZhao/PoseFormerV2}.

cs.CV↗

arXiv2023

FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER

Recently, vision transformers have shown great success in a set of human reconstruction tasks such as 2D human pose estimation (2D HPE), 3D human pose estimation (3D HPE), and human mesh reconstruction (HMR) tasks. In these tasks, feature map representations of the human structural information are often extracted first from the image by a CNN (such as HRNet), and then further processed by transformer to predict the heatmaps (encodes each joint's location into a feature map with a Gaussian distribution) for HPE or HMR. However, existing transformer architectures are not able to process these feature map inputs directly, forcing an unnatural flattening of the location-sensitive human structural information. Furthermore, much of the performance benefit in recent HPE and HMR methods has come at the cost of ever-increasing computation and memory needs. Therefore, to simultaneously address these problems, we propose FeatER, a novel transformer design that preserves the inherent structure of feature map representations when modeling attention while reducing memory and computational costs. Taking advantage of FeatER, we build an efficient network for a set of human reconstruction tasks including 2D HPE, 3D HPE, and HMR. A feature map reconstruction module is applied to improve the performance of the estimated human pose and mesh. Extensive experiments demonstrate the effectiveness of FeatER on various human pose and mesh datasets. For instance, FeatER outperforms the SOTA method MeshGraphormer by requiring 5% of Params and 16% of MACs on Human3.6M and 3DPW datasets. The project webpage is https://zczcwh.github.io/feater_page/.

cs.CV↗

arXiv2023

POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery

Transformer architectures have achieved SOTA performance on the human mesh recovery (HMR) from monocular images. However, the performance gain has come at the cost of substantial memory and computational overhead. A lightweight and efficient model to reconstruct accurate human mesh is needed for real-world applications. In this paper, we propose a pure transformer architecture named POoling aTtention TransformER (POTTER) for the HMR task from single images. Observing that the conventional attention module is memory and computationally expensive, we propose an efficient pooling attention module, which significantly reduces the memory and computational cost without sacrificing performance. Furthermore, we design a new transformer architecture by integrating a High-Resolution (HR) stream for the HMR task. The high-resolution local and global features from the HR stream can be utilized for recovering more accurate human mesh. Our POTTER outperforms the SOTA method METRO by only requiring 7% of total parameters and 14% of the Multiply-Accumulate Operations on the Human3.6M (PA-MPJPE metric) and 3DPW (all three metrics) datasets. The project webpage is https://zczcwh.github.io/potter_page.

cs.CV↗

arXiv2022

Query Your Model with Definitions in FrameNet: An Effective Method for Frame Semantic Role Labeling

Frame Semantic Role Labeling (FSRL) identifies arguments and labels them with frame semantic roles defined in FrameNet. Previous researches tend to divide FSRL into argument identification and role classification. Such methods usually model role classification as naive multi-class classification and treat arguments individually, which neglects label semantics and interactions between arguments and thus hindering performance and generalization of models. In this paper, we propose a query-based framework named ArGument Extractor with Definitions in FrameNet (AGED) to mitigate these problems. Definitions of frames and frame elements (FEs) in FrameNet can be used to query arguments in text. Encoding text-definition pairs can guide models in learning label semantics and strengthening argument interactions. Experiments show that AGED outperforms previous state-of-the-art by up to 1.3 F1-score in two FrameNet datasets and the generalization power of AGED in zero-shot and fewshot scenarios. Our code and technical appendix is available at https://github.com/PKUnlp-icler/AGED.

cs.CL↗

arXiv2022

A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose

Existing deep learning-based human mesh reconstruction approaches have a tendency to build larger networks in order to achieve higher accuracy. Computational complexity and model size are often neglected, despite being key characteristics for practical use of human mesh reconstruction models (e.g. virtual try-on systems). In this paper, we present GTRS, a lightweight pose-based method that can reconstruct human mesh from 2D human pose. We propose a pose analysis module that uses graph transformers to exploit structured and implicit joint correlations, and a mesh regression module that combines the extracted pose feature with the mesh template to reconstruct the final human mesh. We demonstrate the efficiency and generalization of GTRS by extensive evaluations on the Human3.6M and 3DPW datasets. In particular, GTRS achieves better accuracy than the SOTA pose-based method Pose2Mesh while only using 10.2% of the parameters (Params) and 2.5% of the FLOPs on the challenging in-the-wild 3DPW dataset. Code will be publicly available.

cs.CV↗

arXiv2022

A Double-Graph Based Framework for Frame Semantic Parsing

Frame semantic parsing is a fundamental NLP task, which consists of three subtasks: frame identification, argument identification and role classification. Most previous studies tend to neglect relations between different subtasks and arguments and pay little attention to ontological frame knowledge defined in FrameNet. In this paper, we propose a Knowledge-guided Incremental semantic parser with Double-graph (KID). We first introduce Frame Knowledge Graph (FKG), a heterogeneous graph containing both frames and FEs (Frame Elements) built on the frame knowledge so that we can derive knowledge-enhanced representations for frames and FEs. Besides, we propose Frame Semantic Graph (FSG) to represent frame semantic structures extracted from the text with graph structures. In this way, we can transform frame semantic parsing into an incremental graph construction problem to strengthen interactions between subtasks and relations between arguments. Our experiments show that KID outperforms the previous state-of-the-art method by up to 1.7 F1-score on two FrameNet datasets. Our code is availavle at https://github.com/PKUnlp-icler/KID.

cs.CL↗

arXiv2021

3D Human Pose Estimation with Spatial and Temporal Transformers

Transformer architectures have become the model of choice in natural language processing and are now being introduced into computer vision tasks such as image classification, object detection, and semantic segmentation. However, in the field of human pose estimation, convolutional architectures still remain dominant. In this work, we present PoseFormer, a purely transformer-based approach for 3D human pose estimation in videos without convolutional architectures involved. Inspired by recent developments in vision transformers, we design a spatial-temporal transformer structure to comprehensively model the human joint relations within each frame as well as the temporal correlations across frames, then output an accurate 3D human pose of the center frame. We quantitatively and qualitatively evaluate our method on two popular and standard benchmark datasets: Human3.6M and MPI-INF-3DHP. Extensive experiments show that PoseFormer achieves state-of-the-art performance on both datasets. Code is available at \url{https://github.com/zczcwh/PoseFormer}

cs.CV↗

arXiv2020

Automatic Segmentation and Visualization of Choroid in OCT with Knowledge Infused Deep Learning

The choroid provides oxygen and nourishment to the outer retina thus is related to the pathology of various ocular diseases. Optical coherence tomography (OCT) is advantageous in visualizing and quantifying the choroid in vivo. (1) The lower boundary of the choroid (choroid-sclera interface) in OCT is fuzzy, which makes the automatic segmentation difficult and inaccurate. (2) The visualization of the choroid is hindered by the vessel shadows from the superficial layers of the inner retina. In this paper, we propose to incorporate medical and imaging prior knowledge with deep learning to address these two problems. We propose a biomarker infused global-to-local network for the choroid segmentation. It leverages the choroidal thickness, a primary biomarker in clinic, as a constraint to improve the segmentation accuracy. We also design a global-to-local strategy in the choroid segmentation: a global module is used to segment all the retinal and choroidal layers simultaneously for suppressing overfitting and providing global structure information, then a local module is used to refine the segmentation with the biomarker infusion. To eliminate the retinal vessel shadows, we propose a pipeline that firstly use anatomical and OCT imaging knowledge to locate the shadows using their projection on the retinal pigment epithelium layer, then the contents of the choroidal vasculature at the shadow locations are predicted with an edge-to-texture generative adversarial inpainting network. The experiments show our method outperforms the existing methods on both the segmentation and shadow elimination tasks. We further apply the proposed method in a clinical prospective study for understanding the pathology of glaucoma by detecting the structure and vascular changes of the choroid related to the elevation of intra-ocular pressure.

eess.IV↗

arXiv2020

LodoNet: A Deep Neural Network with 2D Keypoint Matchingfor 3D LiDAR Odometry Estimation

Deep learning based LiDAR odometry (LO) estimation attracts increasing research interests in the field of autonomous driving and robotics. Existing works feed consecutive LiDAR frames into neural networks as point clouds and match pairs in the learned feature space. In contrast, motivated by the success of image based feature extractors, we propose to transfer the LiDAR frames to image space and reformulate the problem as image feature extraction. With the help of scale-invariant feature transform (SIFT) for feature extraction, we are able to generate matched keypoint pairs (MKPs) that can be precisely returned to the 3D space. A convolutional neural network pipeline is designed for LiDAR odometry estimation by extracted MKPs. The proposed scheme, namely LodoNet, is then evaluated in the KITTI odometry estimation benchmark, achieving on par with or even better results than the state-of-the-art.

cs.CV↗

arXiv2019

Assessment of Generative Adversarial Networks Model for Synthetic Optical Coherence Tomography Images of Retinal Disorders

Purpose: To assess whether a generative adversarial network (GAN) could synthesize realistic optical coherence tomography (OCT) images that satisfactorily serve as the educational images for retinal specialists and the training datasets for the classification of various retinal disorders using deep learning (DL). Methods: The GANs architecture was adopted to synthesis high-resolution OCT images training on a publicly available OCT dataset including urgent referrals (choroidal neovascularization and diabetic macular edema) and non-urgent referrals (normal and drusen). 400 real and synthetic OCT images were evaluated by 2 retinal specialists to assess image quality. We further trained 2 DL models on either real or synthetic datasets and compared the performance of urgent vs nonurgent referrals diagnosis tested on a local (1000 images from the public dataset) and clinical validation dataset (278 images from Shanghai Shibei Hospital). Results: The image quality of real vs synthetic OCT images was similar as assessed by 2 retinal specialists. The accuracy of discrimination as real vs synthetic OCT images was 59.50% for retinal specialist 1 and 53.67% for retinal specialist 2. For the local dataset, the DL model trained on real (DL_Model_R) and synthetic OCT images (DL_Model_S) had an area under the curve (AUC) of 0.99, and 0.98 respectively. For the clinical dataset, the AUC was 0.94 for DL_Model_R, 0.90 for DL_Model_S. Conclusions: The GAN-synthetic OCT images can be used by clinicians for educational purposes and developing DL algorithms. Translational Relevance: The medical image synthesis based on GANs is promising in human and machine to fulfill clinical tasks.

physics.med-ph↗

arXiv2018

Automated Strabismus Detection for Telemedicine Applications

Strabismus is one of the most influential ophthalmologic diseases in human's life. Timely detection of strabismus contributes to its prognosis and treatment. Telemedicine, which has great potential to alleviate the growing demand of the diagnosis of ophthalmologic diseases, is an effective method to achieve timely strabismus detection. In this paper, a tele strabismus dataset is established by the ophthalmologists. Then an end-to-end framework named as RF-CNN is proposed to achieve automated strabismus detection on the established tele strabismus dataset. RF-CNN first performs eye region segmentation on each individual image, and further classifies the segmented eye regions with deep neural networks. The experimental results on the established tele strabismus dataset demonstrates that the proposed RF-CNN can have a good performance on automated strabismus detection for telemedicine application. Code is made publicly available at: https://github.com/jieWeiLu/Strabismus-Detection-for-Telemedicine-Application.

cs.CV↗