Searcharxiv⌕ Search

arXiv subjects

Wentao Zhu

Publications and source records attributed to Wentao Zhu.

At least 55 records · Page 3Linked to original sources
arXiv2024

OpenMEDLab: An Open-source Platform for Multi-modality Foundation Models in Medicine

The emerging trend of advancing generalist artificial intelligence, such as GPTv4 and Gemini, has reshaped the landscape of research (academia and industry) in machine learning and many other research areas. However, domain-specific applications of such foundation models (e.g., in medicine) remain untouched or often at their very early stages. It will require an individual set of transfer learning and model adaptation techniques by further expanding and injecting these models with domain knowledge and data. The development of such technologies could be largely accelerated if the bundle of data, algorithms, and pre-trained foundation models were gathered together and open-sourced in an organized manner. In this work, we present OpenMEDLab, an open-source platform for multi-modality foundation models. It encapsulates not only solutions of pioneering attempts in prompting and fine-tuning large language and vision models for frontline clinical and bioinformatic applications but also building domain-specific foundation models with large-scale multi-modal medical data. Importantly, it opens access to a group of pre-trained foundation models for various medical image modalities, clinical text, protein engineering, etc. Inspiring and competitive results are also demonstrated for each collected approach and model in a variety of benchmarks for downstream tasks. We welcome researchers in the field of medical artificial intelligence to continuously contribute cutting-edge methods and models to OpenMEDLab, which can be accessed via https://github.com/openmedlab.

cs.CV↗
arXiv2024

Deformable Audio Transformer for Audio Event Detection

Transformers have achieved promising results on a variety of tasks. However, the quadratic complexity in self-attention computation has limited the applications, especially in low-resource settings and mobile or edge devices. Existing works have proposed to exploit hand-crafted attention patterns to reduce computation complexity. However, such hand-crafted patterns are data-agnostic and may not be optimal. Hence, it is likely that relevant keys or values are being reduced, while less important ones are still preserved. Based on this key insight, we propose a novel deformable audio Transformer for audio recognition, named DATAR, where a deformable attention equipping with a pyramid transformer backbone is constructed and learnable. Such an architecture has been proven effective in prediction tasks,~\textit{e.g.}, event classification. Moreover, we identify that the deformable attention map computation may over-simplify the input feature, which can be further enhanced. Hence, we introduce a learnable input adaptor to alleviate this issue, and DATAR achieves state-of-the-art performance.

cs.SD↗
arXiv2024

TPC-ViT: Token Propagation Controller for Efficient Vision Transformer

Vision transformers (ViTs) have achieved promising results on a variety of Computer Vision tasks, however their quadratic complexity in the number of input tokens has limited their application specially in resource-constrained settings. Previous approaches that employ gradual token reduction to address this challenge assume that token redundancy in one layer implies redundancy in all the following layers. We empirically demonstrate that this assumption is often not correct, i.e., tokens that are redundant in one layer can be useful in later layers. We employ this key insight to propose a novel token propagation controller (TPC) that incorporates two different token-distributions, i.e., pause probability and restart probability to control the reduction and reuse of tokens respectively, which results in more efficient token utilization. To improve the estimates of token distributions, we propose a smoothing mechanism that acts as a regularizer and helps remove noisy outliers. Furthermore, to improve the training-stability of our proposed TPC, we introduce a model stabilizer that is able to implicitly encode local image structures and minimize accuracy fluctuations during model training. We present extensive experimental results on the ImageNet-1K dataset using DeiT, LV-ViT and Swin models to demonstrate the effectiveness of our proposed method. For example, compared to baseline models, our proposed method improves the inference speed of the DeiT-S by 250% while increasing the classification accuracy by 1.0%.

cs.CV↗
arXiv2024

Efficient Multiscale Multimodal Bottleneck Transformer for Audio-Video Classification

In recent years, researchers combine both audio and video signals to deal with challenges where actions are not well represented or captured by visual cues. However, how to effectively leverage the two modalities is still under development. In this work, we develop a multiscale multimodal Transformer (MMT) that leverages hierarchical representation learning. Particularly, MMT is composed of a novel multiscale audio Transformer (MAT) and a multiscale video Transformer [43]. To learn a discriminative cross-modality fusion, we further design multimodal supervised contrastive objectives called audio-video contrastive loss (AVC) and intra-modal contrastive loss (IMC) that robustly align the two modalities. MMT surpasses previous state-of-the-art approaches by 7.3% and 2.1% on Kinetics-Sounds and VGGSound in terms of the top-1 accuracy without external training data. Moreover, the proposed MAT significantly outperforms AST [28] by 22.2%, 4.4% and 4.7% on three public benchmark datasets, and is about 3% more efficient based on the number of FLOPs and 9.8% more efficient based on GPU memory usage.

cs.CV↗
arXiv2024

Efficient Selective Audio Masked Multimodal Bottleneck Transformer for Audio-Video Classification

Audio and video are two most common modalities in the mainstream media platforms, e.g., YouTube. To learn from multimodal videos effectively, in this work, we propose a novel audio-video recognition approach termed audio video Transformer, AVT, leveraging the effective spatio-temporal representation by the video Transformer to improve action recognition accuracy. For multimodal fusion, simply concatenating multimodal tokens in a cross-modal Transformer requires large computational and memory resources, instead we reduce the cross-modality complexity through an audio-video bottleneck Transformer. To improve the learning efficiency of multimodal Transformer, we integrate self-supervised objectives, i.e., audio-video contrastive learning, audio-video matching, and masked audio and video learning, into AVT training, which maps diverse audio and video representations into a common multimodal representation space. We further propose a masked audio segment loss to learn semantic audio activities in AVT. Extensive experiments and ablation studies on three public datasets and two in-house datasets consistently demonstrate the effectiveness of the proposed AVT. Specifically, AVT outperforms its previous state-of-the-art counterparts on Kinetics-Sounds by 8%. AVT also surpasses one of the previous state-of-the-art video Transformers [25] by 10% on VGGSound by leveraging the audio signal. Compared to one of the previous state-of-the-art multimodal methods, MBT [32], AVT is 1.3% more efficient in terms of FLOPs and improves the accuracy by 3.8% on Epic-Kitchens-100.

cs.CV↗
arXiv2023

Human Motion Generation: A Survey

Human motion generation aims to generate natural human pose sequences and shows immense potential for real-world applications. Substantial progress has been made recently in motion data collection technologies and generation methods, laying the foundation for increasing interest in human motion generation. Most research within this field focuses on generating human motions based on conditional signals, such as text, audio, and scene contexts. While significant advancements have been made in recent years, the task continues to pose challenges due to the intricate nature of human motion and its implicit relationship with conditional signals. In this survey, we present a comprehensive literature review of human motion generation, which, to the best of our knowledge, is the first of its kind in this field. We begin by introducing the background of human motion and generative models, followed by an examination of representative methods for three mainstream sub-tasks: text-conditioned, audio-conditioned, and scene-conditioned human motion generation. Additionally, we provide an overview of common datasets and evaluation metrics. Lastly, we discuss open problems and outline potential future research directions. We hope that this survey could provide the community with a comprehensive glimpse of this rapidly evolving field and inspire novel ideas that address the outstanding challenges.

cs.CV↗
arXiv2023

Full-length-body CBCT imaging in upright position with robotic-arm system: a simulation study

Upright position CT scans make it possible for full-length-body imaging at conditions more relevant to daily situations, but the substantial weight of the upright CT scanners increases the risks to floor's stability and patients'safety. Robotic-arm CBCT systems are supposed to be a better solution for this task, but such systems still face challenges including long scanning time and low reconstruction quality. To address the above challenges, this paper proposes a novel method to calculate optimal scanning pitch based on data completeness analysis, which can complete the whole-body scan in the shortest time without a significant decline in image quality. Besides, an FDK-style reconstruction method based on normalized projections is proposed to obtain fast image reconstruction. Extensive experiments prove the effectiveness of the proposed optimal scanning trajectory. Qualitative and quantitative comparisons with FDK and iterative algorithms show that the proposed reconstruction method can obtain high imaging quality with reasonable computation costs. The method proposed in this paper is expected to promote the application of robotic-arm CBCT systems in orthopedic functional analysis.

physics.med-ph↗
arXiv2023

Social Motion Prediction with Cognitive Hierarchies

Humans exhibit a remarkable capacity for anticipating the actions of others and planning their own actions accordingly. In this study, we strive to replicate this ability by addressing the social motion prediction problem. We introduce a new benchmark, a novel formulation, and a cognition-inspired framework. We present Wusi, a 3D multi-person motion dataset under the context of team sports, which features intense and strategic human interactions and diverse pose distributions. By reformulating the problem from a multi-agent reinforcement learning perspective, we incorporate behavioral cloning and generative adversarial imitation learning to boost learning efficiency and generalization. Furthermore, we take into account the cognitive aspects of the human social action planning process and develop a cognitive hierarchy framework to predict strategic human social interactions. We conduct comprehensive experiments to validate the effectiveness of our proposed dataset and approach. Code and data are available at https://walter0807.github.io/Social-CH/.

cs.CV↗
arXiv2023

ChimpACT: A Longitudinal Dataset for Understanding Chimpanzee Behaviors

Understanding the behavior of non-human primates is crucial for improving animal welfare, modeling social behavior, and gaining insights into distinctively human and phylogenetically shared behaviors. However, the lack of datasets on non-human primate behavior hinders in-depth exploration of primate social interactions, posing challenges to research on our closest living relatives. To address these limitations, we present ChimpACT, a comprehensive dataset for quantifying the longitudinal behavior and social relations of chimpanzees within a social group. Spanning from 2015 to 2018, ChimpACT features videos of a group of over 20 chimpanzees residing at the Leipzig Zoo, Germany, with a particular focus on documenting the developmental trajectory of one young male, Azibo. ChimpACT is both comprehensive and challenging, consisting of 163 videos with a cumulative 160,500 frames, each richly annotated with detection, identification, pose estimation, and fine-grained spatiotemporal behavior labels. We benchmark representative methods of three tracks on ChimpACT: (i) tracking and identification, (ii) pose estimation, and (iii) spatiotemporal action detection of the chimpanzees. Our experiments reveal that ChimpACT offers ample opportunities for both devising new methods and adapting existing ones to solve fundamental computer vision tasks applied to chimpanzee groups, such as detection, pose estimation, and behavior analysis, ultimately deepening our comprehension of communication and sociality in non-human primates.

cs.CV↗
arXiv2023

A Multi-Scale Spatial Transformer U-Net for Simultaneously Automatic Reorientation and Segmentation of 3D Nuclear Cardiac Images

Accurate reorientation and segmentation of the left ventricular (LV) is essential for the quantitative analysis of myocardial perfusion imaging (MPI), in which one critical step is to reorient the reconstructed transaxial nuclear cardiac images into standard short-axis slices for subsequent image processing. Small-scale LV myocardium (LV-MY) region detection and the diverse cardiac structures of individual patients pose challenges to LV segmentation operation. To mitigate these issues, we propose an end-to-end model, named as multi-scale spatial transformer UNet (MS-ST-UNet), that involves the multi-scale spatial transformer network (MSSTN) and multi-scale UNet (MSUNet) modules to perform simultaneous reorientation and segmentation of LV region from nuclear cardiac images. The proposed method is trained and tested using two different nuclear cardiac image modalities: 13N-ammonia PET and 99mTc-sestamibi SPECT. We use a multi-scale strategy to generate and extract image features with different scales. Our experimental results demonstrate that the proposed method significantly improves the reorientation and segmentation performance. This joint learning framework promotes mutual enhancement between reorientation and segmentation tasks, leading to cutting edge performance and an efficient image processing workflow. The proposed end-to-end deep network has the potential to reduce the burden of manual delineation for cardiac images, thereby providing multimodal quantitative analysis assistance for physicists.

eess.IV↗
arXiv2023

Towards Comprehensive Monocular Depth Estimation: Multiple Heads Are Better Than One

Depth estimation attracts widespread attention in the computer vision community. However, it is still quite difficult to recover an accurate depth map using only one RGB image. We observe a phenomenon that existing methods tend to fail in different cases, caused by differences in network architecture, loss function and so on. In this work, we investigate into the phenomenon and propose to integrate the strengths of multiple weak depth predictor to build a comprehensive and accurate depth predictor, which is critical for many real-world applications, e.g., 3D reconstruction. Specifically, we construct multiple base (weak) depth predictors by utilizing different Transformer-based and convolutional neural network (CNN)-based architectures. Transformer establishes long-range correlation while CNN preserves local information ignored by Transformer due to the spatial inductive bias. Therefore, the coupling of Transformer and CNN contributes to the generation of complementary depth estimates, which are essential to achieve a comprehensive depth predictor. Then, we design mixers to learn from multiple weak predictions and adaptively fuse them into a strong depth estimate. The resultant model, which we refer to as Transformer-assisted depth ensembles (TEDepth). On the standard NYU-Depth-v2 and KITTI datasets, we thoroughly explore how the neural ensembles affect the depth estimation and demonstrate that our TEDepth achieves better results than previous state-of-the-art approaches. To validate the generalizability across cameras, we directly apply the models trained on NYU-Depth-v2 to the SUN RGB-D dataset without any fine-tuning, and the superior results emphasize its strong generalizability.

cs.CV↗
arXiv2023

UPL-SFDA: Uncertainty-aware Pseudo Label Guided Source-Free Domain Adaptation for Medical Image Segmentation

Domain Adaptation (DA) is important for deep learning-based medical image segmentation models to deal with testing images from a new target domain. As the source-domain data are usually unavailable when a trained model is deployed at a new center, Source-Free Domain Adaptation (SFDA) is appealing for data and annotation-efficient adaptation to the target domain. However, existing SFDA methods have a limited performance due to lack of sufficient supervision with source-domain images unavailable and target-domain images unlabeled. We propose a novel Uncertainty-aware Pseudo Label guided (UPL) SFDA method for medical image segmentation. Specifically, we propose Target Domain Growing (TDG) to enhance the diversity of predictions in the target domain by duplicating the pre-trained model's prediction head multiple times with perturbations. The different predictions in these duplicated heads are used to obtain pseudo labels for unlabeled target-domain images and their uncertainty to identify reliable pseudo labels. We also propose a Twice Forward pass Supervision (TFS) strategy that uses reliable pseudo labels obtained in one forward pass to supervise predictions in the next forward pass. The adaptation is further regularized by a mean prediction-based entropy minimization term that encourages confident and consistent results in different prediction heads. UPL-SFDA was validated with a multi-site heart MRI segmentation dataset, a cross-modality fetal brain segmentation dataset, and a 3D fetal tissue segmentation dataset. It improved the average Dice by 5.54, 5.01 and 6.89 percentage points for the three tasks compared with the baseline, respectively, and outperformed several state-of-the-art SFDA methods.

cs.CV↗
arXiv2023

BROW: Better featuRes fOr Whole slide image based on self-distillation

Whole slide image (WSI) processing is becoming part of the key components of standard clinical diagnosis for various diseases. However, the direct application of conventional image processing algorithms to WSI faces certain obstacles because of WSIs' distinct property: the super-high resolution. The performance of most WSI-related tasks relies on the efficacy of the backbone which extracts WSI patch feature representations. Hence, we proposed BROW, a foundation model for extracting better feature representations for WSIs, which can be conveniently adapted to downstream tasks without or with slight fine-tuning. The model takes transformer architecture, pretrained using self-distillation framework. To improve model's robustness, techniques such as patch shuffling have been employed. Additionally, the model leverages the unique properties of WSIs, utilizing WSI's multi-scale pyramid to incorporate an additional global view, thereby further enhancing its performance. We used both private and public data to make up a large pretraining dataset, containing more than 11000 slides, over 180M extracted patches, encompassing WSIs related to various organs and tissues. To assess the effectiveness of \ourmodel, we run a wide range of downstream tasks, including slide-level subtyping, patch-level classification and nuclei instance segmentation. The results confirmed the efficacy, robustness and good generalization ability of the proposed model. This substantiates its potential as foundation model for WSI feature extraction and highlights promising prospects for its application in WSI processing.

cs.CV↗
arXiv2023

MotionBERT: A Unified Perspective on Learning Human Motion Representations

We present a unified perspective on tackling various human-centric video tasks by learning human motion representations from large-scale and heterogeneous data resources. Specifically, we propose a pretraining stage in which a motion encoder is trained to recover the underlying 3D motion from noisy partial 2D observations. The motion representations acquired in this way incorporate geometric, kinematic, and physical knowledge about human motion, which can be easily transferred to multiple downstream tasks. We implement the motion encoder with a Dual-stream Spatio-temporal Transformer (DSTformer) neural network. It could capture long-range spatio-temporal relationships among the skeletal joints comprehensively and adaptively, exemplified by the lowest 3D pose estimation error so far when trained from scratch. Furthermore, our proposed framework achieves state-of-the-art performance on all three downstream tasks by simply finetuning the pretrained motion encoder with a simple regression head (1-2 layers), which demonstrates the versatility of the learned motion representations. Code and models are available at https://motionbert.github.io/

cs.CV↗
arXiv2023

Classification of lung cancer subtypes on CT images with synthetic pathological priors

The accurate diagnosis on pathological subtypes for lung cancer is of significant importance for the follow-up treatments and prognosis managements. In this paper, we propose self-generating hybrid feature network (SGHF-Net) for accurately classifying lung cancer subtypes on computed tomography (CT) images. Inspired by studies stating that cross-scale associations exist in the image patterns between the same case's CT images and its pathological images, we innovatively developed a pathological feature synthetic module (PFSM), which quantitatively maps cross-modality associations through deep neural networks, to derive the "gold standard" information contained in the corresponding pathological images from CT images. Additionally, we designed a radiological feature extraction module (RFEM) to directly acquire CT image information and integrated it with the pathological priors under an effective feature fusion framework, enabling the entire classification model to generate more indicative and specific pathologically related features and eventually output more accurate predictions. The superiority of the proposed model lies in its ability to self-generate hybrid features that contain multi-modality image information based on a single-modality input. To evaluate the effectiveness, adaptability, and generalization ability of our model, we performed extensive experiments on a large-scale multi-center dataset (i.e., 829 cases from three hospitals) to compare our model and a series of state-of-the-art (SOTA) classification models. The experimental results demonstrated the superiority of our model for lung cancer subtypes classification with significant accuracy improvements in terms of accuracy (ACC), area under the curve (AUC), and F1 score.

eess.IV↗
arXiv2023

PDS-MAR: a fine-grained Projection-Domain Segmentation-based Metal Artifact Reduction method for intraoperative CBCT images with guidewires

Since the invention of modern CT systems, metal artifacts have been a persistent problem. Due to increased scattering, amplified noise, and insufficient data collection, it is more difficult to suppress metal artifacts in cone-beam CT, limiting its use in human- and robot-assisted spine surgeries where metallic guidewires and screws are commonly used. In this paper, we demonstrate that conventional image-domain segmentation-based MAR methods are unable to eliminate metal artifacts for intraoperative CBCT images with guidewires. To solve this problem, we present a fine-grained projection-domain segmentation-based MAR method termed PDS-MAR, in which metal traces are augmented and segmented in the projection domain before being inpainted using triangular interpolation. In addition, a metal reconstruction phase is proposed to restore metal areas in the image domain. The digital phantom study and real CBCT data study demonstrate that the proposed algorithm achieves significantly better artifact suppression than other comparing methods and has the potential to advance the use of intraoperative CBCT imaging in clinical spine surgeries.

physics.med-ph↗
arXiv2023

AutoShot: A Short Video Dataset and State-of-the-Art Shot Boundary Detection

The short-form videos have explosive popularity and have dominated the new social media trends. Prevailing short-video platforms,~\textit{e.g.}, Kuaishou (Kwai), TikTok, Instagram Reels, and YouTube Shorts, have changed the way we consume and create content. For video content creation and understanding, the shot boundary detection (SBD) is one of the most essential components in various scenarios. In this work, we release a new public Short video sHot bOundary deTection dataset, named SHOT, consisting of 853 complete short videos and 11,606 shot annotations, with 2,716 high quality shot boundary annotations in 200 test videos. Leveraging this new data wealth, we propose to optimize the model design for video SBD, by conducting neural architecture search in a search space encapsulating various advanced 3D ConvNets and Transformers. Our proposed approach, named AutoShot, achieves higher F1 scores than previous state-of-the-art approaches, e.g., outperforming TransNetV2 by 4.2%, when being derived and evaluated on our newly constructed SHOT dataset. Moreover, to validate the generalizability of the AutoShot architecture, we directly evaluate it on another three public datasets: ClipShots, BBC and RAI, and the F1 scores of AutoShot outperform previous state-of-the-art approaches by 1.1%, 0.9% and 1.2%, respectively. The SHOT dataset and code can be found in https://github.com/wentaozhu/AutoShot.git .

cs.CV↗
arXiv2023

Selective Structured State-Spaces for Long-Form Video Understanding

Effective modeling of complex spatiotemporal dependencies in long-form videos remains an open problem. The recently proposed Structured State-Space Sequence (S4) model with its linear complexity offers a promising direction in this space. However, we demonstrate that treating all image-tokens equally as done by S4 model can adversely affect its efficiency and accuracy. To address this limitation, we present a novel Selective S4 (i.e., S5) model that employs a lightweight mask generator to adaptively select informative image tokens resulting in more efficient and accurate modeling of long-term spatiotemporal dependencies in videos. Unlike previous mask-based token reduction methods used in transformers, our S5 model avoids the dense self-attention calculation by making use of the guidance of the momentum-updated S4 model. This enables our model to efficiently discard less informative tokens and adapt to various long-form video understanding tasks more effectively. However, as is the case for most token reduction methods, the informative image tokens could be dropped incorrectly. To improve the robustness and the temporal horizon of our model, we propose a novel long-short masked contrastive learning (LSMCL) approach that enables our model to predict longer temporal context using shorter input videos. We present extensive comparative results using three challenging long-form video understanding datasets (LVU, COIN and Breakfast), demonstrating that our approach consistently outperforms the previous state-of-the-art S4 model by up to 9.6% accuracy while reducing its memory footprint by 23%.

cs.CV↗