VG4D: Vision-Language Model Goes 4D Video Recognition

Understanding the real world through point cloud video is a crucial aspect of robotics and autonomous driving systems. However, prevailing methods for 4D point cloud recognition have limitations due to sensor resolution, which leads to a lack of detailed information. Recent advances have shown that Vision-Language Models (VLM) pre-trained on web-scale text-image datasets can learn fine-grained visual concepts that can be transferred to various downstream tasks. However, effectively integrating VLM into the domain of 4D point clouds remains an unresolved problem. In this work, we propose the Vision-Language Models Goes 4D (VG4D) framework to transfer VLM knowledge from visual-text pre-trained models to a 4D point cloud network. Our approach involves aligning the 4D encoder's representation with a VLM to learn a shared visual and text space from training on large-scale image-text pairs. By transferring the knowledge of the VLM to the 4D encoder and combining the VLM, our VG4D achieves improved recognition performance. To enhance the 4D encoder, we modernize the classic dynamic point cloud backbone and propose an improved version of PSTNet, im-PSTNet, which can efficiently model point cloud videos. Experiments demonstrate that our method achieves state-of-the-art performance for action recognition on both the NTU RGB+D 60 dataset and the NTU RGB+D 120 dataset. Code is available at \url{https://github.com/Shark0-0/VG4D}.

ModelNet-O: A Large-Scale Synthetic Dataset for Occlusion-Aware Point Cloud Classification

Recently, 3D point cloud classification has made significant progress with the help of many datasets. However, these datasets do not reflect the incomplete nature of real-world point clouds caused by occlusion, which limits the practical application of current methods. To bridge this gap, we propose ModelNet-O, a large-scale synthetic dataset of 123,041 samples that emulate real-world point clouds with self-occlusion caused by scanning from monocular cameras. ModelNet-O is 10 times larger than existing datasets and offers more challenging cases to evaluate the robustness of existing methods. Our observation on ModelNet-O reveals that well-designed sparse structures can preserve structural information of point clouds under occlusion, motivating us to propose a robust point cloud processing method that leverages a critical point sampling (CPS) strategy in a multi-level manner. We term our method PointMLS. Through extensive experiments, we demonstrate that our PointMLS achieves state-of-the-art results on ModelNet-O and competitive results on regular datasets, and it is robust and effective. More experiments also demonstrate the robustness and effectiveness of PointMLS.

Explore Human Parsing Modality for Action Recognition

Multimodal-based action recognition methods have achieved high success using pose and RGB modality. However, skeletons sequences lack appearance depiction and RGB images suffer irrelevant noise due to modality limitations. To address this, we introduce human parsing feature map as a novel modality, since it can selectively retain effective semantic features of the body parts, while filtering out most irrelevant noise. We propose a new dual-branch framework called Ensemble Human Parsing and Pose Network (EPP-Net), which is the first to leverage both skeletons and human parsing modalities for action recognition. The first human pose branch feeds robust skeletons in graph convolutional network to model pose features, while the second human parsing branch also leverages depictive parsing feature maps to model parsing festures via convolutional backbones. The two high-level features will be effectively combined through a late fusion strategy for better action recognition. Extensive experiments on NTU RGB+D and NTU RGB+D 120 benchmarks consistently verify the effectiveness of our proposed EPP-Net, which outperforms the existing action recognition methods. Our code is available at: https://github.com/liujf69/EPP-Net-Action.

How to Efficiently Annotate Images for Best-Performing Deep Learning Based Segmentation Models: An Empirical Study with Weak and Noisy Annotations and Segment Anything Model

Deep neural networks (DNNs) have been deployed for many image segmentation tasks and achieved outstanding performance. However, preparing a dataset for training segmentation DNNs is laborious and costly since typically pixel-level annotations are provided for each object of interest. To alleviate this issue, one can provide only weak labels such as bounding boxes or scribbles, or less accurate (noisy) annotations of the objects. These are significantly faster to generate and thus result in more annotated images given the same time budget. However, the reduction in quality might negatively affect the segmentation performance of the resulting model. In this study, we perform a thorough cost-effectiveness evaluation of several weak and noisy labels. We considered 11 variants of annotation strategies and 4 datasets. We conclude that the common practice of accurately outlining the objects of interest is virtually never the optimal approach when the annotation time is limited, even if notable annotation time is available (10s of hours). Annotation approaches that stood out in such scenarios were (1) contour-based annotation with rough continuous traces, (2) polygon-based annotation with few vertices, and (3) box annotations combined with the Segment Anything Model (SAM). In situations where unlimited annotation time was available, precise annotations still lead to the highest segmentation model performance.

Dynamic Compositional Graph Convolutional Network for Efficient Composite Human Motion Prediction

With potential applications in fields including intelligent surveillance and human-robot interaction, the human motion prediction task has become a hot research topic and also has achieved high success, especially using the recent Graph Convolutional Network (GCN). Current human motion prediction task usually focuses on predicting human motions for atomic actions. Observing that atomic actions can happen at the same time and thus formulating the composite actions, we propose the composite human motion prediction task. To handle this task, we first present a Composite Action Generation (CAG) module to generate synthetic composite actions for training, thus avoiding the laborious work of collecting composite action samples. Moreover, we alleviate the effect of composite actions on demand for a more complicated model by presenting a Dynamic Compositional Graph Convolutional Network (DC-GCN). Extensive experiments on the Human3.6M dataset and our newly collected CHAMP dataset consistently verify the efficiency of our DC-GCN method, which achieves state-of-the-art motion prediction accuracies and meanwhile needs few extra computational costs than traditional GCN-based human motion methods.

GrowCLIP: Data-aware Automatic Model Growing for Large-scale Contrastive Language-Image Pre-training

Cross-modal pre-training has shown impressive performance on a wide range of downstream tasks, benefiting from massive image-text pairs collected from the Internet. In practice, online data are growing constantly, highlighting the importance of the ability of pre-trained model to learn from data that is continuously growing. Existing works on cross-modal pre-training mainly focus on training a network with fixed architecture. However, it is impractical to limit the model capacity when considering the continuously growing nature of pre-training data in real-world applications. On the other hand, it is important to utilize the knowledge in the current model to obtain efficient training and better performance. To address the above issues, in this paper, we propose GrowCLIP, a data-driven automatic model growing algorithm for contrastive language-image pre-training with continuous image-text pairs as input. Specially, we adopt a dynamic growth space and seek out the optimal architecture at each growth step to adapt to online learning scenarios. And the shared encoder is proposed in our growth space to enhance the degree of cross-modal fusion. Besides, we explore the effect of growth in different dimensions, which could provide future references for the design of cross-modal model architecture. Finally, we employ parameter inheriting with momentum (PIM) to maintain the previous knowledge and address the issue of the local minimum dilemma. Compared with the existing methods, GrowCLIP improves 2.3% average top-1 accuracy on zero-shot image classification of 9 downstream tasks. As for zero-shot image retrieval, GrowCLIP can improve 1.2% for top-1 image-to-text recall on Flickr30K dataset.

Learning Snippet-to-Motion Progression for Skeleton-based Human Motion Prediction

Existing Graph Convolutional Networks to achieve human motion prediction largely adopt a one-step scheme, which output the prediction straight from history input, failing to exploit human motion patterns. We observe that human motions have transitional patterns and can be split into snippets representative of each transition. Each snippet can be reconstructed from its starting and ending poses referred to as the transitional poses. We propose a snippet-to-motion multi-stage framework that breaks motion prediction into sub-tasks easier to accomplish. Each sub-task integrates three modules: transitional pose prediction, snippet reconstruction, and snippet-to-motion prediction. Specifically, we propose to first predict only the transitional poses. Then we use them to reconstruct the corresponding snippets, obtaining a close approximation to the true motion sequence. Finally we refine them to produce the final prediction output. To implement the network, we propose a novel unified graph modeling, which allows for direct and effective feature propagation compared to existing approaches which rely on separate space-time modeling. Extensive experiments on Human 3.6M, CMU Mocap and 3DPW datasets verify the effectiveness of our method which achieves state-of-the-art performance.

Towards Medical Artificial General Intelligence via Knowledge-Enhanced Multimodal Pretraining

Medical artificial general intelligence (MAGI) enables one foundation model to solve different medical tasks, which is very practical in the medical domain. It can significantly reduce the requirement of large amounts of task-specific data by sufficiently sharing medical knowledge among different tasks. However, due to the challenges of designing strongly generalizable models with limited and complex medical data, most existing approaches tend to develop task-specific models. To take a step towards MAGI, we propose a new paradigm called Medical-knOwledge-enhanced mulTimOdal pretRaining (MOTOR). In MOTOR, we combine two kinds of basic medical knowledge, i.e., general and specific knowledge, in a complementary manner to boost the general pretraining process. As a result, the foundation model with comprehensive basic knowledge can learn compact representations from pretraining radiographic data for better cross-modal alignment. MOTOR unifies the understanding and generation, which are two kinds of core intelligence of an AI system, into a single medical foundation model, to flexibly handle more diverse medical tasks. To enable a comprehensive evaluation and facilitate further research, we construct a medical multimodal benchmark including a wide range of downstream tasks, such as chest x-ray report generation and medical visual question answering. Extensive experiments on our benchmark show that MOTOR obtains promising results through simple task-oriented adaptation. The visualization shows that the injected knowledge successfully highlights key information in the medical data, demonstrating the excellent interpretability of MOTOR. Our MOTOR successfully mimics the human practice of fulfilling a "medical student" to accelerate the process of becoming a "specialist". We believe that our work makes a significant stride in realizing MAGI.

A Mixer Layer is Worth One Graph Convolution: Unifying MLP-Mixers and GCNs for Human Motion Prediction

The past few years has witnessed the dominance of Graph Convolutional Networks (GCNs) over human motion prediction, while their performance is still far from satisfactory. Recently, MLP-Mixers show competitive results on top of being more efficient and simple. To extract features, GCNs typically follow an aggregate-and-update paradigm, while Mixers rely on token mixing and channel mixing operations. The two research paths have been independently established in the community. In this paper, we develop a novel perspective by unifying Mixers and GCNs. We show that a mixer layer can be seen as a graph convolutional layer applied to a fully-connected graph with parameterized adjacency. Extending this theoretical finding to the practical side, we propose Meta-Mixing Network (M$^2$-Net). Assisted with a novel zero aggregation operation, our network is capable of capturing both the structure-agnostic and the structure-sensitive dependencies in a collaborative manner. Not only is it computationally efficient, but most importantly, it also achieves state-of-the-art performance. An extensive evaluation on the Human3.6M, AMASS, and 3DPW datasets shows that M$^2$-Net consistently outperforms all other approaches. We hope our work brings the community one step further towards truly predictable human motion. Our code will be publicly available.

CapDet: Unifying Dense Captioning and Open-World Detection Pretraining

Benefiting from large-scale vision-language pre-training on image-text pairs, open-world detection methods have shown superior generalization ability under the zero-shot or few-shot detection settings. However, a pre-defined category space is still required during the inference stage of existing methods and only the objects belonging to that space will be predicted. To introduce a "real" open-world detector, in this paper, we propose a novel method named CapDet to either predict under a given category list or directly generate the category of predicted bounding boxes. Specifically, we unify the open-world detection and dense caption tasks into a single yet effective framework by introducing an additional dense captioning head to generate the region-grounded captions. Besides, adding the captioning task will in turn benefit the generalization of detection performance since the captioning dataset covers more concepts. Experiment results show that by unifying the dense caption task, our CapDet has obtained significant performance improvements (e.g., +2.1% mAP on LVIS rare classes) over the baseline method on LVIS (1203 classes). Besides, our CapDet also achieves state-of-the-art performance on dense captioning tasks, e.g., 15.44% mAP on VG V1.2 and 13.98% on the VG-COCO dataset.