Visual interactivity understanding within visual scenes presents a significant challenge in computer vision. Existing methods focus on complex interactivities while leveraging a simple relationship model. These methods, however, struggle with a diversity of appearance, situation, position, interaction, and relation in videos. This limitation hinders the ability to fully comprehend the interplay within the complex visual dynamics of subjects. In this paper, we delve into interactivities understanding within visual content by deriving scene graph representations from dense interactivities among humans and objects. To achieve this goal, we first present a new dataset containing Appearance-Situation-Position-Interaction-Relation predicates, named ASPIRe, offering an extensive collection of videos marked by a wide range of interactivities. Then, we propose a new approach named Hierarchical Interlacement Graph (HIG), which leverages a unified layer and graph within a hierarchical structure to provide deep insights into scene changes across five distinct tasks. Our approach demonstrates superior performance to other methods through extensive experiments conducted in various scenarios.
Group Activity Recognition (GAR) is a fundamental problem in computer vision, with diverse applications in sports video analysis, video surveillance, and social scene understanding. Unlike conventional action recognition, GAR aims to classify the actions of a group of individuals as a whole, requiring a deep understanding of their interactions and spatiotemporal relationships. To address the challenges in GAR, we present REACT (\textbf{R}ecognize \textbf{E}very \textbf{Act}ion Everywhere All At Once), a novel architecture inspired by the transformer encoder-decoder model explicitly designed to model complex contextual relationships within videos, including multi-modality and spatio-temporal features. Our architecture features a cutting-edge Vision-Language Encoder block for integrated temporal, spatial, and multi-modal interaction modeling. This component efficiently encodes spatiotemporal interactions, even with sparsely sampled frames, and recovers essential local information. Our Action Decoder Block refines the joint understanding of text and video data, allowing us to precisely retrieve bounding boxes, enhancing the link between semantics and visual reality. At the core, our Actor Fusion Block orchestrates a fusion of actor-specific data and textual features, striking a balance between specificity and context. Our method outperforms state-of-the-art GAR approaches in extensive experiments, demonstrating superior accuracy in recognizing and understanding group activities. Our architecture's potential extends to diverse real-world applications, offering empirical evidence of its performance gains. This work significantly advances the field of group activity recognition, providing a robust framework for nuanced scene comprehension.
Multiple Object Tracking (MOT) aims to find bounding boxes and identities of targeted objects in consecutive video frames. While fully-supervised MOT methods have achieved high accuracy on existing datasets, they cannot generalize well on a newly obtained dataset or a new unseen domain. In this work, we first address the MOT problem from the cross-domain point of view, imitating the process of new data acquisition in practice. Then, a new cross-domain MOT adaptation from existing datasets is proposed without any pre-defined human knowledge in understanding and modeling objects. It can also learn and update itself from the target data feedback. The intensive experiments are designed on four challenging settings, including MOTSynth to MOT17, MOT17 to MOT20, MOT17 to VisDrone, and MOT17 to DanceTrack. We then prove the adaptability of the proposed self-supervised learning strategy. The experiments also show superior performance on tracking metrics MOTA and IDF1, compared to fully supervised, unsupervised, and self-supervised state-of-the-art methods.
Despite the significant progress made in recent years, Multi-Object Tracking (MOT) approaches still suffer from several limitations, including their reliance on prior knowledge of tracking targets, which necessitates the costly annotation of large labeled datasets. As a result, existing MOT methods are limited to a small set of predefined categories, and they struggle with unseen objects in the real world. To address these issues, Generic Multiple Object Tracking (GMOT) has been proposed, which requires less prior information about the targets. However, all existing GMOT approaches follow a one-shot paradigm, relying mainly on the initial bounding box and thus struggling to handle variants e.g., viewpoint, lighting, occlusion, scale, and etc. In this paper, we introduce a novel approach to address the limitations of existing MOT and GMOT methods. Specifically, we propose a zero-shot GMOT (Z-GMOT) algorithm that can track never-seen object categories with zero training examples, without the need for predefined categories or an initial bounding box. To achieve this, we propose iGLIP, an improved version of Grounded language-image pretraining (GLIP), which can detect unseen objects while minimizing false positives. We evaluate our Z-GMOT thoroughly on the GMOT-40 dataset, AnimalTrack testset, DanceTrack testset. The results of these evaluations demonstrate a significant improvement over existing methods. For instance, on the GMOT-40 dataset, the Z-GMOT outperforms one-shot GMOT with OC-SORT by 27.79 points HOTA and 44.37 points MOTA. On the AnimalTrack dataset, it surpasses fully-supervised methods with DeepSORT by 12.55 points HOTA and 8.97 points MOTA. To facilitate further research, we will make our code and models publicly available upon acceptance of this paper.
One of the recent trends in vision problems is to use natural language captions to describe the objects of interest. This approach can overcome some limitations of traditional methods that rely on bounding boxes or category annotations. This paper introduces a novel paradigm for Multiple Object Tracking called Type-to-Track, which allows users to track objects in videos by typing natural language descriptions. We present a new dataset for that Grounded Multiple Object Tracking task, called GroOT, that contains videos with various types of objects and their corresponding textual captions describing their appearance and action in detail. Additionally, we introduce two new evaluation protocols and formulate evaluation metrics specifically for this task. We develop a new efficient method that models a transformer-based eMbed-ENcoDE-extRact framework (MENDER) using the third-order tensor decomposition. The experiments in five scenarios show that our MENDER approach outperforms another two-stage design in terms of accuracy and efficiency, up to 14.7% accuracy and 4$\times$ speed faster.
This paper introduces a novel approach to Social Group Activity Recognition (SoGAR) using Self-supervised Transformers network that can effectively utilize unlabeled video data. To extract spatio-temporal information, we create local and global views with varying frame rates. Our self-supervised objective ensures that features extracted from contrasting views of the same video are consistent across spatio-temporal domains. Our proposed approach is efficient in using transformer-based encoders for alleviating the weakly supervised setting of group activity recognition. By leveraging the benefits of transformer models, our approach can model long-term relationships along spatio-temporal dimensions. Our proposed SoGAR method achieves state-of-the-art results on three group activity recognition benchmarks, namely JRDB-PAR, NBA, and Volleyball datasets, surpassing the current state-of-the-art in terms of F1-score, MCA, and MPCA metrics.
The development of autonomous vehicles generates a tremendous demand for a low-cost solution with a complete set of camera sensors capturing the environment around the car. It is essential for object detection and tracking to address these new challenges in multi-camera settings. In order to address these challenges, this work introduces novel Single-Stage Global Association Tracking approaches to associate one or more detection from multi-cameras with tracked objects. These approaches aim to solve fragment-tracking issues caused by inconsistent 3D object detection. Moreover, our models also improve the detection accuracy of the standard vision-based 3D object detectors in the nuScenes detection challenge. The experimental results on the nuScenes dataset demonstrate the benefits of the proposed method by outperforming prior vision-based tracking methods in multi-camera settings.
This paper aims to tackle Multiple Object Tracking (MOT), an important problem in computer vision but remains challenging due to many practical issues, especially occlusions. Indeed, we propose a new real-time Depth Perspective-aware Multiple Object Tracking (DP-MOT) approach to tackle the occlusion problem in MOT. A simple yet efficient Subject-Ordered Depth Estimation (SODE) is first proposed to automatically order the depth positions of detected subjects in a 2D scene in an unsupervised manner. Using the output from SODE, a new Active pseudo-3D Kalman filter, a simple but effective extension of Kalman filter with dynamic control variables, is then proposed to dynamically update the movement of objects. In addition, a new high-order association approach is presented in the data association step to incorporate first-order and second-order relationships between the detected objects. The proposed approach consistently achieves state-of-the-art performance compared to recent MOT methods on standard MOT benchmarks.
Self-training crowd counting has not been attentively explored though it is one of the important challenges in computer vision. In practice, the fully supervised methods usually require an intensive resource of manual annotation. In order to address this challenge, this work introduces a new approach to utilize existing datasets with ground truth to produce more robust predictions on unlabeled datasets, named domain adaptation, in crowd counting. While the network is trained with labeled data, samples without labels from the target domain are also added to the training process. In this process, the entropy map is computed and minimized in addition to the adversarial training process designed in parallel. Experiments on Shanghaitech, UCF_CC_50, and UCF-QNRF datasets prove a more generalized improvement of our method over the other state-of-the-arts in the cross-domain setting.
The development of autonomous vehicles provides an opportunity to have a complete set of camera sensors capturing the environment around the car. Thus, it is important for object detection and tracking to address new challenges, such as achieving consistent results across views of cameras. To address these challenges, this work presents a new Global Association Graph Model with Link Prediction approach to predict existing tracklets location and link detections with tracklets via cross-attention motion modeling and appearance re-identification. This approach aims at solving issues caused by inconsistent 3D object detection. Moreover, our model exploits to improve the detection accuracy of a standard 3D object detector in the nuScenes detection challenge. The experimental results on the nuScenes dataset demonstrate the benefits of the proposed method to produce SOTA performance on the existing vision-based tracking dataset.