Predicting pedestrian trajectories is crucial for improving the safety and effectiveness of autonomous driving and mobile robots. However, this task is nontrivial due to the inherent stochasticity of human motion, which naturally requires the predictor to generate multi-model prediction. Previous works have used various generative methods, such as GAN and VAE, for pedestrian trajectory prediction. Nevertheless, these methods may suffer from problems, including mode collapse and relatively low-quality results. The denoising diffusion probabilistic model (DDPM) has recently been applied to trajectory prediction due to its simple training process and powerful reconstruction ability. However, current diffusion-based methods are straightforward without fully leveraging input information and usually require many denoising iterations leading to a long inference time or an additional network for initialization. To address these challenges and promote the application of diffusion models in trajectory prediction, we propose a novel scene-aware multi-modal pedestrian trajectory prediction framework called GBD. GBD combines goal prediction with the diffusion network. First, the goal predictor produces multiple goals, and then the diffusion network generates multi-modal trajectories conditioned on these goals. Furthermore, we introduce a new diffusion sampling algorithm named tree sampling (TS), which leverages common feature to reduce the inference time and improve accuracy for multi-modal prediction. Experimental results demonstrate that our GBD-TS method achieves state-of-the-art performance with real-time inference speed.
Federated learning is known for its capability to safeguard participants' data privacy. However, recently emerged model inversion attacks (MIAs) have shown that a malicious parameter server can reconstruct individual users' local data samples through model updates. The state-of-the-art attacks either rely on computation-intensive search-based optimization processes to recover each input batch, making scaling difficult, or they involve the malicious parameter server adding extra modules before the global model architecture, rendering the attacks too conspicuous and easily detectable. To overcome these limitations, we propose Scale-MIA, a novel MIA capable of efficiently and accurately recovering training samples of clients from the aggregated updates, even when the system is under the protection of a robust secure aggregation protocol. Unlike existing approaches treating models as black boxes, Scale-MIA recognizes the importance of the intricate architecture and inner workings of machine learning models. It identifies the latent space as the critical layer for breaching privacy and decomposes the complex recovery task into an innovative two-step process to reduce computation complexity. The first step involves reconstructing the latent space representations (LSRs) from the aggregated model updates using a closed-form inversion mechanism, leveraging specially crafted adversarial linear layers. In the second step, the whole input batches are recovered from the LSRs by feeding them into a fine-tuned generative decoder. We implemented Scale-MIA on multiple commonly used machine learning models and conducted comprehensive experiments across various settings. The results demonstrate that Scale-MIA achieves excellent recovery performance on different datasets, exhibiting high reconstruction rates, accuracy, and attack efficiency on a larger scale compared to state-of-the-art MIAs.
In this letter, we propose a new method, Multi-Clue Gaze (MCGaze), to facilitate video gaze estimation via capturing spatial-temporal interaction context among head, face, and eye in an end-to-end learning way, which has not been well concerned yet. The main advantage of MCGaze is that the tasks of clue localization of head, face, and eye can be solved jointly for gaze estimation in a one-step way, with joint optimization to seek optimal performance. During this, spatial-temporal context exchange happens among the clues on the head, face, and eye. Accordingly, the final gazes obtained by fusing features from various queries can be aware of global clues from heads and faces, and local clues from eyes simultaneously, which essentially leverages performance. Meanwhile, the one-step running way also ensures high running efficiency. Experiments on the challenging Gaze360 dataset verify the superiority of our proposition. The source code will be released at https://github.com/zgchen33/MCGaze.
Multi-ship tracking (MST) as a core technology has been proven to be applied to situational awareness at sea and the development of a navigational system for autonomous ships. Despite impressive tracking outcomes achieved by multi-object tracking (MOT) algorithms for pedestrian and vehicle datasets, these models and techniques exhibit poor performance when applied to ship datasets. Intersection of Union (IoU) is the most popular metric for computing similarity used in object tracking. The low frame rates and severe image shake caused by wave turbulence in ship datasets often result in minimal, or even zero, Intersection of Union (IoU) between the predicted and detected bounding boxes. This issue contributes to frequent identity switches of tracked objects, undermining the tracking performance. In this paper, we address the weaknesses of IoU by incorporating the smallest convex shapes that enclose both the predicted and detected bounding boxes. The calculation of the tracking version of IoU (TIoU) metric considers not only the size of the overlapping area between the detection bounding box and the prediction box, but also the similarity of their shapes. Through the integration of the TIoU into state-of-the-art object tracking frameworks, such as DeepSort and ByteTrack, we consistently achieve improvements in the tracking performance of these frameworks.
3D interacting hand pose estimation from a single RGB image is a challenging task, due to serious self-occlusion and inter-occlusion towards hands, confusing similar appearance patterns between 2 hands, ill-posed joint position mapping from 2D to 3D, etc.. To address these, we propose to extend A2J-the state-of-the-art depth-based 3D single hand pose estimation method-to RGB domain under interacting hand condition. Our key idea is to equip A2J with strong local-global aware ability to well capture interacting hands' local fine details and global articulated clues among joints jointly. To this end, A2J is evolved under Transformer's non-local encoding-decoding framework to build A2J-Transformer. It holds 3 main advantages over A2J. First, self-attention across local anchor points is built to make them global spatial context aware to better capture joints' articulation clues for resisting occlusion. Secondly, each anchor point is regarded as learnable query with adaptive feature learning for facilitating pattern fitting capacity, instead of having the same local representation with the others. Last but not least, anchor point locates in 3D space instead of 2D as in A2J, to leverage 3D pose prediction. Experiments on challenging InterHand 2.6M demonstrate that, A2J-Transformer can achieve state-of-the-art model-free performance (3.38mm MPJPE advancement in 2-hand case) and can also be applied to depth domain with strong generalization.
Real-time eyeblink detection in the wild can widely serve for fatigue detection, face anti-spoofing, emotion analysis, etc. The existing research efforts generally focus on single-person cases towards trimmed video. However, multi-person scenario within untrimmed videos is also important for practical applications, which has not been well concerned yet. To address this, we shed light on this research field for the first time with essential contributions on dataset, theory, and practices. In particular, a large-scale dataset termed MPEblink that involves 686 untrimmed videos with 8748 eyeblink events is proposed under multi-person conditions. The samples are captured from unconstrained films to reveal "in the wild" characteristics. Meanwhile, a real-time multi-person eyeblink detection method is also proposed. Being different from the existing counterparts, our proposition runs in a one-stage spatio-temporal way with end-to-end learning capacity. Specifically, it simultaneously addresses the sub-tasks of face detection, face tracking, and human instance-level eyeblink detection. This paradigm holds 2 main advantages: (1) eyeblink features can be facilitated via the face's global context (e.g., head pose and illumination condition) with joint optimization and interaction, and (2) addressing these sub-tasks in parallel instead of sequential manner can save time remarkably to meet the real-time running requirement. Experiments on MPEblink verify the essential challenges of real-time multi-person eyeblink detection in the wild for untrimmed video. Our method also outperforms existing approaches by large margins and with a high inference speed.
We propose a simple, yet powerful approach for unsupervised object segmentation in videos. We introduce an objective function whose minimum represents the mask of the main salient object over the input sequence. It only relies on independent image features and optical flows, which can be obtained using off-the-shelf self-supervised methods. It scales with the length of the sequence with no need for superpixels or sparsification, and it generalizes to different datasets without any specific training. This objective function can actually be derived from a form of spectral clustering applied to the entire video. Our method achieves on-par performance with the state of the art on standard benchmarks (DAVIS2016, SegTrack-v2, FBMS59), while being conceptually and practically much simpler. Code is available at https://ponimatkin.github.io/ssl-vos.
Estimating the relative pose of a new object without prior knowledge is a hard problem, while it is an ability very much needed in robotics and Augmented Reality. We present a method for tracking the 6D motion of objects in RGB video sequences when neither the training images nor the 3D geometry of the objects are available. In contrast to previous works, our method can therefore consider unknown objects in open world instantly, without requiring any prior information or a specific training phase. We consider two architectures, one based on two frames, and the other relying on a Transformer Encoder, which can exploit an arbitrary number of past frames. We train our architectures using only synthetic renderings with domain randomization. Our results on challenging datasets are on par with previous works that require much more information (training images of the target objects, 3D models, and/or depth data). Our source code is available at https://github.com/nv-nguyen/pizza