Sample alignment technique is a key component of vertical federated learning. One of the important solutions for sample alignment is known as private set intersection (PSI). It requires multiple participants to collaboratively compute the intersection from their samples while preserving data security and privacy. However, with a growing number of participants and samples, the communication and computation overhead of the multiparty PSI protocol becomes heavy, which severely impacts the performance of vertical federated learning. To improve the efficiency of sample alignment, this paper proposes a distributed multiparty PSI protocol based on fast Fourier transform (FFT) polynomial interpolation and oblivious pseudo-random function (OPRF). The scheme reduces communication complexity by FFT polynomial interpolation. Meanwhile, it employs OPRF to resist collusion attacks. We evaluate the performance of the scheme in two scenarios: without collusion and arbitrary collusion. The experimental results indicate that the scheme is a practical and efficient solution for sample alignment in vertical federated learning.

This paper presents a high-quality human motion pre-diction method that accurately predicts future human poses given observed ones. Our method is based on the observation that a good “initial guess” of the future poses is very helpful in improving the forecasting accuracy. This mo-tivates us to propose a novel two-stage prediction frame-work, including an init-prediction network that just computes the good guess and then a formal-prediction network that predicts the target future poses based on the guess. More importantly, we extend this idea further and design a multi-stage prediction framework where each stage pre-dicts initial guess for the next stage, which brings more performance gain. To fulfill the prediction task at each stage, we propose a network comprising Spatial Dense Graph Convolutional Networks (S-DGCN) and Temporal Dense Graph Convolutional Networks (T-DGCN). Alternatively executing the two networks helps extract spatiotem-poral features over the global receptive field of the whole pose sequence. All the above design choices cooperating together make our method outperform previous approaches by large margins: 6%-7% on Human3.6M, 5%-10% on CMU-MoCap, and 13%-16% on 3DPW. Code is available at https://github.com/705062791/PGBIG.

This paper presents a new surveillance video synopsis method which performs much better than previous approaches in terms of both compression ratio and artifact. Previously, a surveillance video was usually compressed by shifting the moving objects of that video forward along the time axis, which inevitably yielded serious collision and chronological disorder artifacts between the shifted objects. The main observation of this paper is that these artifacts can be alleviated by changing the speed or size of the objects, since with varied speed and size the objects can move more flexibly to avoid collision points or to keep chronological relationships. Based on this observation, we propose a video synopsis method that performs object shifting, speed changing, and size scaling simultaneously. We show how to integrate the three heterogeneous operations into a single optimization framework and achieve high-quality synopsis results. Unlike previous approaches that usually use alternative optimization strategies to solve synopsis optimizations, we develop a Metropolis sampling algorithm to find the solution for our three-variable optimization problem. A variety of experiments demonstrate the effectiveness of our method.

Video stabilization is usually composed of three stages: feature trajectory extraction, trajectory smoothing, and frame warping. Most previous approaches view them as three separate stages. This paper proposes a method combining the last two stages, namely the trajectory smoothing and frame warping stages, into a single optimization framework. The novelty exists in the way of how we combine them: the trajectory smoothing part plays a major role while the frame warping part plays an auxiliary role. With this kind of design, we can conveniently increase the strength of the trajectory smoothing part by a robust first-order derivative term, which makes it possible to produce very aggressive stabilization effects. On the other hand, we adopt adaptive weighting mechanisms in the frame warping part, to follow the smoothed trajectories as much as possible while regularizing other places as similar as possible. Our method is robust to utilize both foreground and background features, and very short trajectories. The utilization of all these information in turn increases the accuracy of the proposed method. We also provide a simplified implementation of our method, which is less accurate but more efficient. Experiments on various kinds of videos demonstrate the effectiveness of our method.