SoccerNet 2024 Challenges Results

The SoccerNet 2024 challenges represent the fourth annual video understanding challenges organized by the SoccerNet team. These challenges aim to advance research across multiple themes in football, including broadcast video understanding, field understanding, and player understanding. This year, the challenges encompass four vision-based tasks. (1) Ball Action Spotting, focusing on precisely localizing when and which soccer actions related to the ball occur, (2) Dense Video Captioning, focusing on describing the broadcast with natural language and anchored timestamps, (3) Multi-View Foul Recognition, a novel task focusing on analyzing multiple viewpoints of a potential foul incident to classify whether a foul occurred and assess its severity, (4) Game State Reconstruction, another novel task focusing on reconstructing the game state from broadcast videos onto a 2D top-view map of the field. Detailed information about the tasks, challenges, and leaderboards can be found at https://www.soccer-net.org, with baselines and development kits available at https://github.com/SoccerNet.

Imagine the Unseen: Occluded Pedestrian Detection via Adversarial Feature Completion

Pedestrian detection has significantly progressed in recent years, thanks to the development of DNNs. However, detection performance at occluded scenes is still far from satisfactory, as occlusion increases the intra-class variance of pedestrians, hindering the model from finding an accurate classification boundary between pedestrians and background clutters. From the perspective of reducing intra-class variance, we propose to complete features for occluded regions so as to align the features of pedestrians across different occlusion patterns. An important premise for feature completion is to locate occluded regions. From our analysis, channel features of different pedestrian proposals only show high correlation values at visible parts and thus feature correlations can be used to model occlusion patterns. In order to narrow down the gap between completed features and real fully visible ones, we propose an adversarial learning method, which completes occluded features with a generator such that they can hardly be distinguished by the discriminator from real fully visible features. We report experimental results on the CityPersons, Caltech and CrowdHuman datasets. On CityPersons, we show significant improvements over five different baseline detectors, especially on the heavy occlusion subset. Furthermore, we show that our proposed method FeatComp++ achieves state-of-the-art results on all the above three datasets without relying on extra cues.

Fairness Optimization for Intelligent Reflecting Surface Aided Uplink Rate-Splitting Multiple Access

This paper studies the fair transmission design for an intelligent reflecting surface (IRS) aided rate-splitting multiple access (RSMA). IRS is used to establish a good signal propagation environment and enhance the RSMA transmission performance. The fair rate adaption problem is constructed as a max-min optimization problem. To solve the optimization problem, we adopt an alternative optimization (AO) algorithm to optimize the power allocation, beamforming, and decoding order, respectively. A generalized power iteration (GPI) method is proposed to optimize the receive beamforming, which can improve the minimum rate of devices and reduce the optimization complexity. At the base station (BS), a successive group decoding (SGD) algorithm is proposed to tackle the uplink signal estimation, which trades off the fairness and complexity of decoding. At the same time, we also consider robust communication with imperfect channel state information at the transmitter (CSIT), which studies robust optimization by using lower bound expressions on the expected data rates. Extensive numerical results show that the proposed optimization algorithm can significantly improve the performance of fairness. It also provides reliable results for uplink communication with imperfect CSIT.

Rate-Splitting Multiple Access for Transmissive Reconfigurable Intelligent Surface Transceiver Empowered ISAC System

In this paper, a novel transmissive reconfigurable intelligent surface (TRIS) transceiver empowered integrated sensing and communications (ISAC) system is proposed for future multi-demand terminals. To address interference management, we implement rate-splitting multiple access (RSMA), where the common stream is independently designed for the sensing service. We introduce the sensing quality of service (QoS) criteria based on this structure and construct an optimization problem with the sensing QoS criteria as the objective function to optimize the sensing stream precoding matrix and the communication stream precoding matrix. Due to the coupling of optimization variables, the formulated problem is a non-convex optimization problem that cannot be solved directly. To tackle the above-mentioned challenging problem, alternating optimization (AO) is utilized to decouple the optimization variables. Specifically, the problem is decoupled into three subproblems about the sensing stream precoding matrix, the communication stream precoding matrix, and the auxiliary variables, which is solved alternatively through AO until the convergence is reached. For solving the problem, successive convex approximation (SCA) is applied to deal with the sum-rate threshold constraints on communications, and difference-of-convex (DC) programming is utilized to solve rank-one non-convex constraints. Numerical simulation results verify the superiority of the proposed scheme in terms of improving the communication and sensing QoS.

Divide and Conquer: Hybrid Pre-training for Person Search

Large-scale pre-training has proven to be an effective method for improving performance across different tasks. Current person search methods use ImageNet pre-trained models for feature extraction, yet it is not an optimal solution due to the gap between the pre-training task and person search task (as a downstream task). Therefore, in this paper, we focus on pre-training for person search, which involves detecting and re-identifying individuals simultaneously. Although labeled data for person search is scarce, datasets for two sub-tasks person detection and re-identification are relatively abundant. To this end, we propose a hybrid pre-training framework specifically designed for person search using sub-task data only. It consists of a hybrid learning paradigm that handles data with different kinds of supervisions, and an intra-task alignment module that alleviates domain discrepancy under limited resources. To the best of our knowledge, this is the first work that investigates how to support full-task pre-training using sub-task data. Extensive experiments demonstrate that our pre-trained model can achieve significant improvements across diverse protocols, such as person search method, fine-tuning data, pre-training data and model backbone. For example, our model improves ResNet50 based NAE by 10.3% relative improvement w.r.t. mAP. Our code and pre-trained models are released for plug-and-play usage to the person search community.

Fairness Optimization of RSMA for Uplink Communication based on Intelligent Reflecting Surface

In this paper, we propose a rate-splitting multiple access (RSMA) scheme for uplink wireless communication systems with intelligent reflecting surface (IRS) aided. In the considered model, IRS is adopted to overcome power attenuation caused by path loss. We construct a max-min fairness optimization problem to obtain the resource allocation, including the receive beamforming at the base station (BS) and phase-shift beamforming at IRS. We also introduce a successive group decoding (SGD) algorithm at the receiver, which trades off the fairness and complexity of decoding. In the simulation, the results show that the proposed scheme has superiority in improving the fairness of uplink communication.

Joint Device Activity Detection, Channel Estimation and Signal Detection for Massive Grant-free Access via BiGAMP

Massive access has been challenging for the fifth generation (5G) and beyond since the abundance of devices causes communication overload to skyrocket. In an uplink massive access scenario, device traffic is sporadic in any given coherence time. Thus, channels across the antennas of each device exhibit correlation, which can be characterized by the row sparse channel matrix structure. In this work, we develop a bilinear generalized approximate message passing (BiGAMP) algorithm based on the row sparse channel matrix structure. This algorithm can jointly detect device activities, estimate channels, and detect signals in massive multiple-input multiple-output (MIMO) systems by alternating updates between channel matrices and signal matrices. The signal observation provides additional information for performance improvement compared to the existing algorithms. We further analyze state evolution (SE) to measure the performance of the proposed algorithm and characterize the convergence condition for SE. Moreover, we perform theoretical analysis on the error probability of device activity detection, the mean square error of channel estimation, and the symbol error rate of signal detection. The numerical results demonstrate the superiority of the proposed algorithm over the state-of-the-art methods in DADCE-SD, and the numerical results are relatively close to the theoretical analysis results.

Grouped Adaptive Loss Weighting for Person Search

Person search is an integrated task of multiple sub-tasks such as foreground/background classification, bounding box regression and person re-identification. Therefore, person search is a typical multi-task learning problem, especially when solved in an end-to-end manner. Recently, some works enhance person search features by exploiting various auxiliary information, e.g. person joint keypoints, body part position, attributes, etc., which brings in more tasks and further complexifies a person search model. The inconsistent convergence rate of each task could potentially harm the model optimization. A straightforward solution is to manually assign different weights to different tasks, compensating for the diverse convergence rates. However, given the special case of person search, i.e. with a large number of tasks, it is impractical to weight the tasks manually. To this end, we propose a Grouped Adaptive Loss Weighting (GALW) method which adjusts the weight of each task automatically and dynamically. Specifically, we group tasks according to their convergence rates. Tasks within the same group share the same learnable weight, which is dynamically assigned by considering the loss uncertainty. Experimental results on two typical benchmarks, CUHK-SYSU and PRW, demonstrate the effectiveness of our method.

Learning Audio-Visual embedding for Wild Person Verification

It has already been observed that audio-visual embedding can be extracted from these two modalities to gain robustness for person verification. However, the aggregator that used to generate a single utterance representation from each frame does not seem to be well explored. In this article, we proposed an audio-visual network that considers aggregator from a fusion perspective. We introduced improved attentive statistics pooling for the first time in face verification. Then we find that strong correlation exists between modalities during pooling, so joint attentive pooling is proposed which contains cycle consistency to learn the implicit inter-frame weight. Finally, fuse the modality with a gated attention mechanism. All the proposed models are trained on the VoxCeleb2 dev dataset and the best system obtains 0.18\%, 0.27\%, and 0.49\% EER on three official trail lists of VoxCeleb1 respectively, which is to our knowledge the best-published results for person verification. As an analysis, visualization maps are generated to explain how this system interact between modalities.

DTG-SSOD: Dense Teacher Guidance for Semi-Supervised Object Detection

The Mean-Teacher (MT) scheme is widely adopted in semi-supervised object detection (SSOD). In MT, the sparse pseudo labels, offered by the final predictions of the teacher (e.g., after Non Maximum Suppression (NMS) post-processing), are adopted for the dense supervision for the student via hand-crafted label assignment. However, the sparse-to-dense paradigm complicates the pipeline of SSOD, and simultaneously neglects the powerful direct, dense teacher supervision. In this paper, we attempt to directly leverage the dense guidance of teacher to supervise student training, i.e., the dense-to-dense paradigm. Specifically, we propose the Inverse NMS Clustering (INC) and Rank Matching (RM) to instantiate the dense supervision, without the widely used, conventional sparse pseudo labels. INC leads the student to group candidate boxes into clusters in NMS as the teacher does, which is implemented by learning grouping information revealed in NMS procedure of the teacher. After obtaining the same grouping scheme as the teacher via INC, the student further imitates the rank distribution of the teacher over clustered candidates through Rank Matching. With the proposed INC and RM, we integrate Dense Teacher Guidance into Semi-Supervised Object Detection (termed DTG-SSOD), successfully abandoning sparse pseudo labels and enabling more informative learning on unlabeled data. On COCO benchmark, our DTG-SSOD achieves state-of-the-art performance under various labelling ratios. For example, under 10% labelling ratio, DTG-SSOD improves the supervised baseline from 26.9 to 35.9 mAP, outperforming the previous best method Soft Teacher by 1.9 points.