Yini Fang

Shiyi Tang, Shu Zhang, Yini Fang

Small object detection has been a challenging problem in the field of object detection. There has been some works that proposes improvements for this task, such as adding several attention blocks or changing the whole structure of feature fusion networks. However, the computation cost of these models is large, which makes deploying a real-time object detection system unfeasible, while leaving room for improvement. To this end, an improved YOLOv5 model: HIC-YOLOv5 is proposed to address the aforementioned problems. Firstly, an additional prediction head specific to small objects is added to provide a higher-resolution feature map for better prediction. Secondly, an involution block is adopted between the backbone and neck to increase channel information of the feature map. Moreover, an attention mechanism named CBAM is applied at the end of the backbone, thus not only decreasing the computation cost compared with previous works but also emphasizing the important information in both channel and spatial domain. Our result shows that HIC-YOLOv5 has improved mAP@[.5:.95] by 6.42% and mAP@0.5 by 9.38% on VisDrone-2019-DET dataset.

Yini Fang, Liang Wu, Frederic Jumelle et al.

Video-based Emotional Reaction Intensity (ERI) estimation measures the intensity of subjects' reactions to stimuli along several emotional dimensions from videos of the subject as they view the stimuli. We propose a multi-modal architecture for video-based ERI combining video and audio information. Video input is encoded spatially first, frame-by-frame, combining features encoding holistic aspects of the subjects' facial expressions and features encoding spatially localized aspects of their expressions. Input is then combined across time: from frame-to-frame using gated recurrent units (GRUs), then globally by a transformer. We handle variable video length with a regression token that accumulates information from all frames into a fixed-dimensional vector independent of video length. Audio information is handled similarly: spectral information extracted within each frame is integrated across time by a cascade of GRUs and a transformer with regression token. The video and audio regression tokens' outputs are merged by concatenation, then input to a final fully connected layer producing intensity estimates. Our architecture achieved excellent performance on the Hume-Reaction dataset in the ERI Esimation Challenge of the Fifth Competition on Affective Behavior Analysis in-the-Wild (ABAW5). The Pearson Correlation Coefficients between estimated and subject self-reported scores, averaged across all emotions, were 0.455 on the validation dataset and 0.4547 on the test dataset, well above the baselines. The transformer's self-attention mechanism enables our architecture to focus on the most critical video frames regardless of length. Ablation experiments establish the advantages of combining holistic/local features and of multi-modal integration. Code available at https://github.com/HKUST-NISL/ABAW5.

Linquan Wu, Tianxiang Jiang, Haoyu Yang et al.

Micro-expression recognition (MER) has achieved impressive accuracy in controlled laboratory settings. However, its real-world applicability faces a significant generalization cliff, severely hindering practical deployment due to poor performance on unseen data and susceptibility to domain shifts. Existing attention mechanisms often overfit to dataset-specific appearance cues or rely on fixed spatial priors, making them fragile in diverse environments. We posit that robust MER requires focusing on quasi-invariant motion orientations inherent to micro-expressions, rather than superficial pixel-level features. To this end, we introduce \textbf{FaceSleuth-R}, a framework centered on our novel \textbf{Single-Orientation Attention (SOA)} module. SOA is a lightweight, differentiable operator that enables the network to learn layer-specific optimal orientations, effectively guiding attention towards these robust motion cues. Through extensive experiments, we demonstrate that SOA consistently discovers a universal near-vertical motion prior across diverse datasets. More critically, FaceSleuth-R showcases superior generalization in rigorous Leave-One-Dataset-Out (LODO) protocols, significantly outperforming baselines and state-of-the-art methods when confronted with domain shifts. Furthermore, our approach establishes \textbf{state-of-the-art results} across several benchmarks. This work highlights adaptive orientation-aware attention as a key paradigm for developing truly generalized and high-performing MER systems.

Yini Fang

Modelling dynamic traffic patterns and especially the continuously changing dependencies between different base stations, which previous studies overlook, is challenging. Traditional algorithms struggle to process large volumes of data and to extract deep insights that help elucidate mobile traffic demands with fine granularity, as well as how these demands will evolve in the future. Therefore, in this thesis we harness the powerful hierarchical feature learning abilities of Deep Learning (DL) techniques in both spatial and temporal domains and develop solutions for precise city-scale mobile traffic analysis and forecasting. Firstly, we design Spider, a mobile traffic measurement collection and reconstruction framework with a view to reducing the cost of measurement collection and inferring traffic consumption with high accuracy, despite working with sparse information. In particular, we train a reinforcement learning agent to selectively sample subsets of target mobile coverage areas and tackle the large action space problem specific to this setting. We then introduce a lightweight neural network model to reconstruct the traffic consumption based on historical sparse measurements. Our proposed framework outperforms existing solutions on a real-world mobile traffic dataset. Secondly, we design SDGNet, a handover-aware graph neural network model for long-term mobile traffic forecasting. We model the cellular network as a graph, and leverage handover frequency to capture the dependencies between base stations across time. Handover information reflects user mobility such as daily commute, which helps in increasing the accuracy of the forecasts made. We proposed dynamic graph convolution to extract features from both traffic consumption and handover data, showing that our model outperforms other benchmark graph models on a mobile traffic dataset collected by a major network operator.