相关论文: From Skeletons to Pixels: Few-Shot Precise Event S…
Precise event spotting (PES) aims to recognize fine-grained events at exact moments and has become a key component of sports analytics. This task is particularly challenging due to rapid succession, motion blur, and subtle visual…
Precise Event Spotting (PES) in sports videos requires frame-level recognition of fine-grained actions from single-camera footage. Existing PES models typically incorporate lightweight temporal modules such as the Gate Shift Module (GSM) or…
Human pose is a useful feature for fine-grained sports action understanding. However, pose estimators are often unreliable when run on sports video due to domain shift and factors such as motion blur and occlusions. This leads to poor…
Precise Event Spotting (PES) aims to identify events and their class from long, untrimmed videos, particularly in sports. The main objective of PES is to detect the event at the exact moment it occurs. Existing methods mainly rely on…
Few-shot segmentation (FSS) aims to rapidly learn novel class concepts from limited examples to segment specific targets in unseen images, and has been widely applied in areas such as medical diagnosis and industrial inspection. However,…
Precise Event Spotting aims to localize fast-paced actions or events in videos with high temporal precision, a key task for applications in sports analytics, robotics, and autonomous systems. Existing methods typically process all frames…
Few-shot segmentation focuses on the generalization of models to segment unseen object with limited annotated samples. However, existing approaches still face two main challenges. First, huge feature distinction between support and query…
Event detection (ED) aims at detecting event trigger words in sentences and classifying them into specific event types. In real-world applications, ED typically does not have sufficient labelled data, thus can be formulated as a few-shot…
Video generation has recently emerged as a central task in the field of generative AI. However, the substantial computational cost inherent in video synthesis makes model distillation a critical technique for efficient deployment. Despite…
Previous knowledge distillation (KD) methods mostly focus on compressing network architectures, which is not thorough enough in deployment as some costs like transmission bandwidth and imaging equipment are related to the image size.…
Spiking neural networks (SNNs) have garnered significant attention for their low power consumption and high biological interpretability. Their rich spatio-temporal information processing capability and event-driven nature make them ideally…
Video event detection has become a cornerstone of modern sports analytics, powering automated performance evaluation, content generation, and tactical decision-making. Recent advances in deep learning have driven progress in related tasks…
We introduce Adversarial Diffusion Distillation (ADD), a novel training approach that efficiently samples large-scale foundational image diffusion models in just 1-4 steps while maintaining high image quality. We use score distillation to…
Among the neural network compression techniques, knowledge distillation is an effective one which forces a simpler student network to mimic the output of a larger teacher network. However, most of such model distillation methods focus on…
Multimodal sarcasm detection is challenging, especially in low-resource settings where subtle image-text contradictions are hard to learn due to scarce annotated data, which hinders the model's performance. Parameter-efficient fine-tuning…
Efficient object detection methods have recently received great attention in remote sensing. Although deep convolutional networks often have excellent detection accuracy, their deployment on resource-limited edge devices is difficult.…
Distribution Matching Distillation (DMD) is a powerful acceleration paradigm, yet its stability is often compromised in Forbidden Zone, regions where the real teacher provides unreliable guidance while the fake teacher exerts insufficient…
Existing video-based human pose estimation methods extensively apply large networks onto every frame in the video to localize body joints, which suffer high computational cost and hardly meet the low-latency requirement in realistic…
Frame-level micro- and macro-expression spotting methods require time-consuming frame-by-frame observation during annotation. Meanwhile, video-level spotting lacks sufficient information about the location and number of expressions during…
In this study, we present a dynamic graph representation learning model on weighted graphs to accurately predict the network capacity of connections between viewers in a live video streaming event. We propose EGAD, a neural network…