Masked video modeling, such as VideoMAE, is an effective paradigm for video self-supervised learning (SSL). However, they are primarily based on reconstructing pixel-level details on natural videos which have substantial temporal redundancy, limiting their capability for semantic representation and sufficient encoding of motion dynamics. To address these issues, this paper introduces a novel SSL approach for video representation learning, dubbed as SMILE, by infusing both spatial and motion semantics. In SMILE, we leverage image-language pretrained models, such as CLIP, to guide the learning process with their high-level spatial semantics. We enhance the representation of motion by introducing synthetic motion patterns in the training data, allowing the model to capture more complex and dynamic content. Furthermore, using SMILE, we establish a new self-supervised video learning paradigm capable of learning strong video representations without requiring any natural video data. We have carried out extensive experiments on 7 datasets with various downstream scenarios. SMILE surpasses current state-of-the-art SSL methods, showcasing its effectiveness in learning more discriminative and generalizable video representations. Code is available: https://github.com/fmthoker/SMILE

Recent studies utilize convolutional neural networks (CNNs) to detect gravitational waves (GWs) from cosmic noises. However, the performance of these models is limited by the inherent local receptive field of CNNs. To address this issue, we propose a new GW detection architecture, named convolutional transformer (CoT), that integrates self-attention and convolution mechanisms elegantly. CoT employs self-attention to capture long-term dependencies via a global receptive field. Meanwhile, CoT leverages convolutional projection to reduce computation cost and complement inductive bias of locality. The hybrid architecture allows us to aggregate informative features and detect GW signals more effectively and efficiently than purely convolution-based architectures. Moreover, we integrate CoT with spectral self-attention that attends to both the time and frequency axes, which better exploits frequency features in the spectrogram representation. Experimental results on the LIGO dataset demonstrate that CoT is superior to CNN-based methods in accuracy (0.6% higher AUC/F1 than 2D-CNN) and inference speed (1.15 times speedup than 1DCNN). To the best of our knowledge, this is the first time the self-attention mechanism has been employed in GW detection.

ABSTRACT To estimate the system performance of RTS/CTS scheme in an error‐prone WLAN channel, this paper proposes a new three‐dimensional Markov model, which considers the impact of bit error on all kinds of frames, and both station short retry limit and long retry limit. The system performance parameters including saturation throughput, packet drop probability, drop time, and average delay are derived using the new Markov model. By comparing the numerical results with simulation results, the model is proved to be more accurate than previous work. The numerical results show that the channel bit error rate has a significant impact not only on system performance, but also on the sensitivity of other system parameters including network scale, channel data rate, and packet length. Copyright © 2010 John Wiley & Sons, Ltd.