Related papers: Improve Video Representation with Temporal Adversa…

Vision Transformers (ViTs) have demonstrated superior performance across a wide range of computer vision tasks. However, structured noise artifacts in their feature maps hinder downstream applications such as segmentation and depth…

Although Deep Neural Networks(DNNs) have achieved successful applications in many fields, they are vulnerable to adversarial examples.Adversarial training is one of the most effective methods to improve the robustness of DNNs, and it is…

Video-language pre-trained models have shown remarkable success in guiding video question-answering (VideoQA) tasks. However, due to the length of video sequences, training large-scale video-based models incurs considerably higher costs…

Recent advancements in sequence prediction have significantly improved the accuracy of video data interpretation; however, existing models often overlook the potential of attention-based mechanisms for next-frame prediction. This study…

Adversarial Propagation (AdvProp) is an effective way to improve recognition models, leveraging adversarial examples. Nonetheless, AdvProp suffers from the extremely slow training speed, mainly because: a) extra forward and backward passes…

Dynamic recommendation systems aim to provide personalized suggestions by modeling temporal user-item interactions across time-series behavioral data. Recent studies have leveraged pre-trained dynamic graph neural networks (GNNs) to learn…

In this paper, we present augmentation inside the network, a method that simulates data augmentation techniques for computer vision problems on intermediate features of a convolutional neural network. We perform these transformations,…

Despite the effectiveness in improving the robustness of neural networks, adversarial training has suffered from the natural accuracy degradation problem, i.e., accuracy on natural samples has reduced significantly. In this study, we reveal…

While audio-visual learning equips models with a richer understanding of the real world by leveraging multiple sensory modalities, this integration also introduces new vulnerabilities to adversarial attacks. In this paper, we present a…

Transformer-based models have achieved state-of-the-art performance in various computer vision tasks, including image and video analysis. However, Transformer's complex architecture and black-box nature pose challenges for explainability, a…

Data augmentation plays a pivotal role in enhancing and diversifying training data. Nonetheless, consistently improving model performance in varied learning scenarios, especially those with inherent data biases, remains challenging. To…

Hardware support for deep convolutional neural networks (CNNs) is critical to advanced computer vision in mobile and embedded devices. Current designs, however, accelerate generic CNNs; they do not exploit the unique characteristics of…

We propose a self-supervised learning approach for videos that learns representations of both the RGB frames and the accompanying audio without human supervision. In contrast to images that capture the static scene appearance, videos also…

Adversarial learning methods are a promising approach to training robust deep networks, and can generate complex samples across diverse domains. They also can improve recognition despite the presence of domain shift or dataset bias: several…

Human behavior understanding in videos is a complex, still unsolved problem and requires to accurately model motion at both the local (pixel-wise dense prediction) and global (aggregation of motion cues) levels. Current approaches based on…

Recent advances in text-to-video diffusion models have enabled high-quality video synthesis, but controllable generation remains challenging, particularly under limited data and compute. Existing fine-tuning methods for conditional…

Most existing transformer based video instance segmentation methods extract per frame features independently, hence it is challenging to solve the appearance deformation problem. In this paper, we observe the temporal information is…

Temporal reasoning is a critical challenge in video-language understanding, as it requires models to align semantic concepts consistently across time. While existing large vision-language models (LVLMs) and large language models (LLMs)…

This report presents our method for Temporal Action Localisation (TAL), which focuses on identifying and classifying actions within specific time intervals throughout a video sequence. We employ a data augmentation technique by expanding…

Robust frame-wise embeddings are essential to perform video analysis and understanding tasks. We present a self-supervised method for representation learning based on aligning temporal video sequences. Our framework uses a transformer-based…