Related papers: Efficient Robustness Assessment via Adversarial Sp…
We explore the black-box adversarial attack on video recognition models. Attacks are only performed on selected key regions and key frames to reduce the high computation cost of searching adversarial perturbations on a video due to its high…
Evaluating the robustness of Video classification models is very challenging, specifically when compared to image-based models. With their increased temporal dimension, there is a significant increase in complexity and computational cost.…
Adversarial Training (AT) has been shown to significantly enhance adversarial robustness via a min-max optimization approach. However, its effectiveness in video recognition tasks is hampered by two main challenges. First, fast adversarial…
We study the problem of attacking video recognition models in the black-box setting, where the model information is unknown and the adversary can only make queries to detect the predicted top-1 class and its probability. Compared with the…
In this paper, we explore the spatial redundancy in video recognition with the aim to improve the computational efficiency. It is observed that the most informative region in each frame of a video is usually a small image patch, which…
Recent research has revealed that reducing the temporal and spatial redundancy are both effective approaches towards efficient video recognition, e.g., allocating the majority of computation to a task-relevant subset of frames or the most…
This paper presents a comprehensive exploration of the phenomenon of data redundancy in video understanding, with the aim to improve computational efficiency. Our investigation commences with an examination of spatial redundancy, which…
Adversarial attacks on video recognition models have been explored recently. However, most existing works treat each video frame equally and ignore their temporal interactions. To overcome this drawback, a few methods try to select some key…
Video enhancement is a challenging problem, more than that of stills, mainly due to high computational cost, larger data volumes and the difficulty of achieving consistency in the spatio-temporal domain. In practice, these challenges are…
Long video understanding is heavily bottlenecked by a rigid one-shot paradigm: existing methods either densely encode videos at prohibitive memory and latency costs, or aggressively compress them into sparse frame sets that irreversibly…
Video moment retrieval targets at retrieving a moment in a video for a given language query. The challenges of this task include 1) the requirement of localizing the relevant moment in an untrimmed video, and 2) bridging the semantic gap…
Recent works have shown that the computational efficiency of video recognition can be significantly improved by reducing the spatial redundancy. As a representative work, the adaptive focus method (AdaFocus) has achieved a favorable…
Although Deep Neural Networks (DNNs) have demonstrated excellent performance, they are vulnerable to adversarial patches that introduce perceptible and localized perturbations to the input. Generating adversarial patches on images has…
No-Reference Video Quality Assessment (NR-VQA) plays an essential role in improving the viewing experience of end-users. Driven by deep learning, recent NR-VQA models based on Convolutional Neural Networks (CNNs) and Transformers have…
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…
Recently, video object segmentation (VOS) networks typically use memory-based methods: for each query frame, the mask is predicted by space-time matching to memory frames. Despite these methods having superior performance, they suffer from…
Deep neural networks exhibit excellent performance in computer vision tasks, but their vulnerability to real-world adversarial attacks, achieved through physical objects that can corrupt their predictions, raises serious security concerns…
The escalating threat of adversarial attacks on deep learning models, particularly in security-critical fields, has underscored the need for robust deep learning systems. Conventional robustness evaluations have relied on adversarial…
Image transmission and processing systems in resource-critical applications face significant challenges from adversarial perturbations that compromise mission-specific object classification. Current robustness testing methods require…
In recent years, video analysis tools for automatically extracting meaningful information from videos are widely studied and deployed. Because most of them use deep neural networks which are computationally expensive, feeding only a subset…