相关论文: How Severe is Benchmark-Sensitivity in Video Self-…

Self-supervised learning (SSL) has become the de facto training paradigm of large models where pre-training is followed by supervised fine-tuning using domain-specific data and labels. Hypothesizing that SSL models would learn more generic,…

Self-supervised learning (SSL) has advanced significantly in visual representation learning, yet comprehensive evaluations of its adversarial robustness remain limited. In this study, we evaluate the adversarial robustness of seven…

Recent self-supervised representation learning techniques have largely closed the gap between supervised and unsupervised learning on ImageNet classification. While the particulars of pretraining on ImageNet are now relatively well…

Mid-level vision capabilities - such as generic object localization and 3D geometric understanding - are not only fundamental to human vision but are also crucial for many real-world applications of computer vision. These abilities emerge…

This work studies feature representations for dense label propagation in video, with a focus on recently proposed methods that learn video correspondence using self-supervised signals such as colorization or temporal cycle consistency. In…

Content moderation systems classify images as safe or unsafe but lack spatial grounding and interpretability: they cannot explain what sensitive behavior was detected, who is involved, or where it occurs. We introduce the Sensitive…

The significant growth of surveillance camera networks necessitates scalable AI solutions to efficiently analyze the large amount of video data produced by these networks. As a typical analysis performed on surveillance footage, video…

Training deep neural networks typically requires large amounts of labeled data which may be scarce or expensive to obtain for a particular target domain. As an alternative, we can leverage webly-supervised data (i.e. results from a public…

Visual saliency models have enjoyed a big leap in performance in recent years, thanks to advances in deep learning and large scale annotated data. Despite enormous effort and huge breakthroughs, however, models still fall short in reaching…

Video-based large language models (Video-LLMs) have been recently introduced, targeting both fundamental improvements in perception and comprehension, and a diverse range of user inquiries. In pursuit of the ultimate goal of achieving…

Query-based video grounding is an important yet challenging task in video understanding, which aims to localize the target segment in an untrimmed video according to a sentence query. Most previous works achieve significant progress by…

Prior works on self-supervised pre-training focus on the joint training scenario, where massive unlabeled data are assumed to be given as input all at once, and only then is a learner trained. Unfortunately, such a problem setting is often…

Reliable and robust evaluation methods are a necessary first step towards developing machine learning models that are themselves robust and reliable. Unfortunately, current evaluation protocols typically used to assess classifiers fail to…

Transfer learning has witnessed remarkable progress in recent years, for example, with the introduction of augmentation-based contrastive self-supervised learning methods. While a number of large-scale empirical studies on the transfer…

Video is a promising source of knowledge for embodied agents to learn models of the world's dynamics. Large deep networks have become increasingly effective at modeling complex video data in a self-supervised manner, as evaluated by metrics…

People increasingly use videos on the Web as a source for learning. To support this way of learning, researchers and developers are continuously developing tools, proposing guidelines, analyzing data, and conducting experiments. However, it…

Although deep networks have significantly increased the performance of visual recognition methods, it is still challenging to achieve the robustness across visual domains that is necessary for real-world applications. To tackle this issue,…

Deep learning has raised hopes and expectations as a general solution for many applications; indeed it has proven effective, but it also showed a strong dependence on large quantities of data. Luckily, it has been shown that, even when data…

Weakly supervised data are widespread and have attracted much attention. However, since label quality is often difficult to guarantee, sometimes the use of weakly supervised data will lead to unsatisfactory performance, i.e., performance…

We propose a self-supervised method for learning motion-focused video representations. Existing approaches minimize distances between temporally augmented videos, which maintain high spatial similarity. We instead propose to learn…